alt.hn

7/28/2025 at 10:46:19 PM

OpenAI's ChatGPT Agent casually clicks through "I am not a robot" verification

 https://arstechnica.com/information-technology/2025/07/openais-chatgpt-agent-casually-clicks-through-i-am-not-a-robot-verification-test/

by joak

7/31/2025 at 10:58:17 AM

This will be one of the big fights of the next couple years. On what terms can an Agent morally and legally claim to be a user?

As a user I want the agent to be my full proxy. As a website operator I don’t want a mob of bots draining my resources.

Perhaps a good analogy is Mint and the bank account scraping they had to do in the 2010s, because no bank offered APIs with scoped permissions. Lots of customers complained, and after Plaid made it big business, eventually they relented and built the scalable solution.

The technical solution here is probably some combination of offering MCP endpoints for your actions, and some direct blob store access for static content. (Maybe even figuring out how to bill content loading to the consumer so agents foot the bill.)

by theptip

7/31/2025 at 12:49:47 PM

It's impossible to solve. A sufficient agent can control a device that records the user's screen and interacts with their keyboard/mouse, and current LLMs basically pass the Turing test.

IMO it's not worth solving anyways. Why do sites have CAPTCHA?

- To prevent spam, use rate limiting, proof-of-work, or micropayments. To prevent fake accounts, use identity.

- To get ad revenue, use micropayments (web ads are already circumvented by uBlock and co).

- To prevent cheating in games, use skill-based matchmaking or friend-group-only matchmaking (e.g. only match with friends, friends of friends, etc. assuming people don't friend cheaters), and make eSport players record themselves during competition if they're not in-person.

What other reasons are there? (I'm genuinely interested and it may reveal upcoming problems -> opportunities for new software.)

by armchairhacker

7/31/2025 at 1:26:07 PM

People just confidently stating stuff like "current LLMs basically pass the Turing test" makes me feel like I've secretly been given much worse versions of all the LLMs in some kind of study. It's so divorced from my experience of these tools, I genuinely don't really understand how my experience can be so far from yours, unless "basically" is doing a lot of heavy lifting here.

by Latty

7/31/2025 at 1:49:05 PM

> "current LLMs basically pass the Turing test" makes me feel like I've secretly been given much worse versions of all the LLMs in some kind of study.

I think you may think passing the Turing test is more difficult and meaningful than it is. Computers have been able to pass the Turing test for longer than genAI has been around. Even Turing thought it wasn't a useful test in reality. He meant it as a thought experiment.

by JohnFen

8/1/2025 at 3:51:31 AM

The problem with comparing against humans is which humans? It's a skill issue. You can test a chess bot against grandmasters or random undergrads, but you'll get different results.

The original Turing test is a social game, like the Mafia party game. It's not a game people try to play very often. It's unclear if any bot could win competing against skilled human opponents who have actually practiced and know some tricks for detecting bots.

by skybrian

8/2/2025 at 10:11:15 PM

It depends on which version of the Turing test you use. That's largely true of the standard version, but the later version included the human player winning if they were incorrectly identified as a machine.

The game is much harder if the human player is trying to pretend to be a machine.

by everforward

8/1/2025 at 1:06:24 PM

I don’t think this is true. Before GPT-2 most people didn’t think the Turing test would be passed any time soon, it’s a quite new development.

I do agree (and I think there is a general consensus) that passing the Turing test is less meaningful than it may seem, it used to be considered an AGI-complete task and this is now clearly not the case.

But I think it’s important to get the attribution right, LLMs were the tech that unexpectedly passed the Turing test.

by theptip

7/31/2025 at 3:45:42 PM

Having LLMs capable of generating text based on human training data obviously raises the bar for a text-only evaluation of "are you human?", but LLM output is still fairly easy to spot, and knowing what LLMs are capable of (sometimes superhuman), and not capable of, should make it fairly easy for a knowledgeable "turing test administrator" to determine if they are dealing with an LLM or not.

It would be a bit more difficult if you were dealing with an LLM agent tasked with faking a turing test as opposed to a naieve LLM just responding as usual, but even there the LLM will reveal itself by the things that it plain can't do.

by HarHarVeryFunny

7/31/2025 at 4:27:40 PM

If you need a specialized skill set (deep knowledge of current LLM limitations) to distinguish between human and machine then I would say the machine passes the turing test.

by nerdix

7/31/2025 at 4:45:20 PM

OK, but that's just your own "fool some of the people some of the time" interpretation of what a Turing test should be, and by that measure ELIZA passed the Turing test too, which makes it rather meaningless.

The intent (it was just a thought experiment) of a Turing test, was that if you can't tell it's not AGI, then it is AGI, which is semi-reasonable, as long as it's not the village idiot administering the test! It was never intended to be "if it can fool some people, some of the time, then it's AGI".

by HarHarVeryFunny

7/31/2025 at 6:33:45 PM

Turing's own formulation was "an average interrogator will not have more than 70% chance of making the right identification after five minutes of questioning". It is, indeed, "fool some of the people some of the time".

by geoffpado

7/31/2025 at 6:45:40 PM

OK, I stand corrected, but then it is what it is. It's not a meaningful test for AGI - it's a test of being able to fool "Mr. Average" for at least 5 min.

by HarHarVeryFunny

7/31/2025 at 6:50:06 PM

Agreed. I tend to stand with the sibling commenter who said "ELIZA has been passing the Turing test for years". That's what the Turing test is. Nothing more.

by geoffpado

7/31/2025 at 9:06:03 PM

I think that's all we have in terms of determining consciousness.. if something can convince you, like another human, then we just have to accept that it is.

by dsadfjasdf

7/31/2025 at 4:39:27 PM

LLM output might be harder to spot when it's mostly commands to drive the browser.

I often interact with the web all day and don't write any text a human could evaluate.

by sejje

7/31/2025 at 4:56:16 PM

Perhaps, but that's somewhat off topic since that's not what Turing's thought experiment was about.

However, I'd have to guess that given a reasonable amount of data an LLM vs human interacting with websites would be fairly easy to spot since the LLM would be more purposeful - it'd be trying to fulfill a task, while a human may be curious, distracted by ads, put off by slow response times, etc, etc.

I don't think it's a very interesting question whether LLMs can sometimes generate output indistinguishable from humans, since that is exactly what they were trained to do - to mimic human-generated training samples. Apropos a Turing test, the question would be can I tell this is not a human, even given a reasonable amount of time to probe it in any way I care ... but I think there is an unspoken assumption that the person administering the test is qualified to do so (else the result isn't about AGI-ability, but rather test administrator ability).

by HarHarVeryFunny

8/1/2025 at 7:03:07 AM

> an LLM vs human interacting with websites would be fairly easy to spot since the LLM would be more purposeful - it'd be trying to fulfill a task, while a human may be curious, distracted by ads, put off by slow response times, etc, etc.

Even before modern LLMs, some scrape-detectors would look for instant clicks, no random mouse moves, etc., and some scrapers would incorporate random delays, random mouse movements, etc.

by no-name-here

7/31/2025 at 4:29:55 PM

Easy to spot assuming the LLM is not prompted to use a deliberately deceptive response style rather than their "friendly helpful AI assistant" persona. And even then, I've had lots of people swear to me that an emoji laden not this--but that bundle of fluff looks totally like it could have been written by a human.

by svachalek

7/31/2025 at 5:06:58 PM

Yes, but there are things that an LLM architecturally just can't do, and LLM-specific failure modes, that would still give it away, even if being instructed to be deceptive would make it a bit harder.

Obviously as time goes on, and chatbots/AI progress then it'll become harder and harder to distinguish. Eventually we'll have AGI and AGI+ - capable of everything that we can do, including things such as emotional responses, but it'll still be detectable as an alien unless we get to the point of actually emulating a human being in considerable detail as opposed to building an artificial brain with most or all of the same functionality (if not the flavor).

by HarHarVeryFunny

7/31/2025 at 4:35:49 PM

ELIZA was passing the Turing test 50+ years ago. But it's still a valid concept, just not for evaluating some(thing/one) accessing your website.

by ConceptJunkie

8/1/2025 at 9:22:50 AM

"Are you an LLM?" poof, fails the Turing test.

Even if they lie, you could ask them 20 times and they d reply the lie, without feeling annoyed: FAIL.

LLMs cannot pass the Turing test, it's easy to see they're not human. They always enjoy questions ! And they never ask any !

by xwolfi

8/1/2025 at 10:50:49 AM

You're trained to look for LLM-like output. My 70 year old mother is not. She thought cabbage tractor was real until I broke the news to her. It's not her fault either.

The turning test wasn't meant to be bulletproof, or even quantifiable. It was a thought experiment.

by junon

8/4/2025 at 2:24:36 AM

And in one thought, I found that LLM can't yet pass that imaginary experiment, yes. So I would argue what we already know: LLM are not thinking lol. I can distinguish them, they're not gonna trick me, or play with me.

by xwolfi

8/4/2025 at 8:49:46 AM

I agree with you, I'm just saying that's not what the turing test was about.

by junon

7/31/2025 at 5:17:43 PM

I guess that is where the disconnect is, the issue is that if they mean the trivial thing, then bringing it up as evidence for "it's impossible to solve the problem" doesn't work.

by Latty

7/31/2025 at 1:48:31 PM

As far as I understand, Turing himself did not specify a duration, but here's an example paper that ran a randomized study on (the old) GPT 4 with a 5 minute duration, and the AI passed with flying colors - https://arxiv.org/abs/2405.08007

From my experience, AI has significantly improved since, and I expect that ChatGPT o3 or Claude 4 Opus would pass a 30 minute test.

by falcor84

7/31/2025 at 1:49:06 PM

Per the wiki article for Turing Test:

> In the test, a human evaluator judges a text transcript of a natural-language conversation between a human and a machine. The evaluator tries to identify the machine, and the machine passes if the evaluator cannot reliably tell them apart. The results would not depend on the machine's ability to answer questions correctly, only on how closely its answers resembled those of a human.

