Goodfire uses Ai2's open post-training stack to predict how training runs change model behavior
allen_ai · x · 2026-09-10
Ai2 highlights that training LLMs on preferred and dispreferred answers improves them while quietly worsening other behaviors. Goodfire AI used Ai2's open post-training stack to predict how a full training run would change responses to different prompts — effectively forecasting side effects of preference training before running it. Details in their technical thread.
More from Models
- GPT-6.1 Terra cuts factual error rate from 22.3% to 4.3%, an ~81% drop — haider1 · 2026-10-27
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude — Angaisb_ · 2026-10-27
- Artificial Analysis Ships Intelligence Index v4.3.2 With GPT-6.1 Terra Comparison — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra cuts hallucination rate by 50 points while lifting accuracy 2 points — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27