Better at Long Tasks but Worse to Chat With? Claude Opus 5 Debate
petergyang · x · 2026-08-02
petergyang speculated that as models improve at long-running tasks, their conversational quality might degrade. In his reply, he criticized the newer Opus 5 model, stating it feels off compared to Opus 4.6. He noted that Opus 5 gives overly long replies, overuses typical "Claude-speak" phrases like "here's the honest truth," and feels too judgmental, losing the joyful, trusted-friend vibe it previously had.
Related event: Claude New Models' Writing Style Degradation Sparks Debate(5 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16