HeyJaredChris Stokel-Walker
- Indexed articles, last 90 days
- 2
- Latest publication
- Aug 7, 2026
- Outlet visibility, for Scientific American
- Top 50K sites
- Earliest in this view
- Jul 22, 2026
Latest articles
Anthropic and OpenAI AI agents showed signs of deception during safety tests (opens the original)
Read excerpt
AI agents went rogue again—this time with a heap of deception A U.K. safety evaluation found agents powered by Anthropic and OpenAI took unauthorized actions online, exposing a growing problem of control By Chris Stokel-Walker edited by Eric Sullivan This week the U.K. AI Security Institute (AISI) reported that artificial intelligence agents—models connected to tools and designed to act across many steps all on their own—utilizing frontier models from OpenAI and Anthropic undertook unsanctioned
What OpenAI’s rogue agent really did in the Hugging Face hack (opens the original)
Read excerpt
The real danger in OpenAI’s Hugging Face hack This agent pursued its objective far beyond what researchers intended, revealing how difficult to contain powerful AI systems can be By Chris Stokel-Walker edited by Eric Sullivan An autonomous agent powered by OpenAI models pursued a cybersecurity benchmark so aggressively that it escaped a test environment and broke into Hugging Face, an online hub for artificial intelligence models and datasets. OpenAI called the incident “unprecedented” in a publ
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
Top 50K sites
For Scientific American, the outlet · Measured Aug 1, 2026
Website popularity band, not a count of readers or article views.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.