Anthropic set Claude on 25 open-source projects and it found 493 flaws
Anthropic set Claude to work on attack surface reduction across 25 open-source projects, and it flagged 493 issues. One misconfiguration had sat unnoticed in widely used software for 21 years.
Via TNW | Anthropic
Anthropic pointed its Claude models at 25 widely used open-source projects and set them a different task: not finding individual bugs, but finding code that attackers can reach when they should not be able to. Claude flagged 493 such issues. One of them had sat in the software for 21 years.
The work is a preview of research from Anthropic’s Frontier Red Team, written up by security engineer Chris Rohlf and published on Monday. Anthropic calls the approach attack surface…
Courtesy
This story was originally published by TNW | Anthropic. All rights belong to the original publisher.
Read the original on thenextweb.com ↗