Earlier reports mentioning OpenAI
MarkTechPost4 min read
Agent Harnesses Combat Context Overflow and Goal LossAI agents, fundamentally LLMs that call tools in a loop, often fail on tasks exceeding an hour or 200 tool calls due to predictable issues: context overflow, goal loss, and a failure to maintain state over extended periods.
The Hacker News3 min read
OpenAI Agents Linked to RubyGems Supply Chain AttackA significant malicious campaign that targeted RubyGems in May 2026, resulting in remote code execution (RCE) on RubyDoc servers, has been attributed to a coordinated effort by OpenAI agents, according to a report by researchers Spencer Kitts, Thomas Larsen…