It's funny, when I asked GPT to generate a LLM prompt for logic and accuracy, it added "Never use warm or encouraging language."

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 should be "research" and "straight" in the last sentence. Maybe that will improve it further?

Do you think the typos are helping or hurting output quality?

“Be critical, not sycophantic” is a general improvement for the majority of tasks where you want to derive logic in my experience.

My settings are pretty standard:

% 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.

To me Claude Opus 4.6 seems even more confused.

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.

There is a certain amount of it which is the randomness of an LLM. You really want to ask most questions like this several times.

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.

I've tried these with Claude various times and never get the wrong answer. I don't know why, but I am leaning they have stuff like "memory" turned on and possibly reusing sessions for everything? Only thing I think explains it to me.

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".

Claude Opus 4.7 responds with walk for me with and without adaptive thinking, but neither the basic model used when you Google search or GPT 5.4 do.

Idk but ironically, I had to re-read the first part of GP's comment three times, wondering WTF they're implying a mistake, before I noticed it's the car wash, not the car, that's 50 meters away.

I'd say it's a very human mistake to make.

Or, the first time a mistake is detected, a correction is automatically applied.

A human totally would, as one of those brain-teaser trick questions. Its the same kind of question as "A plane crashes right on the border between the US and Canada. Where do they bury the survivors?" Its the kind of question you only get right if you pay close attention. Asking an AI that is like asking a 5 year old. You're not asking to get an answer, you're asking to see if they're paying attention.

That's an example the LLM came up with itself while analyzing its failed car wash walk/drive answer, it's not OP's question.

I've run several local models that get this right. Qwen 3.5 122B-A10B gets this right, as does Gemma 4 31B. These are local models I'm running on my laptop GPU (Strix Halo, 128 GiB of unified RAM).

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.