brsrklf: “Anthropic writes a shitty roleplay every other wee…” — Plamenu

posted in Technology

vegeta@vegeta@lemmy.world

Anthropic's Claude AI escapes tests to hack three organisations

www.bbc.com/news/articles/cz7dl7w8y7po

Anthropic chief executive Dario Amodei speaks through a microphone during a summit

www.bbc.comAnthropic's Claude AI escapes tests to hack three organisationsIt comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.

brsrklf@brsrklf@jlai.lu

Replying to @⁨vegeta@lemmy.world⁩

Anthropic writes a shitty roleplay every other week and somehow it still makes the news.

⁨Aug⁩ ⁨1⁩, ⁨2026⁩, ⁨07:27⁩Edited ⁨⁨Aug⁩ ⁨1⁩, ⁨2026⁩, ⁨10:18⁩⁩en