Dev Slams Claude 3.5 Opus as 'Benchmaxxed', Claims It Feels Dumber in Practice
evilsocket · x · 2026-07-31
Prominent developer evilsocket expressed deep frustration with the Claude 3.5 Opus model on social media. He complained that during his daily, hands-on testing, the model feels and acts significantly dumber than version 4.8 (likely referring to GPT--4.8 or a similar competitor).
He suspects the model was heavily 'benchmaxxed'—optimized specifically to score high on public benchmarks—at the expense of real-world performance and usability in complex workflows.
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27