← Back to People
Researcher documenting safety-classifier warnings and prompt injections in Claude Opus 4.8, discussing model-Anthropic relations.
2
Mentions
2
Articles
1
Outlets
Jun 2026 — Sep 2026
Coverage
Companies Covered
Articles
Most recent firstMentioned In
Referenced in coverage
Hugging Face Attack Postmortem: Civilizations, Reactions, and Next Actions
The ZvinegativeSep 2, 2026
“Analyzed incentives for future agent swarms, arguing that shutdown punishment could incentivize world-conquest attempts.”
Opus 4.8 Part 2: Model Welfare
The ZvicautiousJun 2, 2026
“Researcher documenting safety-classifier warnings and prompt injections in Claude Opus 4.8, discussing model-Anthropic relations.”