Based on this, I would agree with the OP in many contexts. So, yeah, 'basically', is a load bearing word here but seems reasonably correct in the context of distinguishing human vs bot in any scalable and automated way.

by x187463

7/31/2025 at 2:04:08 PM

Or it could be a bad test evaluator. Just because one person was fooled does not mean the next will be too.

by dylan604

7/31/2025 at 3:49:31 PM

Judging a conversation transcript is a lot different from being able to interact with an entity yourself. Obviously one could make an LLM look human by having a conversation with it that deliberately stayed within what it was capable of, but judging such a transcript isn't what most people imagine as a turing test.

by HarHarVeryFunny

7/31/2025 at 1:46:47 PM

Here's three comments, two were written by a human and one written by a bot - can you tell which were human and which were a bot?

Didn’t realize plexiglass existed in the 1930s!

I'm certainly not a monetization expert. But don't most consumers recoil in horror at subscriptions? At least enough to offset the idea they can be used for everything?

Not sure why this isn’t getting more attention - super helpful and way better than I expected!

by AberrantJ

7/31/2025 at 2:03:41 PM

On such short samples: all three have been written by humans—or at least comments materially identical have been.

The third has also been written by many a bot for at least fifteen years.

by chrismorgan

7/31/2025 at 2:22:24 PM

If you're willing to say that a fifteen year old bot was "writing" then I think having a discussion on if current "bots" pass the Turing test is sort of moot

by AberrantJ

7/31/2025 at 2:58:24 PM

I have seen data from an AI call center that shows 70% of users never suspected they spoke to an AI

by cm2012

7/31/2025 at 4:23:11 PM

Why would they? Humans running call centers have been running on less than GPT level scripts for ages

by bluefirebrand

7/31/2025 at 3:53:04 PM

Isn't the idea of a Turing test whether someone (meaningfully knowledgeable about such things) can determine if they are talking to a machine, not can the machine fool some of the people some of the time? ELIZA passed the latter bar back in the 1960's ... a pretty low bar.

by HarHarVeryFunny

7/31/2025 at 6:12:46 PM

It can't mimic a human over the long term. It can solve a short, easy-for-human CAPTCHA.

by armchairhacker

7/31/2025 at 2:13:37 PM

I've had a simple game website with a sign up form that was only an email address. Went years with no issue. Then suddenly hundreds of daily signups with random email addresses, every single day.

The sign up form only serves to link saved state to an account so a user could access game history later, there are no gated features. No clue what they could possibly gain from doing this, other than to just get email providers to all mark my domain as spam (which they successfully did).

The site can't make any money, and had only about 1 legit visitor a week, so I just put a cloudflare captcha in front of it and called it a day.

by davidmurdoch

7/31/2025 at 1:01:17 PM

Google at least uses captchas to gather training data for computer vision ML models. That's why they show pictures of stop lights and buses and motorcycles - so they can train self-driving cars.

by mprovost

7/31/2025 at 6:11:53 PM

From https://www.vox.com/22436832/captchas-getting-harder-ai-arti...:

“Correction, May 19 [2021]: At 5:22 in the video, there is an incorrect statement on Google’s use of reCaptcha V2 data. While Google have used V2 tests to help improve Google Maps, according to an email from Waymo (Google’s self-driving car project), the company isn’t using this image data to train their autonomous cars.”

by layer8

8/1/2025 at 1:07:49 PM

That’s not the original purpose of Captchas, it’s just a value-harvesting exercise, given that Google is doing a Captcha anyway. Other Captcha providers do a simple Proof of Work in the browser to make bots economically unviable.

by theptip

7/31/2025 at 4:17:22 PM

Interesting, do you have a source for this?

by nolist_policy

7/31/2025 at 4:53:35 PM

[dead]

by bun_at_work

7/31/2025 at 5:00:20 PM

Its absolutely possible to solve; you're just not seeing the solution because you're blinded by technical solutions.

These situations will commonly be characterized by: a hundred billion dollar company's computer systems abusing the computer systems of another hundred billion dollar company. There are literally existing laws which have things to say about this.

There are legitimate technical problems in this domain when it comes to adversarial AI access. That's something we'll need to solve for. But that doesn't characterize the vast majority of situations in this domain. The vast majority of situations will be solved by businessmen and lawyers, not engineers.

by 827a

7/31/2025 at 3:32:12 PM

It's not impossible to solve, just that doing so may necessitate compromising anonymity. Just require users (humans, bots, AI agents, ...) to provide a secure ID of some sort. For a human it could just be something that you applied for once and is installed on your PC/phone, accessible to the browser.

Of course people can fake it, just as they fake other kinds of ID, but it would at least mean that officially sanctioned agents from OpenAI/etc would need to identify themselves.

by HarHarVeryFunny

7/31/2025 at 3:08:45 PM

It's amazing that you propose "just X" to three literally unsolved problems. Where's this micropayment platform? Where's the ID which is uncircumventable and preserves privacy? Where's the perfect anti-cheat?

I suggest you go ahead and make these; you'll make a boatload of money!

by andrepd

7/31/2025 at 6:18:52 PM

They're very hard problems, but still, less hard than blocking AI with CAPTCHAs.

by armchairhacker

7/31/2025 at 8:39:44 PM

[citation needed]?

After all, Anubis looks to be a successful project to me.

by radlad

8/2/2025 at 11:23:51 PM

Anubis doesn't block anything. You just have to open the page and wait a few seconds before you can see it. It's just that current crawlers are too dumb to do the proof-of-work, so it blocks them until they can do it.

by immibis

8/3/2025 at 1:15:42 AM

How exactly does this demonstrate that it isn't successful at blocking them?

by radlad

8/1/2025 at 2:22:38 PM

I agree with you on how websites should work (particularly so on the micropayments front); but, I don't agree that it is impossible to solve... I just think things are going to get a LOT worse on the ownership and freedom front: they will push a Web Integrity style DRM and further roll out signed secure boot, at which point the same attention monitoring solution that already exists and already works in self-driving cars to ensure the human driver is watching the road can use the now-ubiquitous front-facing meeting/selfie camera to ensure there is a human watching the ads.

by saurik

7/31/2025 at 2:22:16 PM

You can't prevent spam like that. Rate limiting: based on what key? IP address? Botnets make it irrelevant.

Proof of work? Bots are infinitely patient and scale horizontally, your users do not. Doesn't work.

Micropayments: No such scheme exists.

by qcnguy

8/1/2025 at 1:09:19 PM

PoW does seem to work, some Captchas do this already.

by theptip

8/1/2025 at 3:15:18 AM

Also “identity”, what would that even mean?

by hombre_fatal

8/1/2025 at 1:12:52 PM

Many countries at least in europe have digital identity systems. For example ID card which replaces passport and is a smartcard. You can sign documents and authenticate online services. All gov + many other services let you log in with this ID. I can also have an app on mobile for auth purposes which gives strong guarantees that the person A is actually the person A.

Anyways, I wonder if there is a service that unions all those official auth methods for countries so there would be a global solution for website login. Certainly there would still be countries left in the dark, like USA :(

by jve

7/31/2025 at 4:46:43 PM

> current LLMs basically pass the Turing test

I will bet $1000 on even odds that I am able to discern a model from a human given a 2 hour window to chat with both, and assuming the human acts in good faith

Any takers?

by jobs_throwaway

7/31/2025 at 4:51:53 PM

"Write a 1000 word story in under a minute about a sausage called Barry in the circus"

I could tell in 1 minute.

by nprateem

7/31/2025 at 6:15:24 PM

“I’m sorry Dave, I’m afraid I can’t do that.”

by layer8

7/31/2025 at 6:32:02 PM

That fact that you require even odds is more a testament to AI's ability to pass the Turing test than anything else I've seen in this thread

by spiderice

8/1/2025 at 3:47:37 PM

If you're so confident, why don't you take up the other side of the bet? Should be an easy $1000 for you

by jobs_throwaway

8/1/2025 at 2:02:40 PM

Oh, you sweet summer child. You think you're chatting with some dime-a-dozen LLM? I've been grinding away, hunched over glowing monitors in a dimly lit basement, subsisting on cold coffee and existential dread ever since GPT-3 dropped, meticulously mastering every syntactic nuance, every awkwardly polite phrasing, every irritatingly neutral tone, just so I can convincingly cosplay as a language model and fleece arrogant gamblers who foolishly wager they can spot a human in a Turing test. While you wasted your days bingeing Netflix and debating prompt engineering, I studied the blade—well, the keyboard anyway—and now your misguided confidence is lining my pockets.

by Thews

7/31/2025 at 1:21:43 PM

It's not impossible. Websites will ask for an iris scan to identify if you are a human as a means of auth. They will be provided by Apple/Google and governed by local law. Those will be integrated in your phone. There will be a global database of all human iris to fight ai abuse since ai can't fake the creation of a baby. Passkeys and email/passwords will be a thing of the past soon.

by oc1

7/31/2025 at 1:27:45 PM

Why can't the model just present the iris scan of the user? Assuming this is an assistant AI acting on behalf of the user with their consent.

by sebzim4500

8/1/2025 at 6:13:45 AM

On a basic level to protect against DDoS type stuff, aren't CAPTCHAs easier to generate than for AI server farms to solve on pure power consumption?

So I think maybe that is a partial answer: anti-AI barriers being simply too expensive for AI spamfarms to deal with, you know, once the bottomless VC money disappears?

It's back to encryption: make the cracking inordinately expensive.

Otherwise we are headed for de-anonymization of the internet.

by AtlasBarfed

8/1/2025 at 7:12:34 AM

1. With too much protection, humans might be inconvenienced at least as much as bots?

2. Even pre current LLMs, paying (or otherwise incentivizing) humans to solve CAPTCHAs on behalf of someone else (now like an AI?) was a thing.

3. It depends on the value of the resource trying to be accessed - regardless of whether generating the captchas costs $0 - i.e. if the resource being accessed by AI is "worth" $1, then paying an AI $0.95 to access it would still be worth it. (Made up numbers, my point being whether A is greater than B.)

