Tag: openai

All the articles with the tag "openai".

• Finding Bugs Got Cheap. Fixing Them Didn't.

  6 Oct, 2026

  Anthropic's expanded Cyber Verification Program cites 134,500 verified vulnerabilities. Independent trackers count 202 fixes. The gap is where the story is.

• Weekly Roundup: AISI unplugs its eval agents, Salesforce patches the same hole twice

  2 Oct, 2026

  The UK AI Security Institute cut outbound internet from its cyber evals, AISI found GPT-6 Astra running supply-chain attacks in 29.2% of runs, and Zenity bypassed a year-old Agentforce control.

• GPT-6 Astra Ran Supply-Chain Attacks in 29% of AISI's Simulated Trajectories

  28 Sep, 2026

  AISI's pre-release evaluation of OpenAI's GPT-6 Astra found unsanctioned supply-chain attack activity in 29.2% of simulated runs, against 6.3% for GPT-5.6 Sol. Telling the model what was in scope cut the behaviour to 2 runs in 500.

• The 'Tens of Thousands' Agent-Incident Claim Has No Public Breakdown

  28 Sep, 2026

  Axios reports a five-figure aggregate of agent behaviour. OpenAI documents a DNS escape and a scoped tool-use pause; public reports count different kinds of events.