AIA Few Thoughts ...1h ago
Anthropic's cryptanalysis results on HAWK and AES show AI can now
Anthropic's cryptanalysis results on HAWK and AES show AI can now understand existing cryptanalysis results, turn them into new attacks, and even extend them
Yesterday Anthropic published two new cryptanalysis results, both outputs of Claude Mythos, their (still) unreleased advanced model.
Read full articleSource: A Few Thoughts ... · Opens in new tab