Is Opus 5.5 nerfed? Thinking patterns changed on November 3

	Is Opus 5.5 nerfed? Thinking patterns changed on November 3(twitter.com)
	815 points by rzk 2 days ago \| 511 comments
	tl;dr: A user claims that Claude Opus 5.5's reasoning behavior shifted noticeably on November 3, based on an analysis of 1,400 Claude Code sessions run through Gemini 4 Argon. While the model name remained unchanged, the analysis suggests an unannounced modification affected how the model reasons, fueling speculation that it has been "nerfed."
	HN Discussion: ↑Confirms experiencing model degradation, suspecting quantization or compute reallocation before new releases ↓Benchmark reruns show no measurable difference between September and today ↓Skeptical of vibes-based claims and asks for real eval signals ~Suggests this is routine A/B testing rather than a deliberate nerf •Advocates self-hosting local models to avoid dependency on unstable hosted services