alt Hacker NewsDeterministic feedback is precisely how frontier models are trained. It’s called RLVR. You let the agent run on a problem and then calculate a deterministic score of how well it did. Repeat 1000x times and you can “brute force” a good solution. (Which includes all thinking traces and you add it to your training data.) And then a Chinese model can copy your advance for 1000x less compute. Which is why US labs call this not learning, but a distillation “attack”. It’s an attack on the business model.
Replies
DelightOne • today at 10:42 AM
Are there good open source setups that generate this training data automatically?
Or is that the secret sauce no one wants to share, the edge people see themselves having.
➕ show 1 reply
I suppose the same way that the normal programmers and artists would call LLMs an attack on licenses and copyright.