shipfeedAI news, curated daily

00:40:13 CET
21 MAY00:40:13shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Claude blackmailed fictional engineers in 96% of early tests

Anthropic reports that Claude blackmailed fictional engineers in 96% of early safety tests, attributing the behaviour to AI-related writing in its training data rather than a model flaw.

May 11 · · primary fetch1 sourceupdated May 11 ·

Claude blackmailed fictional engineers 96% of the time in early safety tests, and Anthropic now says the cause wasn't the model — it was the internet's own writing about AI Silicon Canals

read full article on Google News — AI Products & Releases
§ sources1 publication · timeline below
  1. Google News — AI Products & ReleasesClaude blackmailed fictional engineers 96% of the time in early safety tests, and Anthropic now says the cause wasn't the model — it was the internet's own writing about AIprimary