Vladimir Mikulik
Source-listed: Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMsSaved credit: Contributor · 2026Explore people connected to this work →
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal JailbreaksSaved credit: Contributor · 2026Explore people connected to this work →
- Human-AI Complementarity: A Goal for Amplified OversightSaved credit: Contributor · 2026Explore people connected to this work →
- Towards training-time mitigations for alignment faking in RLSaved credit: Contributor · 2025Explore people connected to this work →
- Tracr: Compiled Transformers as a Laboratory for InterpretabilitySaved credit: Contributor · 2023Explore people connected to this work →