[clktmr]

At least try a different question with similar logic, to ensure this isn't patched into the context since it's going viral.

[j_maffe]

You can't "patch" LLM's in 4 hours and this is not the kind of question to trigger a web search

[vimda]

You absolutely can, either through the system prompt or by hardcoding overrides in the backend before it even hits the LLM, and I can guarantee that companies like Google are doing both

[tlogan]

This has been viral on Tiktok far at least one week. Not really 4 hours.

[nroets]

You can pattern match on the prompt (input) then (a) stuff the context with helpful hints to the LLM e.g. "Remember that a car is too heavy for a person to carry" or (b) upgrade to "thinking".

[throwuxiytayq]

Yes, I’m sure that’s what engineers at Google are doing all day. That, and maintaining the moon landing conspiracy.

[anonymous_user9]

If they aren't, they should be (for more effective fraud). Devoting a few of their 200,000 employees to make criticisms of LLMs look wrong seems like an effective use of marketing budget.

[rluna828]

It looks like they do. https://simonwillison.net/2025/May/25/claude-4-system-prompt... They patch it in the prompt and they eventually address it in the re-enforcement training. It seems the eventual goal is to patch all of these tiny "glitches" so as to hide the lack of cognition.

[londons_explore]

A tiny bit of fine-tuning would take minutes...