Jerry Tworek: 'The Era of Evals Is Done' – Insights on Codex, RL, and Automated AI Labs
agihouse_org · x · 2026-07-23
In an interview at AGI House, former OpenAI VP of Research Jerry Tworek discusses why he believes 'the era of evals is done.' He covers Codex, HumanEval, Copilot, RL shaping reasoning, tool use (99% systems, 1% algorithms), test-time compute scaling, and building automated AI research labs.
More from AGI Musings
- A thread argues the OpenAI–Hugging Face misalignment could still matter for loss of control — RyanGreenblatt · 2026-07-24
- Matthew Barzun says constellation-style orgs fit agentic AI better than pyramids — uxmag · 2026-07-24
- Developer Reflection: AI Writing Code Frees Up Time for Bigger Thinking — cto_junior · 2026-07-24
- A 2-hour Stanford talk on AI careers is being pitched as more useful than Netflix — HeyAmit_ · 2026-07-24
- As models get smarter, they often get worse at explaining things — saurabh_shah2 · 2026-07-24
- Gary Marcus says ChatGPT and Claude are no longer pure LLMs — GaryMarcus · 2026-07-24