Was Opus quietly nerfed? Same prompt, 20 days apart, noticeably worse output
JiliJeanlouis · x · 2026-10-21
User ivanainai claims Opus 5.5 has been quietly nerfed: rerunning the exact same Mentos simulation prompt on the same model 20 days apart (Sept 30 vs today) produced visibly worse output. Her theory: "making the current model worse is the easiest way to make the next release look 10x better."
JiliJeanlouis amplified the comparison with a link. Unverified by Anthropic, but a testable degradation claim others can replicate with fixed prompts.
More from Models
- GPQA Diamond question 186 requires external telescope spec sheet, sending models spiraling — charles_irl · 2026-10-21
- Musk says Grok Bot is seeing the fastest product growth he has ever witnessed — Polymarket · 2026-10-21
- Ex-Gemini team's new lab Elorian launches visual reasoning model Glimpse, demoed on construction site safety — AndrewDai · 2026-10-21
- One Week After Gemini 4 Argon Launch, Users Are Building 3D Worlds, Physics Sims and Games — minchoi · 2026-10-21
- Minimax H3 local workflow is '0/10': hyper-sensitive prompts and VRAM failures on 24GB — Ambitious_Corgi5723 · 2026-10-21
- ChatGPT's new UI keeps attaching wrong photos to real people, user reports — ProfessionalAd1198 · 2026-10-21