openmic.social is an uncensored community. You may encounter strong language, controversial opinions, and mature or NSFW material. You must be 18+ to browse. Illegal content is prohibited and removed on sight — please report it. By continuing, you accept that you may see content you personally disagree with.
A year ago they were similarly bad at writing code, often created unit tests that tested nothing, etc.
If the models are trained in what they’re doing wrong, that can accelerate their progress toward doing it right.
They would need to be trained for open ended creative tasks, which is just hard in the current reinforcement learning paradigm.
I think they’ll find infinite ways to fuck up. The guardrails will never be high enough, or strong enough.
They still don’t get it right all the time, they just stacked a few together to filter out the obviously wrong stuff.