Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by skerit on Thursday March 20, 2025 @07:46AM
(#43421877)
Claude Sonnet 3.7 really, really loves to rewrite tests so they'll pass. I've had it happen many times in a claude-code session, I had to add this to each request (though it did not fix it 100%)
[ Parent
| on HN ]
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by jsight on Thursday March 20, 2025 @12:06PM
(#43425094)
I'm guessing this is a side effect of mistakes in the reinforcement learning face. It'd be really easy to build a reward model that favors passing tests, without properly measuring the quality of those tests.