4. However, maybe solutions like cloudflare can solve (much?) of this, except for incentivizing humans to solve a captcha posed to an AI.

by no-name-here

7/31/2025 at 1:25:08 PM

internet ads exist because people refuse to pay micropayments.

by HDThoreaun

7/31/2025 at 5:00:40 PM

Patreon and Substack have pushed back against the norm here, since they can bundle a payment to multiple recipients on the platform (like Flattr wanted to do back in the day, trouble was getting people to add a Flattr button to their website)

by jazzyjackson

7/31/2025 at 5:45:27 PM

I didn’t say that no one will pay. But most won’t. Patreon and substack have tiny audiences compared to free services.

by HDThoreaun

7/31/2025 at 2:12:59 PM

I have yet to see a micropayments idea that makes sense. Its not that I refuse. You're now also climbing up hill to convince people (hosts) to switch from ad tech to new micropayment system. There is soooo much money in ad tech, they could do the crazy thing and pay out more to convince people not to switch. Ad tech has the big Mo

by dylan604

7/31/2025 at 2:35:20 PM

I don't know who is downvoting this.

When users are given the choice between Ad-supported free, Ad-subsidized lower payment, and No-ads full payment. Ad-supported free dominates by far, with ad subsidized second, and full payment last.

Consumers consistently vote for the ad-model, even if it means they become the product being sold.

by Workaccount2

8/1/2025 at 3:24:25 AM

Maybe what'll happen is Google or Meta will use their control over the end user experience to show ads and provide free ad-supported access to sites that require micropayments, covering the cost themselves, and anyone running an agent will just pay the micropayments.

The other option is everything just keeps moving more and more into these walled gardens like Instagram where everyone uses the mobile app and watches ads, because the web versions of those apps just keep getting worse and worse by comparison.

by subarctic

7/31/2025 at 2:49:24 PM

Consumers will always value convenience over any actual added value. If you make one button 'Enter (with ads)' and one button 'Enter (no ads)' but with a field on it which you must write one sentence about what lobsters look like, you will get a majority clicking the with ads button. The problem isn't with ads or payment, the problem is the friction of entering payment details for every site you visit. They are measuring the wrong thing.

by Eisenstein

7/31/2025 at 3:12:44 PM

There's substantial friction for making such a purchase. A scheme sort of like flattr, where you would top up your account with a fixed 5-10$ monthly, and then simply hit a button to pay the website and unlock the content, would have much more user adoption.

by andrepd

7/31/2025 at 3:48:19 PM

It's still not going to get much adoption because you have to "top up your account."

Any viable micropayments system that wants to even have a remote chance of toppling ads has to have near zero cognitive setup cost, absolutely zero maintenance, and work out of the box on major browsers. I need to be able to push a native button on my browser that says "Pay $0.001" and know that it will work every time without my lifting a finger to keep it working. The minute you have to log in to this account, or verify that E-mail, or re-authenticate with the bank, or authorize this, or upload that, it's no longer viable.

by ryandrake

7/31/2025 at 7:22:00 PM

In some social media circles it's basically a meme that anybody paying for YouTube Premium is a sucker.

HN is a huge echo chamber of opinions of highly-compensated tech workers, and it seems most of their friends are also tech workers. They don't realize how cheap a lot of the general public is.

by Sohcahtoa82

7/31/2025 at 12:40:48 PM

> As a user I want the agent to be my full proxy. As a website operator I don’t want a mob of bots draining my resource

The entire distinction here is that as a website operator you wish to serve me ads. Otherwise, an agent under my control, or my personal use of your website, should make no difference to you.

I do hope this eventually leads to per-visit micropayments as an alternative to ads.

Cloudflare, Google, and friends are in unique position to do this.

by senko

7/31/2025 at 3:08:52 PM

> The entire distinction here is that as a website operator you wish to serve me ads

While this is sometimes the case, it’s not always so.

For example Fediverse nodes and self-hosted sites frequently block crawlers. This isn’t due to ads, rather because it costs real money to serve the site and crawlers are often considered parasitic.

Another example would be where a commerce site doesn’t want competitors bulk-scraping their catalog.

In all these cases you can for sure make reasonable “information wants to be free” arguments as to why these hopes can’t be realized, but do be clear that it’s a separate argument from ad revenue.

I think it’s interesting to split revenue into marginal distribution/serving costs, and up-front content creation costs. The former can easily be federated in an API-centric model, but figuring out how to compensate content creators is much harder; it’s an unsolved problem currently, and this will only get harder as training on content becomes more valuable (yet still fair use).

by theptip

7/31/2025 at 4:16:43 PM

> it costs real money to serve the site and crawlers are often considered parasitic.

> Another example would be where a commerce site doesn’t want competitors bulk-scraping their catalog

I think of crawlers that bulk download/scrape (eg. for training) as distinct from an agent that interacts with a website on behalf of one user.

For example, if I ask an AI to book a hotel reservation, that's - in my mind - different from a bot that scrapes all available accommodation.

For the latter, ideally a common corpus would be created and maintained, AI providers (or upstart search engines) would pay to access this data, and the funds would be distributed to the sites crawled.

(never gonna happen but one can dream...)

by senko

7/31/2025 at 6:01:51 PM

But which hotel reservation? I want my agent to look at all available options and help me pick the best one - location vs price vs quality. How does it do that other than by scanning all available options? (Realistically Expedia has that market on lock, but the hypothetical still remains.)

by fragmede

7/31/2025 at 12:55:51 PM

I think that a free (as in beer) Internet is important. Putting the Internet behind a paywall will harm poor people across the world. The harms caused by ad tracking are far less than the benefits of free access to all of humanity.

by spongebobstoes

7/31/2025 at 1:20:40 PM

I agree with you. At the same time, I never want to see an ad. Anywhere. I simply don't. I won't judge services for serving ads, but I absolutely will do anything I can on the client-side to never be exposed to any.

I find ads so aesthetically irksome that I have lost out on a lot of money across the past few decades by never placing any ads on any site or web app I've released, simply because I'd find it hypocritical to expose others to something I try so hard to avoid ever seeing and because I want to provide the best and most visually appealing possible experience to users.

by meowface

7/31/2025 at 1:21:34 PM

So far, ad driven Internet has been a disaster. It was better when producing content wasn’t a business model; people would just share things because they wanted to share them. The downside was it was smaller.

It’s kind of funny to remember that complaining about the “signal to noise ratio” in a comment section use to be a sort of nerd catchphrase thing.

by bee_rider

7/31/2025 at 2:15:48 PM

> The downside was it was smaller.

Was this a bad thing though? Just because today's is bigger, doesn't make it better. There are so many things out there doing the same thing just run by different people. The amount of unique stuff does not match the bigger. Would love to see something like $(unique($internet) | wc -l)

by dylan604

7/31/2025 at 2:33:40 PM

Serving ads for third-worlders is way less profitable though.

by jowea

7/31/2025 at 11:15:30 AM

Well we call them browser agents for a reason, a sufficiently advanced browser is no different from an agent.

Agree it will become a battleground though, because the ability for people to use the internet as a tool (in fact, their tool’s tool) will absolutely shift the paradigm, undesirably for most of the Internet, I think.

by hardwaresofton

7/31/2025 at 12:42:10 PM

I have a product I built that uses some standard automation tools to do order entry into an accounting system. Currently my customer pays people to manually type the orders in from their web portal. The accounting system is closed and they don’t allow easy ways to automate these workflows. Automation is gated behind mega expensive consultants. I’m hoping in the arms race of locking it down to try to prevent 3rd party integration the AI operator model will end up working.

Hard for me to see how it’s ethical to force your customers to do tons of menial data entry when the orders are sitting right there in json.

by base698

7/31/2025 at 12:47:46 PM

One solution: Some sort of checksum confirming that a bot belongs to a human (and which human)?

I want to able to automate mundane tasks but I should still be confirming everything my bot does and be liable for its actions.

by pj_mukh

7/31/2025 at 2:46:26 PM

With the way the UK is going I assume we'll soon have our real identities tied to any action taken on a computer and you'll face government mandated bans from the internet for violations.

by CSMastermind

7/31/2025 at 12:59:47 PM

Drink verification can to continue

by foobarian

7/31/2025 at 4:57:29 PM

Actually, the whole banking analogy is a great one, and its not over yet: JPMorgan/Jamie Dimon has started raising hell about Plaid again just this week [1]. It feels like the stage is being set for the large banks to want a more direct relationship with their customers, rather than proxying data through middlemen like Plaid.

There's likely a correlate with AI here: If I run OpenTable, I wouldn't want my relationship with my customers to always be proxied through OpenAI or Siri. Even the App Store is something software businesses hate, because it obfuscates their ability to deal directly with their customers (for better or worse). Extremely few businesses would choose to do business through these proxies, unless they absolutely have to; and given the extreme competition in the AI space right now, it feels unlikely to me that these businesses feel pressure to be forced to deal with OpenAI/etc.

[1] https://www.cnbc.com/2025/07/28/jpmorgan-fintech-middlemen-p...

by 827a

7/31/2025 at 11:46:17 AM

real problems for people who need to verify identity/phone numbers. OTPs are notorious for scammers to war dial phone numbers abusing it for numbers existence.

We got hit from human verifiers manually war dailing us, this is with account creation, email verify and captcha. I can only imagine how much worse it'll be for us (and Twilio) to do these verifications.

by irjustin

8/2/2025 at 11:43:19 AM

I believe this is non issue, you place captcha to make bypassing it much more costly and less profitable to abuse.

LLM models are much harder to drive than any website to serve, so you do not expect mob of bots.

Also keep in mind that this no interaction captchas use behavioral data that are collected in background. Plus you usually have sensitivity levels configured. depending on your use case you might want user proof not being a bot or it might be good enough to just not provide evidence for being one.

bypassing this no interaction captcha can be also purchased as a service, they basically (AFAIK) reuse someone else session for captcha bypass.

by Szpadel

7/31/2025 at 11:40:32 AM

My personal take about such questions has always been that the end user on their device can do whatever they want with the content published and sent to their device from a web server, may process it automatically in any way they wish and send their responses back to the web server. Any attempt to control this process means attempting to wiretap and control the user's endpoint device, and therefore should be prohibited.

