Interpretability researcher joining Goodfire AI post-PhD, calls for speeding up the field
mathildepapillo · x · 2026-10-27
Researcher mathildepapillo argues interpretability is the most important scientific problem of our lifetime but is moving too slowly, and co-authored thoughts with @banburismus on how to accelerate it. She also announced she will be joining Goodfire AI after finishing her PhD.
Related event: Interpretability Researcher Calls for Faster Progress, Joins Goodfire AI(2 posts)→
More from Companies & People
- Interpretability researchers call for a 'Human Genome Project for AI'; author joins Goodfire — ninamiolane · 2026-10-27
- AIE Code Summit 2026 opens applications: 800 seats, keynotes streamed free — trq212 · 2026-10-27
- After Microsoft's 60K layoffs, pundit predicts 50-60% headcount cuts at big companies — krishnan · 2026-10-27
- Vercel founder Rauch: pencil, press, JS share one trait — and it's why he's bullish on agents — round · 2026-10-27
- 'Explain how AI isn't impacting productivity': 27% workforce cut sparks debate — alvelda · 2026-10-27
- Claude now handles 27% of Anthropic's R&D, up from zero months ago — thursdai_pod · 2026-10-27