OpenAI researcher: scaling has hit a wall, and it's 100% eval saturation
willdepue · x · 2026-09-04
OpenAI researcher Will Depue says scaling has hit a wall, and the wall is entirely eval saturation — existing benchmarks are so saturated they can no longer distinguish model progress, highlighting the industry's lack of fresh, meaningful benchmarks.
More from Models
- Best-value AI coding subscriptions charted against AA Intelligence Index v4.2 — popiazaza · 2026-09-05
- Prompting Fable 5.1 with embodied mannerisms like *shrugs* makes roleplay flow better — repligate · 2026-09-05
- Astra appears in ChatGPT/Codex on Windows but not Mac, same account — cheesecakegood · 2026-09-05
- No usage reset on GPT-6 Astra launch day, developer calls out OpenAI — tobowers · 2026-09-05
- Debate: Models Fuzzily Recall Concepts, Not Text — SAE Features vs Edit-Distance Memorization — voooooogel · 2026-09-05
- Blogger feeds GPT6 Astra a PPT template, gets 30 conference slides with the right avatar — vista8 · 2026-09-05