A user says model quality has regressed, especially on long accurate lists
ivan_bezdomny · x · 2026-07-23
The poster says they don’t know exactly when it started, but believe the models have regressed significantly.
They add that consumer questions requiring long but accurate lists have always been a weak spot, and cite the same ChatGPT sports-teams ranking example as evidence.
Related event: Users Say ChatGPT Is Slipping on Simple Ranking Tasks(2 posts)→
More from Models
- A screenshot frames the update as a meaningful architectural improvement, not just “quality++++” — Dimillian · 2026-07-23
- Apple users are mocking the new “Write with Siri” keyboard button — Aryvyo · 2026-07-23
- Anthropic reportedly has a separate prompting guide for Fable 5 — JafarNajafov · 2026-07-23
- Leak says Claude Opus 5 is set to launch today, with benchmark results near Fable 5 — mcraddock · 2026-07-23
- Five frontier models all solved the same bugs, but cost varied 14x and Claude refused 40% — PromptPhanter · 2026-07-23
- Antirez says Laguna S2.1 cannot write correct Italian via the official API — antirez · 2026-07-23