EvalEval Coalition on the science of AI evaluation grows to 800+ researchers, adopts new governance
evijit · x · 2026-10-06
The EvalEval Coalition, focused on the science of evaluating AI evaluations, has grown from a small group to 800+ researchers and practitioners in under two years. It adopted new bylaws and a leadership structure (effective October 2026), led by a Steering Committee and Chairs.
- Mission: fix flawed evaluations, lack of consensus on documenting evaluation applicability, and uneven coverage of broader impact categories
- Track record: NeurIPS/ICML publications, workshops including the ACL 2026 Evaluating Evaluations workshop, and a social-impact framework chapter in the Oxford Handbook on Generative AI
- Steering committee includes Hugging Face's Avijit Ghosh and Irene Solaiman
More from Companies & People
- n8n Grew 10x Last Year Despite Being Declared Dead Three Times, CEO Says — aakashgupta · 2026-10-06
- AI companies often voice support for state AI bills only after they pass, observer notes — Miles_Brundage · 2026-10-06
- Skip SF Tech Week events and host your own, says founder who turned one birthday party into 10+ real connections — tech__unicorn · 2026-10-06
- A traveler's jet lag kit: melatonin, sunglasses and caffeine timed with Timeshifter (shifted 2-3 hours earlier) — austinc3301 · 2026-10-06
- Researcher to attend COLM with 1:1 slots, recruiting PhD students in interp and safety — johnhewtt · 2026-10-06
- iamtrask boosts token-attribution idea to fix enterprise AI's incentive misalignment — iamtrask · 2026-10-06