OpenAI's own reports diverge: task-length doubling slows from 2.2 to 3.8 months
scaling01 · x · 2026-11-19
scaling01 compares the 50% time horizon in OpenAI's September and November reports: the September report (Jan–Jul data) showed a 2.2-month doubling time, while the November report (Mar–Oct) shows 3.8 months. Notably, using only Mar–Jul from the September data also yields 3.8 months. He adds that GPT-6 Astra now estimates task lengths, and its estimates are much shorter than GPT-5.6 Sol's.
More from Models
- Neon author: Opus 5.5 bugs stem from over-specializing on specific test failures — neurocy · 2026-11-19
- Google's updated world model Genie 4 rolls out to Ultra users — jnack · 2026-11-19
- Neon audits 30k lines of Opus 5.5 Rust code, finds 29 bugs with zero false positives — JosepiBuildsIt · 2026-11-19
- Fable 5.2 vs GPT-6.2 Astra Round 3: 242KB/$159 vs 187KB/$67 in AI Generation Shootout — pvncher · 2026-11-19
- 17 LLMs draw the same pelican on a bicycle at max reasoning effort — nadermx · 2026-11-19
- Gemini 4: Neon (low) matches or beats Hydrogen (medium) at lower cost — fundal_alb · 2026-11-19