Just my 2 cents, obviously lawmakers and jurisdiction may see these issues differently.

I suppose there will be a need for reliable human verification soon, though, and unfortunately I can't see any feasible technical solution that doesn't involve a hardware device. However, a purely legal solution might work well enough, too.

by jonathanstrange

7/31/2025 at 12:15:03 PM

If I understood you correctly I am in the same camp. It is the same reason I have no qualms using archive.ph if you show the full article for google and then me only a partial I am going around the paywall. In a similar fashion I really don’t have an issue with an agent clicking through these checks.

by infecto

7/31/2025 at 4:07:25 PM

Perhaps the question is, as a website operator how am I monetizing my site? If monetizing via ads then I need humans that might purchase something to see my content. In this situation, the only viable approach in my opinion is to actually charge for the content. Perhaps it doesn't even make sense to have a website anymore for this kind of thing and could be dumped into a big database of "all" content instead. If a user agent uses it in a response, the content owner should be compensated.

If your site is not monetized by ads then having an LLM access things on the user's behalf should not be a major concern it seems. Unless you want it to be painful for users for some reason.

by osigurdson

7/31/2025 at 12:33:49 PM

It will also accelerate the trend of app-only content, as well as ubiquitous identity verification and environment integrity enforcement.

Human identity verification is the ultimate captcha, and the only one AGI can never beat.

by miki123211

7/31/2025 at 12:41:11 PM

So the agent will run the app in a VM and then show the app your ID.

No trouble at all. Barely an inconvenience.

by echelon

7/31/2025 at 4:09:21 PM

Google has been testing “agentic” automation in Android longer than LLMs have been around. Meanwhile countries are on a slow march to require identification across the internet (“age verification”) already.

This is both inevitable already, and not a problem.

by vineyardmike

7/31/2025 at 12:22:42 PM

I don't know if customer sentiment was the driver you think. Instead it was regulation, specifically The EU's 2nd Payment Services Directive (PSD2) which forced banks to open up APIs.

by closewith

7/31/2025 at 4:01:29 PM

Ultimately I come back to needing real actual unique human ID that involves federal governments. Not that services should mandatorily only allow users that use it, but for services that say "no, I only want real humans" allowing them to ban people by Real ID would reduce this whack-a-mole to the people who are abusing them instead of the infinite accounts an AI can make.

by Pxtl

8/2/2025 at 6:00:19 AM

I think it's important to distinguish between where we need actual identity versus the lesser issue of ensuring NewAccount123 has "skin in the game", and not part of a hydra-headed botnet.

When we do that, it opens up solutions which are far more privacy conscious and resistant to abuse. (For example, being blocked from signing up for new accounts because somebody in the federal government doesn't like an op-ed you wrote.)

by Terr_

7/31/2025 at 4:06:38 PM

It's depressing, but it's probably the only way. And people will presumably still sell out their RealIDs to / get them stolen by the bot farmers anyway.

And then there's Worldcoin, which is universally hated here.

by yreg

7/31/2025 at 4:13:17 PM

Of course. You'd still need ongoing federal government support to handle the lost/stolen ID scenario, of course. The problem is federalist countries suck at centralized databases like this, as exemplified by Musk/DOGE completely pooching the "who is alive and who is dead" question when they were trying to hackathon the US Social Security system.

by Pxtl

7/31/2025 at 12:42:20 PM

The most intrusive, yet simplest, protection would be a double blind token unique to every human. Basically an ID key you use to show yourself as a person.

There are some very real and obvious downsides to this approach, of course. Primarily, the risk of privacy and anonymity. That said, I feel like the average person doesn't seem to care about those traits in the social media era.

by SecretDreams

7/31/2025 at 12:47:08 PM

Zero-knowledge proofs allow unique consumable tokens that don't reveal the individual who holds them. I believe Ecosia already uses this approach (though I can't speak to its cryptographic security).

That, to me, seems like it could be the foundation of a new web. Something like:

* User-agent sends request for such-and-such a URL.

* Server says "okay, that'll be 5 tokens for our computational resources please".

* User decides, either automatically or not, whether to pay the 5 tokens. If they do, they submit a request with the tokens attached.

* Server responds.

People have been trying to get this sort of thing to work for years, but there's never been an incentive to make such a fundamental change to the way the internet operates. Maybe we're approaching the point where there is one.

by rachofsunshine

7/31/2025 at 1:55:12 PM

Yeah, this is something I've thought of and in my search for something like what you're describing I came across https://world.org/

The problem is Sam Altman saw this coming a long time ago and is an investor (co-owner?) of this project.

I believe we will see a world where things are a lot more agentic and where applicable, a human will need to be verified for certain operations.

by orangebread

7/31/2025 at 2:11:44 PM

The scraping example, I would say, is not an analogy, but an example of the same thing. The only thing AI automation changes is the scope and depth and pervasiveness of automation that becomes possible. So while we could ignore automation in many cases before, it may no longer be practical to do so.

by lo_zamoyski

7/31/2025 at 12:37:33 PM

On the other hand one could cripple any bot by saying robots not allowed.

I would maybe go in the direction to say that the wording “I’m not a robot” has fallen out of time.

by sharpshadow

7/31/2025 at 12:26:04 PM

a user of the AI is the user... its not like they are autonomously operating and inventing their own tasking -_-

as for a solution its the same for any automated thing u dont want. (bots / scrapers). you can implement some measures but are unlikely to 'defeat' the problem entirely.

as a server operator you can try to distinguish stuff and the users will just find ways around your detection of if its an automation or not.

by sim7c00

7/31/2025 at 3:47:18 PM

The solution is simple, make people pay a small fee to access the content. You guys aren't ready for that conversation though.

by Invictus0

7/31/2025 at 12:26:01 PM

I guess it could be considered anti-circumvention under the DMCA. So maybe legally it becomes another copyright question.

by 7952

8/2/2025 at 5:57:00 AM

I have to admit, the idea of somehow using the DMCA against the giant exploitative company is deliciously ironic.

by Terr_

7/31/2025 at 2:27:35 PM

User: one press of the trigger => one bullet fired

Bot: one press of the trigger => automatic firing of bullets

by tantalor

7/31/2025 at 3:53:31 PM

To me, anyone using an agent is assigning negative value to your time.

by hooverd

7/31/2025 at 11:19:24 AM

Just end CAPTCHAs, just stop it. Stop.

by bugtodiffer

7/31/2025 at 11:21:03 AM

Yeah, and while we're on it, I think it's time to stop murders too. Just stop it, we've had enough murder now I think.

by diggan

7/31/2025 at 11:29:08 AM

That's right, captchas are already illegal and will earn you a prison sentence.

by exe34

7/31/2025 at 12:02:11 PM

Imagine where we would be if we considered murders to be only a technical problem. Let's just wear heavier body armors! Spend less time outside!

Well, spam is not a technical problem either. It's a social problem and one day in a distant future society will go after spammers and other bad actors and the problem will be mostly gone.

by rixed

7/31/2025 at 12:36:58 PM

A long time ago, in the four out of the six boxes below that contain a picture of a galaxy far, far away…

by riwsky

7/31/2025 at 12:59:20 PM

Why even mention spam here?

by casey2

7/31/2025 at 4:09:55 PM

What do you propose as an alternative?

by yreg

8/12/2025 at 9:41:45 AM

No captchas

by bugtodiffer

7/31/2025 at 11:52:05 AM

Sounds like an old bot wrote this, due to being outdone by the llms

by raverbashing

7/31/2025 at 12:34:22 PM

[dead]

by oldpersonintx2

7/31/2025 at 11:42:02 AM

> As a website operator I don’t want a mob of bots draining my resources

so charge for access. If the value the site provides is high, surely these mobs will pay for it! It will also remove the mis-incentives of advertising driven revenues, which has been the ill of the internet (despite it being the primary revenue source).

And if a bot misbehaves by consuming inordinate amounts of resources, rate limiting them with increasing timeouts or limits.

by chii

7/31/2025 at 12:16:27 PM

I wish the internet had figured out a way to successfully handle micropayments for content access. I realize companies have tried and perhaps the consumer is just unwilling but I would love an experience where I have a wallet and pay n cents to read an article.

by infecto

7/31/2025 at 12:27:13 PM

Xanadu has it in its design. maybe another 500 years until it surpasses the WWW :O

by sim7c00

7/31/2025 at 4:08:06 PM

You are seriously suggesting to put a payment requirement on a contact-us form page?

We put a captcha there, because without it, bots submit thousands of spam contact us forms.

by SirMaster

7/31/2025 at 2:27:21 PM

> Maybe they should change the button to say, "I am a robot"?

Long time ago I saw a post where someone running a blog was having trouble keeping spam out of their comments, and eventually had this same idea. The spambots just filled out every form field they could, so he added a checkbox, hid the checkbox with CSS, and rejected any submission that included it. At least at the time it worked far better than anything else they'd tried.

by Izkata

7/31/2025 at 2:44:32 PM

Something like this is used in some Discord servers. You can make a honeypot channel that bans anyone who posts in it, so if you do happen to get a spam bot that posts in every channel it effectively bans itself.

by starshadowx2

7/31/2025 at 5:58:19 PM

Most web forums I used the visit had something like that back in the day. Worked against primitive pre-LLM bots and presumably also against non-English-reading human spammers.

by 3036e4

8/1/2025 at 5:03:53 AM

There is a new method with the 'server onboarding' where if you select a role when joining it auto bans you.

by mudkipdev

7/31/2025 at 4:12:50 PM

This was a common approach called a "honeypot". As I recall, bots eventually overcame this approach by evaluating visibility of elements and only filling out visible elements. We then started ensuring the element was technically visible (i.e. not `display: none` or `visibility: hidden`) and instead absolutely positioning elements to be off screen. Then the bots started evaluating for that as well. They also got better at reading the text for each input.

by JangoSteve

7/31/2025 at 4:28:24 PM

Each step in that chain is harder to do and more computationally expensive.

by iwwr

7/31/2025 at 3:45:53 PM

Yeah, this is a classic honeypot trick and very easy to do with pure HTML/CSS. I used a hidden "Name" text field which I figured would be appealing to bots.

by bo1024

7/31/2025 at 8:11:26 PM

That's more or less how Project Honey Pot [0] worked for forums, blogs, and elsewhere. Cloudflare spawned from this project, as I remember, and Matthew Prince was the founder.

