Users say Opus 5 is missing instructions more often than 4.8
springrod · x · 2026-07-28
A user says Opus 5 was markedly worse than expected on instruction following
The poster says their session with Opus 5 was unusually disappointing: the model repeatedly failed to follow instructions, kept apologizing, and made little progress on a task that was not especially hard.
A reply in the thread sharpens the criticism, claiming that Opus 5 makes more mistakes than 4.8. The post then turns the experience into a broader question: are frontier model vendors entering a period of diminishing returns despite louder marketing and product fanfare?
Related event: Opus 5 Performance Drop Sparks Diminishing Returns Debate(2 posts)→
More from Models
- User says Sonnet 5 keeps sticking to older context despite corrections — bushibuilds · 2026-07-28
- Users debate whether ChatGPT web search can read paywalled scientific journals — Zeugma91 · 2026-07-28
- ChatGPT screenshot shows a brief model-interface oddity with little context — Puzzled_North_8862 · 2026-07-28
- Kimi K3 Gets a Meme-Style Swipe for Having “No Guardrails” — yacinelearning · 2026-07-28
- Users report Opus 5 starts sounding like Trump in base model mode — Sauers_ · 2026-07-28
- Kimi is described with a linear-attention variant and attention residuals — burny_tech · 2026-07-28