Snorkel Frontier Data Summit posts 10 talks on agent evals and reward hacking
ysu_nlp · x · 2026-10-17
Snorkel AI has published all ten talks from its Frontier Data Summit, featuring researchers and builders on how to evaluate frontier AI.
Topics span agent evaluation, reward hacking, open benchmarks, and bringing real-world expert judgment into eval pipelines.
Speakers include François Chollet, Dawn Song, Sanmi Koyejo, Alex Shaw, and others.
More from Research
- Cohere research: agent teams hit frontier performance at 30% of the cost — nouhadziri · 2026-10-17
- Cohere publishes blog and paper on scaling agent teams at 30% cost — nouhadziri · 2026-10-17
- scaling01 launches a research project on looping models — scaling01 · 2026-10-17
- 'ink': an adaptive programming language with proof-backed rules that lets AI optimize itself in a loop — _AustinCalvert_ · 2026-10-17
- NYU Courant opens two-year postdoc position on self-improving AI and AI for math — thegautamkamath · 2026-10-17
- Berkeley PhD reading group asks: when labor becomes capital, who owns expertise? — TaniaBabina · 2026-10-17