Anthropic models solve hard science but can't stop being verbose, users complain
kimmonismus · x · 2026-09-08
- A user highlights a long-standing complaint about Anthropic's models: they can solve the hardest scientific problems yet remain needlessly verbose and inefficient.
- The post, described as one of the most reliably reproducible observations, asks when Anthropic will finally address the verbosity problem.
Related event: Anthropic Models Slammed for Verbose, Inefficient Outputs(2 posts)→
More from Models
- AI beats 1800-rated chess bot in 31 moves after engine upgrades, no opening book used — MikePFrank · 2026-09-08
- GPT-6 scores below Kimi K3 on GDPval-AA v2 and neither OpenAI nor Artificial Analysis will explain why — ChrisGPT · 2026-09-08
- Artificial Analysis ships Intelligence Index v4.3 with AutomationBench-AA — SonglinYang4 · 2026-09-08
- IFM Releases K2-Horizon Models, Including a 375B A23B MoE — PhilippeEiffel · 2026-09-08
- davinci-002 shuts down Sept 28: dev recreates the original GPT experience as a farewell — cephaloform · 2026-09-08
- Founder's model ranking: ChatGPT underrated, Gemini 'knocked flat', Claude overhyped — firstadopter · 2026-09-08