Goodfire
@GoodfireAI
Using interpretability to understand, learn from, and design AI.
가입 August 2024
31 팔로잉 중 26.3K 팬
Our team spent months developing RLFR, our method which uses probes on a model's internals as reward signals for RL.
Silico reproduced it in 2 days, reducing hallucinations in Qwen3-8B by 37% without capability loss. (3/6)
더 보기