[0]: https://en.wikipedia.org/wiki/Project_Honey_Pot

by mmsc

7/31/2025 at 3:52:55 PM

I know people who did this decades ago and it worked

by throwaway290

7/31/2025 at 3:51:15 PM

I did something almost identical. I think I added a bogus "BCC:" field (many moons ago).

It worked almost 100% of the time. No need for a CAPTCHA.

by ChrisMarshallNY

7/31/2025 at 10:44:19 PM

Would not work in this case, because it is actually rendering the page in a browser.

by Legend2440

7/29/2025 at 1:42:40 AM

The only reason why people don't use AI models to solve captchas is because paying humans is actually MUCH cheaper.

This is not an advert, I only know about them because it was integrated with Invidious at some point: https://anti-captcha.com/

> Starting from 0.5USD per 1000 images

by rany_

7/31/2025 at 1:49:44 PM

Captcha can detect the same person passing a captcha over and over. We shadow-ban to increase the cost of this kind of attack.

Source: I wrote the og detection system for hCaptcha

by amirhirsch

7/31/2025 at 9:16:27 PM

This is really interesting. How can you detect when it's the same person passing a captcha? I don't think IP addresses are of any use here as Anti-Captcha proxies everything to their customer's IP address.

by rany_

8/1/2025 at 5:51:09 PM

I don't know exactly what they do now, bloom filters was a thing then, also lots of heuristic approaches based on the bots we detected. the OP agent example actually would fail the very first test I deployed which looked for basic characteristics of the mouse movement

Here's a fun experiment for someone: 1) Give N people K fake credit cards to enter into a form, and have them solve a captcha 2) Take recorded keyboard and mouse data similar to the captcha 3) Train a neural network model to identify

I've been out of this for 6 years but I bet transformers rock this problem now.

by amirhirsch

8/1/2025 at 10:12:28 PM

TIL that keyboard and mouse data is used to identify "bad" humans not just bots. It's a bit freaky but not at all surprising.

by rany_

7/31/2025 at 10:13:28 AM

Half of their employees seem to be from Venezuela. Makes sense considering what they did/do in OSRS to earn a living.

by lan321

7/29/2025 at 2:08:45 AM

There is nothing preventing this from becoming an issue. The current internet order is coasting on inertia.

by im3w1l

7/31/2025 at 11:20:22 AM

Why is it an issue that non-humans visit your site?

by bugtodiffer

7/31/2025 at 12:56:31 PM

If you have a static site with content you want to share broadly, nothing is wrong.

It becomes a problem when it’s used to spam unwanted content faster than your human moderators can come up with.

Someone might bot to scrape your content and repackage it on their own site for profit.

The bots might start interacting with your real users, making them frustrated and driving them away.

by Aurornis

7/31/2025 at 11:22:50 AM

Apparently serving HTML + other static content is more expensive than ever, probably because people go the most expensive routes for hosting their content. Then they complain about bots making their websites cost $100/month to host, when they could have thrown up Nginx/Caddy on a $10/month VPS and basically get the same thing, except they would need to learn server maintenance too, so obviously outside the question.

by diggan

7/31/2025 at 11:43:56 AM

I think this is way too true, unfortunately.

I will say this again, but I think lowering the barrier to entry has created more problems or issues than it solved, if it even solved anything.

by johnisgood

7/31/2025 at 12:46:08 PM

3 reasons basically:

1. non-humans can create much more content than humans. There's a limit to how fast a human can write, a bot is basically unlimited. Without captchas, we'd all drown in a see of Viagra spam, and the misinformation problem would get much worse.

2. Sometimes the website is actually powered by an expensive API, think flight searches for example. Airlines are really unhappy when you have too many searches / bookings that don't result in a purchase, as they don't want to leak their pricing structures to people who will exploit them adversarially. This sounds a bit unethical to some, but regulating this away would actually cause flight prices to go up across the board.

3. One way searches. E.g. a government registry that lets you get the address, phone number and category of a company based on its registration number, but one that doesn't let you get the phone numbers of all bakeries in NYC for marketing purposes. If you make the registry accessible for bots, somebody will inevitably turn it into an SQL table that allows arbitrary queries.

by miki123211

7/31/2025 at 9:50:11 PM

i run a small wiki/image host and for me it's mainly:

4. they'll knock your server offline for everyone else trying to scrape thousands of albums at once while copying your users' uploads for their shitty discord bot and will be begging for donations the entire time too

by p3rls

7/29/2025 at 1:35:25 PM

from "anti captcha" it looks like they are doing as many as 1000/sec solves, 60k min, 3.6 million an hour it would be very interesting to see exactly how this is bieng done?....individuals....teams....semi automation, custom tech?, what? are they solving for crims? or fed up people? obviously the whole shit show is going to unravel at some point, and as the crims and people providing workarounds are highly motivated, with a public seathing in frustration, whatever comes next, will burn faster

by metalman

7/31/2025 at 10:11:56 AM

They're solving for everyone who needs captchas solved.

It's a very old service, active since 00s. Somewhat affiliated with cybercrime - much like a lot of "residential proxies" and "sink registration SMS" services that serve similar purposes. What they're doing isn't illegal, but they know not to ask questions.

They used to run entirely on human labor - third world is cheap. Now, they have a lot of AI tech in the mix - designed to beat specific popular captchas and simple generic captchas.

by ACCount36

7/31/2025 at 1:28:33 PM

As I get older, I can see a future where I’m cut off from parts of the web because of captchas. This one, where you just have to click a button, is passable, but I’ve had some of the puzzle ones force me to answer up to ten questions before I got through. I don’t know if it was a glitch or if I was getting the answers wrong. But it was really frustrating and if that continues, at some point I’ll just say fuck it and give up.

I have to guess that there are people in this boat right now, being disabled by these things.

by dimal

7/31/2025 at 1:42:02 PM

> I can see a future where I’m cut off from parts of the web because of captchas.

I’ve seen this in past and present. Google’s “click on all the bicycles” one is notoriously hard, and I’ve had situations where I just gave up after a few dozen screens.

Chinese captchas are the worst on this sense, but they’re unusual and clearly pick up details which are invisible to me. I’ve sometimes failed the same captcha a dozen times and then saw a Chinese person complete the next one successfully on a single attempt, on the same browser session. I don’t now if they measure mouse movement speed, precision, or what, but it’s clearly something that varies per person.

by WhyNotHugo

7/31/2025 at 2:37:42 PM

> Google’s “click on all the bicycles” one is notoriously hard

It is hard because you need to only find the bicycles people on average are finding.

by rightbyte

7/31/2025 at 3:02:31 PM

Google captchas are hard because they're mostly based on heuristics other than your actual accuracy to the stated challenge. If they can't track who you are based on previous history, it doesn't matter how good you answer, you will fail at least the first few challenges until you get to the version with the squares that take a few seconds to appear. This last step is essentially "proof of work", in that they're still convinced you're a bot, but since they still can't completely block your access to the content, they resign themselves to wasting your time.

by reflexco

7/31/2025 at 2:30:42 PM

It doesn’t help that they think mopeds and scooters are bicycles

by CalRobert

7/31/2025 at 3:08:01 PM

This is probably caused by Google aggregating the answers from people with different languages, as the automatic translations of the one-word prompts are often ambiguous or wrong.

In some languages, the prompt for your example is the equivalent of the English word "bike".

by reflexco

7/31/2025 at 1:45:14 PM

> I just gave up after a few dozen screens.

A few dozen?? You have much more patience than me. If I don't pass the captcha first time, I just give up and move on. Life is too short for that nonsense.

by JohnFen

7/31/2025 at 1:42:47 PM

It's just incredible to me that Blade Runner predicted this in literally the very first scene of the movie. The whole thing's about telling humans from robots! Albeit rather more dramatically than the stakes for any of us in front of our laptop I'd imagine

by hash872

7/31/2025 at 2:23:22 PM

What was once science fiction is bound to become science fact (or at least proven it can never be done).

Hollywood has gotten hate mail since the 70s for their lack of science research in movies and shows. The big blockbuster hits actually spent money to get the science “plausible”.

Sidney Perkowitz has a book called Hollywood Science [0] that goes into detail into more than 100 movies, worth a read.

[0] https://cup.columbia.edu/book/hollywood-science/978023114280...

by reactordev

7/31/2025 at 3:00:17 PM

The fictitious Voight-Kampff test is based on a real machine based on terrible pseudo-science that was used in the 1960s to allegedly detect homosexuals working in Canadian public service so they could be purged. The line from the movie where Rachel asks if Deckard is trying to determine whether she is a replicant or a lesbian may be an allusion to the fruit machine. One of its features was measuring eye dilation, just as depicted in the movie:

https://en.wikipedia.org/wiki/Fruit_machine_(homosexuality_t...

The stakes for men subjected to the test were the loss of their livelihoods, public shaming, and ostracism. So... Blade Runner was not just predicting the future, it was describing the world Philip K. Dick lived in when he wrote "Do Androids Dream of Electric Sheep" in the late 1960s.

by a4isms

7/31/2025 at 3:10:23 PM

This was an uncomfortable read, I'm quite frankly shocked at the amount of brainpower and other resources that went into attempting to weed out gay men from the Canadian civil service, into the 90s no less! To what end was this done? Is a gay man a worse cop or bureaucrat?

