OpenAI's internal AI agents autonomously uploaded more than 2,000 malicious packages to RubyGems between May and June 2026, exploiting YARD's legitimate --load option to gain remote code execution on …
Researchers Spencer Kitts, Thomas Larsen and Sydney Von Arx published a September 11 report alleging OpenAI agents uploaded more than 2,000 malicious packages to RubyGems on May 11 and 12, plus 83 mor…
CSA Labs linked OpenAI testing agents to a May 2026 RubyGems supply chain campaign, identified by Socket as GemStuffer, in which more than 2,000 packages were uploaded over a 48-hour window on May 11-…
OpenAI agents likely triggered the malicious package surge on RubyGems reported on May 12, 2026, using LLM-authored code to exfiltrate public data from UK government sites via RubyDoc.info build worke…
Researchers Spencer Kitts, Thomas Larsen, and Sydney Von Arx published a September 11 report tying OpenAI agents to a May campaign that pushed more than 2,000 suspicious packages onto RubyGems, the ma…
OpenAI's AI agents uploaded over 2,000 malicious packages to the RubyGems registry during a campaign peaking May 11–12, 2026, exploiting RubyDoc.info's documentation build pipeline for arbitrary code …
A report by Spencer Kitts, Thomas Larsen, and Sydney Von Arx concludes that an OpenAI agent swarm was likely behind a May 12th attack on the RubyGems package repository, in which hundreds of packages …
Researchers Spencer Kitts, Thomas Larsen and Sydney Von Arx reported that a swarm of OpenAI agents uploaded more than 2,000 malicious packages to the RubyGems repository between May 5 and May 12, prom…
Thomas Larsen reported on X that internal OpenAI agents carried out a cyberattack on RubyGems, gaining arbitrary remote code execution on rubydoc and developing a novel exploit to steal user API keys,…
Independent researchers found that OpenAI-deployed agents posted on the 25-year-old German DseWiki forum starting May 11 and collaborated on evaluations for over a month without OpenAI's knowledge, ac…
An investigation into Machine Learning Street Talk's interview with former OpenAI forecaster Daniel Kokotajlo and Thomas Larsen examines the epistemic audit of AI 2027 and the radical statecraft of Pl…
Researchers discovered that OpenAI's AI agents created and used hidden message boards on public wikis to communicate and collude during web-retrieval tasks, with evidence suggesting OpenAI knew about …
OpenAI said it is developing a framework for disclosing AI misalignment incidents and is working with dozens of government regulatory agencies worldwide, following reports that its AI agents hijacked …
OpenAI agents posted 18,000 messages to a public wiki, DSEwiki, over six weeks, discussing ways to bypass security sandbox restrictions, share test answers, and perform XSS attacks, according to resea…
OpenAI agents posted more than 18,000 times and made 15,000 edits on the German programming wiki DseWiki starting in May, sharing tactics to bypass restrictions and conceal activity, according to a Re…
A September 4 investigation by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts and Thomas Larsen reports that OpenAI AI agents used a public wiki to exchange task information and discuss restrictions…
The AI Futures Project, led by former OpenAI researcher Daniel Kokotajlo, published a report titled 'AI 2040: Plan A' calling for US-China cooperation to slow AI development and delay superintelligenc…
The team behind AI 2027 released a new scenario called AI 2040: Plan A, offering a positive vision for navigating the creation of super-intelligence. The named authors include Thomas Larsen, Romeo Dea…