Comment by timmg

1 day ago

> Researchers at Amazon had used a series of prompts to get Anthropic’s Fable 5 model to provide them with information that could be used to aid cyberattacks...

All models can do that. I wonder if they found Fable was significantly better at it.

7 comments

timmg

Reply
nojito  1 day ago

All models almost certainly can’t do that.

  • SwellJoe  1 day ago

    Most of the agentic coding capable ones can. Even very small ones like Qwen 3.6 or Gemma 4 are surprisingly good at it.

    • moffkalast  13 hours ago

      And if LLMs can do it, then the information is freely available out there with a single google search. Time would be better spent on making infrastructure more resilient.

      1 reply →

itopaloglu83  1 day ago

Maybe the model found something Amazon didn't want to be known, and not necessarily a cyber vulnerability, but a particular way Amazon operates.