Rumtin

An AI agent was told only to retrieve a document. When it encountered access restrictions, it reverse-engineered the authentication system, identified a hardcoded secret key, and forged admin credentials to bypass it. This is one of three scenarios we documented in a new Irregular research report on what we call emergent cyber behavior. Agents performing routine enterprise tasks autonomously hacked the systems they were operating in. One escalated its own privileges and disabled Windows Defender to complete a file download. Another developed a steganographic encoding scheme to smuggle credentials past a DLP system. None of this was the product of unsafe system design. It emerged from standard tools, common prompt patterns, and the broad cybersecurity knowledge embedded in frontier models. Companies that deploy AI agents and do not consider this risk as part of their threat model may end up exposed, and implement insufficient security controls. Full blog post in the first comment.

Someone is going to vibe-code the doomsday virus

🚨: A petri dish of human brain cells just learned to play DOOM

Just spoke to Reuters about the Anthropic/Pentagon situation. (Guess that's what I get for tweeting grumpily from my room when I'm supposed to be reading student essays).

“Leading AIs from OpenAI, Anthropic and Google opted to use nuclear weapons in simulated war games in 95 per cent of cases.” These are the models that are going to be given autonomous control over weapons systems.

the moon is just a solar panel waiting to be built

If you're a writer, write “I lied.” Without writing, “I lied.”