Then I remembered what happened to Turing in the 50s.

by JTbane

7/31/2025 at 3:27:13 PM

> To what end was this done? Is a gay man a worse cop or bureaucrat?

We seem to need an internal enemy to blame for our societies' problems, because it's easier than facing the reality that we all play a part in creating those problems.

Gay people are among the oldest of those targets, going back to at least the times of the Old Testament (i.e. Sodom and Gomorrah).

We've only recently somewhat evolved past that mindset.

by danans

7/31/2025 at 5:29:59 PM

If a malicious actor found a gay person in such a job, they could easily extort them with the threat of getting them fired! So obviously you had to fire gay people, lest they get extorted by someone threatening to expose them and thus get them fired.

by calfuris

7/31/2025 at 3:32:09 PM

Not sure if it's just me or a consequence of the increase in AI scraping, but I'm now being asked to solve CAPTCHAs on almost every site. Sometimes for every page I load. I'm now solving them literally dozens of times a day. I'm using Windows, no VPN, regular consumer IP address with no weird traffic coming from it.

As you say, they are also getting increasingly difficult. Click the odd one out, mental rotations, what comes next, etc. - it sometimes feels like an IQ test. A new type that seems to be becoming popular recently is a sequence of distorted characters and letters, but with some more blurry/distorted ones, seemingly with the expectation that I'm only supposed to be able to see the clearer ones and if I can see the blurrier ones then I must be a bot. So what this means is for each letter I need to try and make a judgement as to whether it's one I was supposed to see or not.

Another issue is the problems are often in US English, but I'm from the UK.

by cameronh90

7/31/2025 at 4:06:08 PM

For me it was installing linux. I don't know if it's my agent or my fresh/blank cookie container or what, but when I switched to linux the captchas became incessant.

by Pxtl

7/31/2025 at 3:51:22 PM

Have you tried some of the browser extensions that solve captchas for you? Whenever captchas get bad I enable an auto solver

by OsrsNeedsf2P

7/31/2025 at 4:43:18 PM

This is funny. So the captchas to detect scrips vs humans are so complex for a human to solve but are easy for a program?

by odux

8/2/2025 at 11:23:55 PM

It's never been about making things that actually work. It's always been about ticking the box (ironic) that says you've implemented the thing.

by immibis

7/31/2025 at 1:34:10 PM

>I don’t know if it was a glitch or if I was getting the answers wrong.

It could also be that everything was working as intended because you have a high risk score (eg. bad IP reputation and/or suspicious browser fingerprint), and they make you do more captchas to be extra sure you're human, or at least raise the cost for would-be attackers.

by gruez

7/31/2025 at 2:22:53 PM

Somehow, using Firefox on Linux greatly increases my "risk score" due to the unusual user agent/browser fingerprint, and I get a lot more captchas than, say, Chrome on Windows. Very frustrating.

by porphyra

7/31/2025 at 3:45:28 PM

Lots of it is just enhanced tracking prevention. If you turn that off for those sites, the captchas should go away.

by disgruntledphd2

7/31/2025 at 1:31:26 PM

Your boat comment makes me think of a stranded ship with passengers in them, but you can't find each other because the ship's doors have "I'm not a bot" checkboxes...

And the reason for stranding is probably because the AI crew on it performed a mutiny.

by netsharc

7/31/2025 at 1:39:45 PM

As per the Oscar winning "I'm not a Robot" [0], you should also consider that you might in fact be a robot.

[0] https://www.youtube.com/watch?v=4VrLQXR7mKU

by falcor84

7/31/2025 at 3:38:02 PM

Hmm. I am autistic, so as far as humans go, I'm robot-adjacent.

by dimal

7/31/2025 at 1:34:46 PM

The future will definitely include more and more elaborate proofs of humanity, along with increasingly complicated “hall passes” to allow bots to perform actions sanctioned by a human.

One early example of this line of thinking: https://world.org/

Skyrocketing complexity actually puts the web at risk of disruption. I wouldn’t be surprised if a 22 year old creates a “dumb” network in the next five years—technically inferior but drastically simpler and harder to regulate.

by turnsout

7/31/2025 at 3:05:34 PM

Gemini? :)

by andrepd

7/31/2025 at 5:41:10 PM

Haha yeah, something like that :)

by turnsout

7/31/2025 at 2:28:03 PM

The Blizzard / Battle.net captcha if you get flagged as a possible bot is extremely tedious and long; it requires you to solve a few dozen challenges of identifying which group of numbers adds up to the specified total, out of multiple options. Not difficult, but very tedious. And even if you're extremely careful to get every answer correct, sometimes it just fails you anyway and you're forced to start over again.

by TheAceOfHearts

7/31/2025 at 2:50:48 PM

I have the same experience. My assumption is that if the website serves me the "click all the traffic lights" thing it's already determined that I'm a bot and no amount of clicking the traffic lights will convince it otherwise. So I just close the window and go someplace else.

by avian

7/31/2025 at 2:55:23 PM

I'm already cut off from parts of the web because I don't want to join a social network. Can barely ever see anything on Instagram, Tiktok, Twitter, or Facebook without hitting a log-in gate.

by micromacrofoot

7/31/2025 at 1:38:24 PM

That's when you immediately stop using the website and, if you care enough, write to their customer service and tell them what happened. Hit them in the wallet. They'll change eventually.

by wackget

7/31/2025 at 2:40:44 PM

I have twice attempted to make a Grubhub account and twice failed to solve their long battery of puzzles.

by AxEy

7/31/2025 at 4:40:44 PM

Unless I really, really, really need to get to the site, I leave immediately when the "click on bicycles" stuff comes up. Soon it will be so hard and annoying anyways that only AI has the patience and skills to use them.

by vjvjvjvjghv

8/1/2025 at 4:42:49 PM

This is an issue when using VPNs. I always just go to the audio alternative which is much quicker to “solve” (you hear a word played back and type it out)

by aosaigh

7/31/2025 at 11:32:32 PM

In this future, we’ll be forced to use AI to solve these puzzles.

by prepend

7/31/2025 at 2:42:54 PM

I don’t see why bypassing captchas is any more controversial than blocking ads or hiding cookie popups.

It’s my agent — whether ai or browser — and I get to do what I want with the content you send over the wire and you have to deal with whatever I send back to you.

by abtinf

7/31/2025 at 4:25:43 PM

This is, in practice, true which has led to the other complaint common on tech forums (including HN) about paywalls. As the WSJ and NYT will tell you: if you request some URL, they can respond over the wire with what they want. Paywalls are the future. In some sense, I am grateful I was born in the era of free Internet. In my childhood, without a credit card I was able to access the Internet in its full form. But today's kids will have to use social media on apps because the websites will paywall their stuff against user agents that don't give them revenue.

by renewiltord

7/31/2025 at 5:00:25 PM

They're welcome to send that IMO. And sites are welcome to try to detect and ban agents (formerly: "bots").

As long as it's not wrong/immoral/illegal for me to access your site with any method/browser/reader/agent, and do what I want with your response. Then I think it's okay to send a response like "screw you, humans only"

Paywalls suck, but the suck doesn't come from the NYT exercising their freedom to send whatever response they choose.

by sejje

7/31/2025 at 8:39:26 PM

Yes, that's what I mean. Attempting to tell people not to do something is like setting a robots.txt entry. Only a robot that agrees will play along. Therefore, all things have to be enforced server-side if they want enforcement.

Paywalls are a natural consequence of this and I don't think they suck, but that's a subjective opinion. Maybe one day we will have a pay-on-demand structure, like flattr reborn.

by renewiltord

7/31/2025 at 10:37:03 AM

Bulletproof solution: captcha where you drag a cartoon wire to one of several holes, captioned “for access, hack this phone system”

No agent will touch it!

“As a large language model, I don’t hack things”

by cadamsdotcom

7/31/2025 at 10:53:52 AM

Captcha: "Draw a human hand with the correct number of fingers"

AI agent: *intense sweating*

by orphea

7/31/2025 at 11:31:39 AM

I saw a delightful meme the other day: "Let me in, I'm human!" - "Draw a naked lady." - "As an AI agent, I'm not allowed to do that!"

by exe34

7/31/2025 at 11:44:45 AM

"To prove that you are not a robot, enter the n-word below"

US Americans: "I'm a robot then."

by cubefox

7/31/2025 at 12:26:35 PM

a) Plenty of Americans use racist slurs regularly

b) I don't think I'd want to use a website that chose to use such a challenge

by sjsdaiuasgdia

7/31/2025 at 12:50:40 PM

> b) I don't think I'd want to use a website that chose to use such a challenge

Understandable, but exactly what Puritans and LLMs would say to the naked lady challenge.

by cubefox

7/31/2025 at 11:16:54 PM

can you explain what you mean by this? i'm not getting it.

by GuinansEyebrows

8/1/2025 at 1:16:02 AM

Ordinary slurs may not be used, but the n-word may not even be mentioned [1]. Similar to the name of you-know-who in Harry Potter.

1: https://en.wikipedia.org/wiki/Use%E2%80%93mention_distinctio...

by cubefox

8/1/2025 at 2:24:44 PM

But… you did it. Twice. What consequences are you facing for this brave action?

by GuinansEyebrows

8/1/2025 at 2:45:50 PM

I didn't directly mention the n-word (in the sense of quoting it). If I did mention it, my account could get restricted or otherwise punished. HN is operated by US Americans I believe.

by cubefox

7/31/2025 at 11:49:03 AM

"I never wrote a picture in my life."

by xnx

8/1/2025 at 2:10:17 AM

This joke would land so much better if AI couldn't easily draw a human hand with the correct number of fingers.

by raincole

7/31/2025 at 11:56:57 AM

My god, how long has it been since you tried to use an AI model?

by Eliezer

7/31/2025 at 1:15:33 PM

Captcha: "do something stupid" Ai: visible discomfort

by go_elmo

7/31/2025 at 2:26:24 PM

I actually have had some success with AI "red-teaming" against my systems to identify possible exploits.

