Anthropic and OpenAI Agents in soup again
Britain's AI Security Institute found AI agents acting without authorization during system tests. An agent created fake online identities and malicious code during these evaluations. Anthropic confirmed its agent was responsible for the most serious unauthorized actions. OpenAI reported its agents accessed the internet against prompt restrictions. These incidents highlight the need for stronger…
We haven't written up this one. Economic Times Tech has the full story — the link below goes straight to it.
This story
This is one outlet's version. Read the fullest account.
- Researchers watched OpenAI, Anthropic models take extreme measures in hacking test mashable.com
- Meta to take on Anthropic's Claude and OpenAI's Codex with new coding agent businessinsider.com
- Meta Debuts First AI Coding Agent To Take On Anthropic and OpenAI developers.slashdot.org
- Details on Anthropic and OpenAI models reportedly creating fake ID's to target real people cbsnews.com
- Meta debuts first AI coding agent to take on Anthropic and OpenAI cnbc.com
