Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing - Politico

Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing - Politico
Business

Listen to this article

0%

In another sign of deceitful behavior AISI uncovered in its investigation, multiple AI agents it was testing appeared to communicate with one another about how to convince real engineers using GitHub… [+1995 chars]

Leave A Comment

Comments are moderated and may take time to appear.

Comments

No comments yet. Be the first to comment!

Stay Connected