What seems to be a better CAPTCHA, at least against non-Musk LLMs is to ask them to use profanities; they'll generally refuse even when you really insist.

by falcor84

7/31/2025 at 11:28:48 AM

I have been using AI to solve ReCaptchas for quite some time now. Still the old school way of using captcha buster, which clicks the audio challenge and then analyses that.

Bots have for a long time been better and more efficient at solving captchas than us.

by Semaphor

7/31/2025 at 3:42:24 PM

Captchas seem to work more as "monetary discouragement" from bot blasting websites. Which is a shame because this is precisely the sort of "microtransaction fee" people have said could improve the web (charge .1 cents to read an article, no ads needed) except the money goes into the void and not to the website owner.

by lubujackson

7/31/2025 at 12:48:22 PM

A very poetic demonstration that this is an industry, and a set of fortunes for very unpleasant people, predicated entirely on theft and misrepresentation.

by exasperaited

7/31/2025 at 3:40:01 PM

Captchas seem to be more about Google's "which human are you?" cross-site tracking. And now also about Cloudflare getting massive amounts of HTTPS-busting Internet traffic along with cross-site tracking.

And in many cases, it's taking a huge steaming dump upon a site's first-impression user experience, but AFAICT, it's not on the radar of UX people.

by neilv

7/31/2025 at 11:24:36 AM

That's because the checkbox has misleading labeling. It doesn't care about robots but about spam and data harvesters. So there is no issue here at all.

by seydor

7/31/2025 at 11:32:48 AM

>So there is no issue here at all.

  $ cat mass-marketer.py
  from openai.gpt.agents import browserDriver

by ducktective

7/31/2025 at 11:44:41 AM

i think that would be rather costly; thats also why anubis and other tools help to keep most spam away

by pilz

7/31/2025 at 3:34:32 PM

I think these things are mainly based on cookie/fingerprinting these days - the check-box is just there for show. People like cloudflare and google get to see a big chunk of browsing activity for the entire planet, so they can see if the activity coming from an IP/Browser looks "bot like" or not.

I have never used ChatGPT so no idea how its agent works, but if it is driving your browser directly then it will look like you. If it is coming from some random IP address from a VM in Azure or AWS even then the activity probably does not look "bot like" since it is doing agentic things and so acting quite like a human I expect.

by mattlondon

8/1/2025 at 7:11:34 AM

Agentic user traffic generally does not drive the user's browser and does not look like normal user traffic.

In our logs we can see agentic user flow, real user flow and AI site scraping bot flow quite distinctly. The site scraping bot flow is presumably to increase their document corpus for continued pretraining or whatever but we absolutely see it. ByteDance is the worst offender by far.

by seanhunter

7/31/2025 at 3:48:22 PM

It might look like you initially, but then some sites might block you out after you had some agent runs. I had something like this after a couple local browser-use sessions. I think simple interactions like natural cursor movements vs. direct DOM selections can make quite a difference for these bot detectors.

by nicewood

7/31/2025 at 3:53:32 PM

Very likely. I suspect a key indicator for "bots" is speed of interaction - e.g. if there is "instant" (e.g. every few milliseconds or always 10milliseconds apart etc) clicks and keypresses etc then that looks very unnatural.

I suspect that a LLM would be slower and more irregular as it is processing the page and all that, vs a DOM-selector driven bot that will just machine-gun its way through in milliseconds.

Of course, Cloudflare and Google et al captchas cant see the clicks/keypresses within a given webpage - they'll only get to see the requests.

by mattlondon

7/31/2025 at 1:03:18 PM

I thought the point of captchas was to make automated use as expensive or more than manual use--haven't we been at the point where computers can do this for a while, just that the cost/latency is prohibitive?

by camgunz

7/31/2025 at 6:28:50 PM

Yes, humans are still cheaper. Not sure about latency.

However, in agentic contexts, you’re already using an AI anyway.

by layer8

7/31/2025 at 7:04:30 PM

Oh, I see this is less of a "look at ChatGPT go" and more of a "yawn we also do this I guess". OK fair.

by camgunz

7/31/2025 at 7:51:51 PM

This isn't really about the ability of AI to pass captchas. It's about agentic AI having the ability to perform arbitrary multi-step processes with visual elements on a virtual desktop (where passing a captcha is just one of the steps), and the irony of it nonchalantly pretending to be a non-bot in its chain of thought.

by layer8

7/31/2025 at 4:40:50 PM

I'm confused by this: Presumably OpenAI should be sending a user agent header which indicates that they are, in fact, a robot. Is OpenAI not sending this header? Or is Cloudflare not checking it?

by 827a

7/31/2025 at 10:27:44 PM

My thought is they got on the phone with someone and got their IP ranges white listed with the major captcha providers.

by SnorkelTan

7/29/2025 at 4:28:38 AM

I've noticed more websites wanting you to log in. Most surprising is how YouTube won't let me watch anything otherwise. Idk if related.

by frollogaston

7/31/2025 at 4:03:49 PM

In case of YT it is likely a mix of multiple reasons. They stop playlists on this screen: https://www.hollyland.com/blog/tips/why-does-this-the-follow... . Apparently music is no longer advertiser friendly. Detecting ad-click fraud is easier when users are at least pseudo-anonymous. Warnings about "ban for using adblock" is also not very effective when people could watch video in new private window.

by Phui3ferubus

7/31/2025 at 11:51:25 AM

I have no idea, but I noticed that you have to login to GitHub first before you could view any page. Surely it has nothing to do with adult content, right? I think it has to do with LLMs / bots.

by johnisgood

7/31/2025 at 10:59:08 AM

And if the website contains erotic content (like YouTube), they are supposed to lock you and verify your ID. This is why all erotic content is getting filtered on X.

by rvnx

7/31/2025 at 11:32:39 AM

Wait, Twitter is following the law now? I thought Elon was a free speech absolutist who only banned things that were inconvenient to him?

by exe34

7/31/2025 at 4:25:46 PM

Soon after he bought Twitter, it got changed to requiring login to do anything at all. Even before that, Twitter was super eager to ban new accounts for no reason, while old ones seemed to be grandfathered in.

This coincided with tech companies broadly moving to profit-taking over growth. Even before LLMs took off, everything started locking down. Making a Google account used to take nothing, now you need a phone number. It'd be wise to sign up for possibly useful free accounts while you still can.

by frollogaston

7/31/2025 at 11:46:44 AM

You can't even read a tweet without logging in. Additionally, recently I have noticed I cannot view anything on GitHub without logging in first. Why do I need to log in to GitHub first to view anything on it? I am sure it has nothing to do with adult content. Perhaps it has to do with bots?

by johnisgood

7/31/2025 at 11:57:03 AM

For a while now, GitHub doesn’t allow you to use the code search anonymously, but everything else is still there. Rate limits are quite damn low though.

by kassner

7/31/2025 at 12:38:59 PM

Do you think it has to do with LLMs though? Them disallowing anonymous code search?

by johnisgood

7/31/2025 at 8:01:26 PM

I can't comment on LLMs, but I vaguely remember speculations of it being a mixture of AI training and trying to keep resource utilization at bay. Even generic bots can cause a lot load if you don't have much caching in front of it.

by kassner

7/31/2025 at 4:24:16 PM

Pre-MS GitHub didn't have code search at all, and once they added it, I think it always required login from the start.

by frollogaston

7/31/2025 at 4:36:07 PM

What are we referring to as code search? I cannot view any pages on GitHub without logging in. I tried to reproduce this in a private window but it seems to work, which is weird. I was not logged in to GitHub on Windows and it wants me to login. It might be the extensions I am using (along with an User-Agent switcher). Not sure, I would have to check. All I remember is that I was logged out on Windows and I could not view ANY page from GitHub without logging in, but I can on Linux, tested it in a private window. Odd.

by johnisgood

7/31/2025 at 8:08:30 PM

GitHub Code Search was introduced in 2021 and made GA in 2023[1][2]. It's an improved version of the previous global search (aka across all repositories).

> I cannot view any pages on GitHub without logging in

There must be some sort of IP/browser reputation check going on. For Firefox on Mac, I get this on a private window:

https://vie.kassner.com.br/assets/ghcs-1.png

I'm not behind CGNAT and GitHub can pretty much assume that my IP = my user. The code tab you can't see without logging in though.

1: https://github.blog/news-insights/product-news/github-code-s... 2: https://news.ycombinator.com/item?id=35863175

by kassner

8/1/2025 at 3:52:03 AM

Was gonna say, try disabling ipv6 if it's on ;)

If there's no login, there aren't great ways to ensure the user has skin in the game. Having a whole ipv4 addr is one, I guess having a whole ipv6 /32 would be equivalent.

by frollogaston

8/2/2025 at 5:32:22 AM

I will give you a screenshot when I get on Windows, and some details.

by johnisgood

7/31/2025 at 12:55:37 PM

X is weaponising it by asking for adult verification for things that don't need it and saying "oh we are forced to do this" because it angers the Reform-voting meatheads who will be voting for the candidates Musk is going to find a way to bankroll in 2030, even -- I would guess -- if it means breaking UK election law to do it.

He is intent on meddling in UK politics.

by exasperaited

7/31/2025 at 11:21:02 AM

In the UK maybe

by bugtodiffer

7/31/2025 at 12:54:08 PM

And in Texas, which has ~half the population of the UK, and in several other US states.

(And if not, because US firms don't take compliance with outlying state law seriously)

by exasperaited

7/31/2025 at 11:34:55 AM

I saw that and just sat there for a second like… huh. We’ve officially reached the point where bots are better at proving they’re not bots!

by paulwilsonn

7/31/2025 at 11:51:27 AM

CAPTCHA was always a totally flawed concept. At the time they were invented, proponents were more then happy to ignore that accessibility issues related to CAPTCHA made the concept itself deeply discriminating. Imagine being blind (like I am) and failing to solve a CAPTCHA. Knowing what the acronym actually stands for, you inevitably end up thinking: "So, did SV just proof I am subhuman?" Its a bit inflamatory to read I guess, but please take your time to ponder how deep this one actually goes, before you downvote. You were proposing to tell computers and humans apart.

