Opus 5.5 gets skittish about identifying authors from writing, defaulting to sandbagging
tracewoodgrains · x · 2026-10-23
tracewoodgrains reports that Opus 5.5 has become much more reluctant to identify people based on their writing style. The model is fully capable — a screenshot shows a sharp stylometric analysis — but its default reaction is to sandbag and moralize, only complying when the prompt is angled correctly. He calls the behavior irritating.
More from Models
- Scale CEO teases new models as users say Muse Wonder Full is underrated — alexandr_wang · 2026-10-24
- Canva Craft trained on millions of templates and 25,000 designer-evaluated image pairs — jacob_top · 2026-10-24
- $34.72 of Kimi K3.1 Pro tokens builds a playable Spider-Man Manhattan in 8 hours — sven_ai · 2026-10-24
- Cisco engineer replicates free Antares security model at ~80% of official score — shashib · 2026-10-24
- Kimi K3.1 vs Opus 5.5: 80% Cheaper and 4x Faster on Same Task — sven_ai · 2026-10-24
- Claim: Open-source Kimi K3.1 Pro beats OpenAI's GPT-6-Astra, unverified — sven_ai · 2026-10-24