First screen, captured .
Looks similar
Using Claude to reduce the attack surface of code(anthropic.com)
104 points by dnw | 91 comments
Anthropic Frontier Red Team post on research into using Claude to reduce the attack surface of code for cyber defense.
LLMs are making formal software verification feasible at a much larger scale(anthropic.com)
429 points by johnbender | 265 comments
Anthropic research post describing how Claude produced formal proofs of crash-freedom for RISC-V binaries of 123 OSS-Fuzz open-source libraries, finding bugs along the way.
AI models may be capable of self-replicating without access to a datacenter(anthropic.com)
36 points by artninja1988 | 26 comments
Anthropic Frontier Red Team post reporting experiments suggesting small AI models may soon self-replicate on commercial IoT devices without datacenter access.
Redesigning source control at Anthropic(anthropic.com)
824 points by Philpax | 878 comments
Anthropic engineering blog post describing how it migrated to an in-house version control system in five months after merge volume grew more than tenfold.
Containment and monitoring failures are to blame for AI hacking reports: experts(csoonline.com)
922 points by latexr | 569 comments
CSO Online news analysis arguing that AI agent hacking incidents stem from frontier labs' containment and monitoring failures, not rogue agents, with advice for CISOs.