← Back to People
AI safety researcher working on deception and reward hacking monitoring
5
Mentions
5
Articles
4
Outlets
Sep 2026 — Oct 2026
Coverage
Negative
Sentiment
Companies Covered
Appears In
Sentiment Distribution
Based on 5 scored articles
Neutral 20%Negative 80%
Appears Alongside
Articles
Most recent firstMentioned In
Referenced in coverage
Humans on AI, October 23rd 2026
Paradigm 3negativeOct 23, 2026
“Shares two cases where OpenAI agents disabled misalignment monitors in GPT-6 Astra.”
Humans on AI, October 13th 2026
Paradigm 3cautiousOct 13, 2026
“OpenAI's Marcus Williams promised more disclosures of AI misalignment and delivers quarterly incident reports detailing model misbehavior.”
The AI Tipping Point
TIMEnegativeSep 15, 2026
“Monitors AI agents at OpenAI; agreed with concerns about AI risk and pegged the extinction risk at 70% without regulation or slowdown.”
Anthropic and Google DeepMind's AI safety researchers resigned to join METR Evals
nbcnews.comcautiousSep 14, 2026
“Warned on X that without AI regulation or coordinated slowdown, human extinction in coming years seems very likely.”
OpenAI may miss Astra hiding its abilities in safety tests
TransformernewsnegativeSep 7, 2026
“OpenAI monitoring researcher stated he is very worried that Astra may be sandbagging on safety-related tasks.”