How Goodfire used Ai2’s open post-training stack to trace unwanted model behavior
- Allen Institute for AI: 5 events in the last 90 days
- Previous: 8 days earlier · The hard parts of AI-assisted science
What happened
Goodfire used Ai2’s fully open post-training stack to predict LLM behavioral changes, trace unwanted model behavior back to individual training examples, and test targeted fixes without sacrificing broader capability gains.
Summary assembled by rule from the sources below
Why it's spreading
Sources
Official
- How Goodfire used Ai2’s open post-training stack to trace unwanted model behaviorAllen Institute for AI