AI Safety Classifiers

concepts · 2 notes linked

Related: Zvi Mowshowitz · Anthropic · Claude · Janus · Model Welfare · AI Alignment · AI Consciousness · Interpretability

Notes

• Claude Fable 5 and Mythos 5: Capabilities — Fable 5 capability review, benchmarks, classifiers, reception
• Fable and Mythos: Model Welfare — Model welfare assessment of Fable 5 / Mythos 5