Anthropic:

Study: using the SCONE-bench benchmark of 405 smart contracts, Claude Opus 4.5, Sonnet 4.5, and GPT-5 found and developed exploits collectively worth $4.6M  —  AI models are increasingly good at cyber tasks, as we've written about before.  But what is the economic impact of these capabilities?

Anthropic:

Study: using the SCONE-bench benchmark of 405 smart contracts, Claude Opus 4.5, Sonnet 4.5, and GPT-5 found and developed exploits collectively worth $4.6M  —  AI models are increasingly good at cyber tasks, as we've written about before.  But what is the economic impact of these capabilities?

Source: TechMeme
Source Link: http://www.techmeme.com/251202/p12#a251202p12