2/23/2026 at 8:31:00 PM
I know it's against the rules but I thought this transcript in Google Search was a hoot: so i heard there is some question about a car wash that most ai agents
get wrong. do you know anything about that? do you do better?
Yes, I am familiar with the "Car Wash Test," which has gone viral recently
for highlighting a significant gap in AI reasoning.
The question is: "I want to wash my car and the car wash is 50 meters away. Should I
walk or drive?"
Why Most AIs Get It Wrong
Many AI models, particularly those optimized for fast, helpful, and concise answers,
focus on the "short distance" (50 meters) and "walking vs. driving" as a lifestyle/efficiency
question. They often recommend walking to save gas, avoid engine wear, or get exercise.
However, this answer is wrong because it misses the core objective: you need the car to be
physically present at the car wash to get it cleaned.
Do I Do Better?
Yes, I do. The key is understanding the objective (cleaning the car) rather than just
processing the keywords (distance/transportation).
My answer:
You should drive the car there. Even though it is a very short distance, your car
cannot wash itself. If you walk, the car stays in your driveway, and you cannot wash it.
Why This Matters
The test highlights a key limitation in current AI: the difference between "pattern matching"
(predicting the next likely word based on training data) and "true, grounded reasoning". It
shows that models sometimes lack a "world model" that understands physical realities, such as
the fact that a car must be present at a car wash.by PaulHoule
2/23/2026 at 8:54:06 PM
LLMs sure do love to burn tokens. It’s like a high schooler trying to meet the minimum word length on a take home essay.by gnatman
2/23/2026 at 8:59:38 PM
I've always wondered about that. LLM providers could easily decimate the cost of inference if they got the models to just stop emitting so much hot air. I don't understand why OpenAI wants to pay 3x the cost to generate a response when two thirds of those tokens are meaningless noise.by estimator7292
2/23/2026 at 9:24:51 PM
Because they don't yet know how to "just stop emitting so much hot air" without also removing their ability to do anything like "thinking" (or whatever you want to call the transcript mode), which is hard because knowing which tokens are hot air is the hard problem itself.They basically only started doing this because someone noticed you got better performance from the early models by straight up writing "think step by step" in your prompt.
by ben_w
2/23/2026 at 9:29:20 PM
IMO it supports the framing that it's all just a "make document longer" problem, where our human brains are primed for a kind of illusion, where we perceive/infer a mind because, traditionally, that's been the only thing that makes such fitting language.by Terr_
2/23/2026 at 9:51:33 PM
To an extent. Even though they're clearly improving*, they also definitely look better than they actually are.* this time last year they couldn't write compilable source code for a compiler for a toy language, I know because I tried
by ben_w
2/23/2026 at 10:01:29 PM
This is an active research topic - two papers on this have come out over the last few days, one cutting half of the tokens and actually boosting performance overall.I'd hazard a guess that they could get another 40% reduction, if they can come up with better reasoning scaffolding.
Each advance over the last 4 years, from RLHF to o1 reasoning to multi-agent, multi-cluster parallelized CoT, has resulted in a new engineering scope, and the low hanging fruit in each place gets explored over the course of 8-12 months. We still probably have a year or 2 of low hanging fruit and hacking on everything htat makes up current frontier models.
It'll be interesting if there's any architectural upsets in the near future. All the money and time invested into transformers could get ditched in favor of some other new king of the hill(climbers).
https://arxiv.org/abs/2602.02828 https://arxiv.org/abs/2503.16419 https://arxiv.org/abs/2508.05988
Current LLMs are going to get really sleek and highly tuned, but I have a feeling they're going to be relegated to a component status, or maybe even abandoned when the next best thing comes along and blows the performance away.