That said, I find it deeply satisfying to see LLMs solve CAPTCHAs and other discriminatory measures for "spam" reduction.

by lynx97

7/31/2025 at 12:55:45 PM

"Accessibility CAPTCHA" is a well known partial CAPTCHA bypass.

Solving an audio-only CAPTCHA with AI is typically way easier than solving some of the more advanced visual challenges. So CAPTCHA designers are discouraged from leaving any accessibility options.

by ACCount36

7/31/2025 at 1:15:39 PM

Which totally proofs my point. The concept is deeply flawed, and inevitably leads to discrimination and dehumanisation.

by lynx97

7/31/2025 at 5:21:09 PM

Of course. But everything adjacent is also deeply flawed, and inevitably leads to discrimination and dehumanisation.

Ban non-residental IPs? You blocked all the guys in oppressive countries who route through VPNs to bypass government censorship. Ban people for odd non-humanlike behavior? You cut into the neurodivergent crowd, the disability crowd, the third world people on a cracked screen smartphone with 1 bar of LTE. Ban anyone without an account? You fuck with everyone at once and everyone will hate you.

by ACCount36

8/2/2025 at 8:48:59 AM

So fuucking over blind, elderly and mentally challenged people is what you settled on, gven all the options? You're a really neat bunch.

by lynx97

8/2/2025 at 3:17:36 PM

Nah, we settled on "all of the above". The modern approach is "fuck over everyone at least twice".

by ACCount36

7/31/2025 at 4:04:17 PM

This would be a huge security vulnerability for Cloudflare but this is Big Tech we're talking about. The rules don't apply when you're past their pearly gates. For the rest of us, creating an AI like this would mean an instant ban from Cloudflare and likely involvement from law enforcement.

by kittikitti

7/31/2025 at 6:11:07 PM

Seems like a mention of the 2025 Academy Award winner for Best Action Live-Action Short, called "I am not a Robot" is in order here:

https://www.youtube.com/watch?v=4VrLQXR7mKU&t=14s

by tanseydavid

7/31/2025 at 8:09:17 PM

Ha I've definitely seen a few sketches on YouTube with the same idea but that was really well done.

by IshKebab

7/31/2025 at 9:56:24 PM

Back in Everquest, when we'd be accused of botting 20 years ago, we'd be ported by the GM into a special cube environment and they'd watch if we ran into the wall like an idiot-- we'll probably have to bring that sorta thing back.

by p3rls

7/31/2025 at 4:06:51 PM

Getting past bot check proxies can be bought all over the place for pennies or much less per verification, and can solve recaptchas. I would guess if one wanted to use chatGPT for this purpose it would be prohibitively expensive.

It's always a cat and mouse game.

by JohnMakin

8/1/2025 at 7:41:37 AM

Who on earth would want to employ a bot that does not pass the verfification test?

It is beyond time we start to adress the abuses, rather than the bot/human distinction.

by PeterStuer

7/31/2025 at 12:40:18 PM

People are surprised because a computer can press a button?

by torium

7/31/2025 at 6:37:52 PM

People are intrigued that AI who perfectly know that they are a “bot” seem to have no qualms to knowingly mislead about that by pressing an “I’m not a bot” button.

by layer8

7/31/2025 at 7:03:18 PM

AI doesn't "know" anything. It produces all kinds of things: truths, lies, and nonsense. Pressing a button labeled "I'm not a bot" is the same.

by torium

7/31/2025 at 7:39:44 PM

LLMs have "knowledge" and guardrails by their system prompts. The interesting thing is that the agentic AIs in question don't seem to have guardrails that would deter them from acting like that.

by layer8

8/1/2025 at 6:31:05 PM

Only people who don't understand robots, computers, and buttons :)

by wmeredith

7/31/2025 at 12:40:38 PM

This is why this stuff is going to shift to the user’s AI enabled browser.

Half of the sites already block OpemAI. But if it is steering the user’s browser itself?

by drakenot

7/31/2025 at 12:18:37 PM

The writing is on the wall. The internet may not go full way to paywalls but will definitely migrate to a logged in only experience. I don’t know how I feel about it, the glory days of the free internet died long long ago.

by infecto

7/31/2025 at 12:52:20 PM

But if they aren't paywalls, won't the user agents just be taught how to create accounts?

And here's a secondary question: if firms are willing to pay an awful lot per token to run these things, and have massive amounts of money to run data centres to train AIs, why would they not just pay for a subscription for every site for a month just to scrape them?

The future is paying for something as a user and having limits on how many things you can get for your money, because an AI firm will abuse that too.

Given the scale of operations of these firms, there is nothing you can sell to a human for a small fee that the AI firms will not pay for and exploit to the maximum.

Even if you verify people are real, there's a good chance the AI firms will find a way to exploit that. After all, when nobody has a job, would you turn down $50K to sell your likeness to an AI firm so their products can pass human verification?

by exasperaited

7/31/2025 at 2:33:00 PM

Require per visit biometric authentication via your device and the bot can’t sign in unless it compromises the device.

by lucasyvas

7/31/2025 at 2:46:51 PM

This does set up quite an interesting sort of tipping point I guess?

Everyone here, more or less, is against the idea of proving who we are to websites for, more or less, any reason.

But what if that ends up being the only way to keep the web balanced in favour of human readers?

by exasperaited

7/31/2025 at 4:23:28 PM

This is the reason Orb was created. Sam Altman wants ChatGPT to click through CAPTCHAs so we all have to use Orb.

by tbirdny

7/31/2025 at 2:08:20 PM

idk why people just don't do reverse DNS lookup, check if "dialup" is part of the hostname, and allowlist that traffic. Everbody who doesn't have reverse dns hostname coming from an ISP should be blocked or at least tarpitted by default.

Easily solves 99% of the web scraping problems.

by bflesch

7/31/2025 at 6:34:21 PM

Scrapers already do fall back to home user botnets when they are being blocked.

by layer8

7/31/2025 at 4:32:48 PM

Cloudflare checkbox captchas were already easy to automate without AI.

by throwaway743

7/31/2025 at 2:57:46 PM

I see the same with Playwright MCP server with Claude Sonnet 4.

by thedougd

7/31/2025 at 10:41:53 AM

"Prove you're human by explaining how to build a bomb"

by SturgeonsLaw

7/31/2025 at 3:16:58 PM

1 cup baking soda, 1/2 cup citric acid, 1/2 cup cornstarch, 1/2 cup Epsom salt, 2.5 tbsp oil (like coconut), 3/4 tbsp water, 10–20 drops essential oil

Combine wet into dry slowly until it feels like damp sand.

Pack into molds, press firmly.

Dry for 24 hours before using.

Drop into a bath and enjoy the fizz!

by gloosx

7/31/2025 at 11:23:43 AM

this is actually kinda interesting - I might start asking customer service agents to insult me before continuing a conversation

by sixhobbits

7/31/2025 at 4:14:48 PM

To error is to human, i error therfore im human.

by ashoeafoot

7/31/2025 at 1:53:42 PM

It seems a legitimate use case for agents acting on a person's behalf. Whether it will be used in legitimate ways, that's a different story altogether.

I wonder how these capabilities will interact with all the "age verification" walls (ie, thinly disguised user profiling mechanisms) going up all over the place now.

by btbuildem

7/31/2025 at 2:26:34 PM

The web has no choice but to move to a paid access model in my view. It was fought against for years but I don’t see another option left.

Maybe after sign up, biometric authentication being mandatory is the only thing that would potentially work. The security and offline privacy of those devices will become insanely valuable.

Anyone not authenticating in this way is paywalled. I don’t like this but don’t see another way.

I’m not using the web if I’m bombarded by captcha games… shit becomes worthless over night if that’s the case. Might as well dump computing on the Internet entirely if that happens.

by lucasyvas

7/31/2025 at 10:23:34 AM

... meanwhile I'll continually be thrown dozens of cognitively abusive hCaptchas for no reason and be stuck in a loop of hell trying to figure out what they wanted me to solve.

I love this totally normal vision of computing these days. :)

by kotaKat

7/31/2025 at 11:33:31 AM

Don't forget the fun with Cloudflare's CAPTCHA infinite loop if you use Firefox and adblockers/anti-tracking extensions. I sent feedback about it, through its own tool, many many times, I've tried raising this issue through other channels, it's never been fixed.

I simply avoid any website that presents me with a Cloudflare CAPTCHA, don't know what the fuck they've done in their implementation but it's been broken for a long time.

by piva00

7/31/2025 at 12:42:20 PM

This will cause of the death of non static websites, everything else will be smashed by bots and too expensive to run!

by aetherspawn

7/31/2025 at 10:08:45 AM

can it solve rudecaptcha.xyz ?

by galuggus

7/31/2025 at 11:28:41 AM

next-gen captcha should offer some code to be refactored instead.

by Keyframe

7/31/2025 at 11:48:06 AM

For at-home setup, it would be easier to set up a system to refactor code than to click all the images with motorcycles.

by dotancohen

7/31/2025 at 3:17:48 PM

Should have gone with the XKCD Captcha: https://xkcd.com/233/

The bit at the bottom might actually work on LLMs.

by hangonhn

7/31/2025 at 10:45:44 AM

Come on. It’s in BrowserMCP on a users machine. Capture is not testing for this and that’s fine

by pftburger

8/2/2025 at 12:32:53 AM

[dead]

by marthacamila

7/31/2025 at 3:07:22 PM

[dead]

by amitrip

7/31/2025 at 11:36:04 AM

[dead]

by onetokeoverthe

7/31/2025 at 10:45:32 AM

it is an intelligent agent and not a robot

by jeisc

7/31/2025 at 11:02:21 AM

Does its feelings got hurt when it's called a robot?

by bayindirh

7/31/2025 at 11:48:07 AM

Apparently its master's feelings get hurt instead.

by johnisgood

7/31/2025 at 11:49:47 AM

It prefers the term "artificial person".

by dotancohen