Teknium Criticizes Claude Opus 5: Subjectively Disliked, Tips Provided
Teknium · x · 2026-08-06
Responding to community praise for Claude Opus 5's agentic engineering capabilities, prominent open-source model developer Teknium expressed a different subjective experience, stating bluntly that 'everyone hates it.' However, he referenced official documentation tips to improve the experience, such as instructing the model to be concise, specifying progress updates, limiting artifact length, and removing unnecessary verification instructions.
Related event: Developers Slam Claude Opus 5: Arrogant, Preachy, and Underwhelming(13 posts)→
More from Models
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
- Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16