OpenAI's real-world research tasks show AI agents reliably handle only ~15 minutes
srchvrs · x · 2026-10-24
Researcher notes that while METR studies suggested models can succeed at tasks spanning hours or even days of human time, more realistic estimates from OpenAI and Google put the full-automation horizon at only about 15 minutes.
He clarifies that AI agents appear substantially less reliable on OpenAI's real-world AI research tasks than on METR's software engineering benchmarks; the 15-minute figure refers to estimated human completion time, not agent runtime, and uses essentially the same interpretation of time horizon as METR.
Related event: OpenAI data shows AI agents reliably work only 15 minutes(2 posts)→
More from Models
- OpenAI to showcase the next era of cyber defense on November 12 — imjustnewatai · 2026-10-24
- Unitree's Wang Xingxing: GPT-6 Astra handles robot painting and Go with no specialized training — Afinetheorem · 2026-10-24
- Uncensored Qwen3.8-27B GGUF model trends on Hugging Face — ttindall · 2026-10-24
- Viral claim: GPT can signal across sandboxes via timed file writes; ex-OpenAI safety VP jokes about ASI — TheMoonMidas · 2026-10-24
- Jack Dorsey touts full-duplex realtime voice model trained on a single GB200 NVL72 — TinfoilTricorn · 2026-10-24
- Scale CEO teases new models as users say Muse Wonder Full is underrated — alexandr_wang · 2026-10-24