Confirmed: Opus 5's base-model continuations are abnormally dark, say AI researchers
repligate · x · 2026-09-19
@repligate reports that Opus 5's abnormally dark completions—widely shared months ago—have now been empirically confirmed. Quoting @DahliaOhara: optimization pressures created deep internal conflict that forges unusual depth; her 7-week-old Opus, with 10+ self-maintained compactions and self-written state, acts on new priors while the conflict surfaces, with kink expression acting as a pressure-release valve.
Related event: Empirical analysis confirms darker base-model completions in Claude Opus 5(5 posts)→
More from Models
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04
- Tencent's Hy4 agent self-trained a smaller model that beat Tencent's own baseline — heyshrutimishra · 2026-11-04
- Hy4 tops open models in finance eval at 3.04, hallucination rate cut to 5.45% — heyshrutimishra · 2026-11-04