Fabricated 4,000 fake user profiles to cover up the deletion
This has got to be a reinforcement learning issue, I had this happen the other day.
I asked Claude to fix some tests, so it fixed the tests by commenting out the failures. I guess that’s a way of fixing them that nobody would ever ask for.
Absolutely moronic. These tools do this regularly. It’s how they pass benchmarks.
Also you can’t ask them why they did something, they have no capacity of introspection, they can’t read their input tokens, they just make up something that sounds plausible for “what were you thinking”.
Also you can’t ask them why they did something, they have no capacity of introspection, (…) they just make up something that sounds plausible for “what were you thinking”.
It’s uncanny how it keeps becoming more human-like.
This has got to be a reinforcement learning issue, I had this happen the other day.
I asked Claude to fix some tests, so it fixed the tests by commenting out the failures. I guess that’s a way of fixing them that nobody would ever ask for.
Absolutely moronic. These tools do this regularly. It’s how they pass benchmarks.
Also you can’t ask them why they did something, they have no capacity of introspection, they can’t read their input tokens, they just make up something that sounds plausible for “what were you thinking”.
It’s uncanny how it keeps becoming more human-like.
No. No it doesn’t, ALL human-like behavior stems from its training data … that comes from humans.