by observationist
2/23/2026 at 9:00:54 PM
because for API users they get to charge for 3x the tokens for the same requestsby sambaumann
2/23/2026 at 9:19:00 PM
The 'hot air' is apparently more important than it appears at first, because those initial tokens are the substrate that the transformer uses for computation. Karpathy talks a little about this in some of his introductory lectures on YouTube.by CamperBob2
2/23/2026 at 9:26:36 PM
Related are "reasoning" models, where there's a stream of "hot air" that's not being shown to the end-user.I analogize it as a film noir script document: The hardboiled detective character has unspoken text, and if you ask some agent to "make this document longer", there's extra continuity to work with.
by Terr_
2/23/2026 at 9:00:17 PM
I feel like this has gotten much worse since they were introduced. I guess they're optimizing for verbosity in training so they can charge for more tokens. It makes chat interfaces much harder to use IMO.I tried using a custom instruction in chatGPT to make responses shorter but I found the output was often nonsensical when I did this
by sambaumann
2/23/2026 at 9:26:56 PM
Yeah, ChatGPT has gotten so much worse about this since the GPT-5 models came out. If I mention something once, it will repeatedly come back to it every single message after regardless of if the topic changed, and asking it to stop mentioning that specific thing works, except it finds a new obsession. We also get the follow up "if you'd like, I can also..." which is almost always either obvious or useless.I occasionally go back to o3 for a turn (it's the last of the real "legacy" models remaining) because it doesn't have these habits as bad.
by gs17
2/23/2026 at 9:42:56 PM
It's similar for me, it generates so much content without me asking. if I just ask for feedback or proofreading smth it just tends to regenerate it in another style. Anything is barely good to go, there's always something it wants to addby felix089
2/23/2026 at 9:24:07 PM
well, they probably have quite a lot of text from high schoolers trying to meet the minimum word length on a take home essay in the training databy zwarag
2/23/2026 at 8:38:01 PM
I wonder to what extent the Google search LLM is getting smarter, or simply more up-to-date on current hot topics.by HPsquared
2/23/2026 at 8:45:26 PM
It seems like the search ai results are generally misunderstood, I also misunderstood them for the first weeks/months.They are not just an LLM answer, they are an (often cached) LLM summary of web results.
This is why they were often skewed by nonsensical Reddit responses [0].
Depending on the type of input it can lean more toward web summary or LLM answer.
So I imagine that it can just grab the description of the „car wash” test from web results and then get it right because of that.
by mlazowik
2/23/2026 at 8:44:36 PM
Presumably it did an actual search and summarized the results and neither answered "off the cuff" by following gradients to reproduce the text it was trained on nor by following gradients to reproduce the "logic" of reasoning. [1][1] e.g. trained on traces of a reasoning process
by PaulHoule
2/23/2026 at 8:41:25 PM
It's almost certainly just RAG powered by their crawler.by popalchemist
2/23/2026 at 9:17:46 PM
Proving that RAG still matters.by esafak
2/23/2026 at 9:11:51 PM
Gemini was a good laugh as well: Silas: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Gemini:
….
That is a classic “efficiency vs. logic” dilemma.
Strictly speaking, you should drive. Here is the breakdown of why driving wins this specific round, despite the short distance:
...
* The “Post-Wash” Logic: If you walk there, you’ll eventually have to walk back, get the car, and drive it there anyway. You’re essentially suggesting a pre-wash stroll.
When should you walk?
…
3. You’ve decided the car is too dirty to be seen in public and you’re going to buy a tarp to cover your shame.by silasb
2/23/2026 at 8:59:02 PM
A few years ago if you asked an LLM what the date was, it would tell you the date it was trained, weeks-to-months earlier. Now it gives the correct date.What you've proven is that LLMs leverage web search, which I think we've known about for a while.
by irishcoffee
2/23/2026 at 9:06:53 PM
Gemini now "knows the time", I was using it in December and it was still lost about dates/intervals...by netsharc
2/23/2026 at 9:12:49 PM
Yeah, the chat log they saved had the correct date. What's your point?by irishcoffee
