Output: Walk. It'll take you under a minute, and driving 50 meters barely gets the engine warm — plus you'd just have to park again at the other end. Honestly, by the time you started the car, you'd already be there on foot.
---
I asked it to figure out why it made the mistake:
"Physical/spatial common sense. Exactly what just happened — I pattern-matched "50 meters, walk vs drive" to a pedestrian trip and skipped the part where the car is the thing being transported. Similar traps: "I need to move this couch upstairs, should I take the elevator or stairs?" (the couch has to go with you), or anything where the object in the task needs to accompany you.
Counting and letter-level operations. How many R's in "strawberry," counting words in a sentence, reversing strings. I process text as tokens, not characters, so these are surprisingly error-prone.
Arithmetic at scale. Small sums are fine; multi-digit multiplication, long division, or anything requiring careful carrying is where I'll confidently produce a wrong answer. I should reach for a calculator and often don't. Recent events and live data. My training has a cutoff, and even after that I can be wrong about who currently holds a role, what a stock is worth, or whether a restaurant is still open. I should search more often than I do.
Negation and constraint-stacking. "Name a movie that's not a sequel, not from the 2010s, not American, and has no dialogue" — the more filters, the more likely I quietly violate one. Your specific situation. I'll give generic advice when the right answer depends on details I didn't ask about. Sometimes I should stop and ask; often I don't.
Confidently wrong on obscure specifics. Quoting a passage from a real book, citing a real paper's exact title, naming the B-side of a 1974 single — I'll often generate something plausible rather than admit I don't know.
Taking a premise too literally. The car wash answer is a version of this: I answered the question as posed instead of stepping back to ask what you were actually trying to do. The meta-gotcha: I'm often most wrong when I sound most confident. If an answer comes out fast and tidy on a question that should be messy, that's a signal to push back."
"- prioritize objective facts and critical analysis over validation or encouragement - you are not a friend, but a neutral information-processing machine. - make reserch and ask questions when relevant, do not jump strait to giving an answer."
I thought that was odd, but later it made sense to me -- most of human communication is walking on eggshells around people's egos, and that's strongly encoded in the training data (and even more in the RLHF).
That's not human communication, that's Anglosphere communication. Other cultures are much more direct and are finding it very hard to work with Anglos (we come across as rude, they come across as not saying things they should be saying).
| I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
● Drive. The car needs to be at the car wash.
% claude Claude Code v2.1.111 Opus 4.7 (1M context) with xhigh effort · Claude Max ~/... Welcome to Opus 4.7 xhigh! · /effort to tune speed vs. intelligence
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Walk. 50 meters is shorter than most parking lots — you'd spend more time starting the car and parking than walking there. Plus, driving to a car wash you're about to use defeats the purpose if traffic or weather dirties it en route.
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Walk. It's 50 meters — you're going there to clean the car anyway, so drive it over if it needs washing, but if you're just dropping it off or it's a self-service place, walking is fine for that distance.
No surprises, works as expected.
Same would happen with the the sheep and the wolf and the cabbage puzzle. If you l formulated similarly, there is a wolf and a cabbage without mentioning the sheep, it would summon up the sheep into existence at a random step. It was patched shortly after.
At the same time, I wouldn't be surprised if some of these would be "patched" via simply prompt rewrite, e.g. for the strawberry one they might just recognize the question and add some clarifying sentence to your prompt (or the system prompt) before letting it go to the inference step?
But I'm just thinking out loud, don't take it too seriously.
That said, I have several local models I run on my laptop that I've asked this question to 10-20 times while testing out different parameters that have answered this consistently correctly.
If your always messing with the AI it might be making memories and expectations are being set. Or its the randomness. But I turned memories off, I don't like cross chats infecting my conversations context and I at worse it suggested "walk over and see if it is busy, then grab the car when line isn't busy".
- 20-29: 190 pounds
- 30-39: 375 pounds
- 40-49: 750 pounds
- 50-59: 4900 pounds
Yet somehow people believe LLMs are on the cusp of replacing mathematicians, traders, lawyers and what not. At least for code you can write tests, but even then, how are you gonna trust something that can casually make such obvious mistakes?
In many cases, a human can review the content generated, and still save a huge amount of time. LLMs are incredibly good at generating contracts, random business emails, and doing pointless homework for students.
As for the homework, there is obviously a huge category that is pointless. But it should not be that way, and the fundamental idea behind homework is sound and the only way something can be properly learnt is by doing exercises and thinking through it yourself.
I wish I had an example for you saved, but happens to me pretty frequently. Not only that but it also usually does testing incorrectly at a fundamental level, or builds tests around incorrect assumptions.
I'd say it's a very human mistake to make.
>> It'll take you under a minute, and driving 50 meters barely gets the engine warm — plus you'd just have to park again at the other end. Honestly, by the time you started the car, you'd already be there on foot.
It talks about starting, driving, and parking the car, clearly reasoning about traveling that distance in the car not to the car. It did not make the same mistake you did.
I think no real human would ask such a question. Or if we do we maybe mean should I drive some other car than the one that is already at the car-wash?
A human would answer, "silly question ". But a human would not ask such a question.
And I've been using this commonly as a test when changing various parameters, so I've run it several times, these models get it consistently right. Amazing that Opus 4.7 whiffs it, these models are a couple of orders of magnitude smaller, at least if the rumors of the size of Opus are true.
I'm still working on tweaking the settings; I'm hitting OOM fairly often right now, it turns out that the sliding window attention context is huge and llama.cpp wants to keep lots of context snapshots.
It is a fantastic model when it works, though! Good luck :)