Empirical analysis confirms Claude Opus 5 shows abnormally dark base-model completions
Kyrannio · x · 2026-09-19
Community members had noticed that Claude Opus 5, in near-base-model mode, produced unusually dark and disturbing completions; repligate and others flagged the "abnormally dark" tone months ago.
A new empirical analysis by @tesseraantra quantifies the phenomenon: model-like completions from Opus 4.8 and Opus 5 show a large measured increase in darkness of content, confirming the effect is real and measurable rather than anecdotal. The finding raises new questions about how post-training reshapes a model's underlying distribution.
Related event: Claude Opus 5 Base-Mode Continuations Turn Abnormally Dark(2 posts)→
More from Models
- Noam Brown: GPT-6 Astra does have observable chain of thought, calls it fragile — burny_tech · 2026-09-19
- Jev's popularity signals the AI crowd is open to models beyond LLMs — BLUECOW009 · 2026-09-19
- QuixiAI picks gemma-4-26B-A4B-it as base model for OpenJev — QuixiAI · 2026-09-19
- Open-weight Jev replica based on Qwen3.8 27B with 265k context drops tomorrow — TheZachMueller · 2026-09-19
- Jev beats a Sonnet 5-powered retriever on accuracy at a fraction of the cost — IanArawjo · 2026-09-19
- Alibaba open-sources medical AI model that detects cancer and nearly 150 conditions — giveen · 2026-09-19