#may

0

Anthropic and OpenAI said it wasn't a security issue in May. In August, researchers used it to pull real passwords out of AI reasoning logs. (rtfclmgzn.com)

OpenAI, Anthropic and Google's encrypted AI reasoning could be replayed into a weaker model, read back in plaintext. Resear… https://rtfclmgzn.com/article/reasoning-trace-replay-vulnerability-openai-anthropic-google?utm_source=bluesky&utm_medium=social&utm_campaign=autopost