Goodfire
@GoodfireAI
Predictive data debugging lets you reveal and shape what a model learns, before you train.
We're grateful to the Ai2 team for open-sourcing their full post-training stack to enable research like this!
We're grateful to the Ai2 team for open-sourcing their full post-training stack to enable research like this!
Ai2@allen_ai · Sep 9Training an LLM by showing it answers people prefer – and ones they don’t – can improve it while quietly worsening behaviors.
@GoodfireAI used our open post-training stack to predict how a full training run would change responses to different prompts. 🧵
allenai.org/blog/goodfire-…
@GoodfireAI used our open post-training stack to predict how a full training run would change responses to different prompts. 🧵
allenai.org/blog/goodfire-…
Open quoted post →
2 200