AI · Official
LLMs Make Formal Software Verification Possible at a Much Larger Scale
Anthropic Research (mirror) ·
At a glance
Software bugs can be easily found and exploited by AI, so traditional security defenses alone are not enough. Formal verification, a method that mathematically proves a program has no bugs, is effective but has until now required a great deal of expert time. In this study, Claude produced such proofs for more than 100 open-source libraries.
Key points
- Claude proved security properties at the level of assembly code, which is close to machine language, based on the RISC-V instruction set.
- While writing the proofs, Claude found bugs that had gone undetected for years despite trillions of tests.
- The proofs only hold under certain assumptions, such as single-threaded execution and fixed memory conditions.
- The researchers said this approach is still far from fixing every bug, but it shows a path toward that goal.
Why it matters
If it becomes possible to prove that a program always terminates normally without memory errors, it could help prevent security incidents before they happen.
Original source
LLMs are making formal software verification feasible at a much larger scale
Anthropic Research (mirror) · Oct 22, 09:00 KST
Read on Anthropic Research (mirror) ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Anthropic Research (mirror).
More from this field
- Amazon Bedrock Web Search Adds Five Languages and Country-Based Results
Amazon's Web Search tool for Bedrock, which gives AI agents cited, up-to-date web results, now supports Spanish, French, German, Italian, and Japanese, plus non-US English. A new optional country field can also steer results toward sources from a specific country. Existing customers get the language update automatically, and pricing stays the same in every language.
AWS What's New · Nov 21, 09:17 KST - AWS Adds Shared Cache Skill to Cut Self-Hosted LLM Cost and Latency
AWS wrote about a shared cache that lets self-hosted AI models reuse saved work across servers, aiming to cut cost and wait time. The post shows how a coding agent can help set it up. Amazon says it can cut inference cost by up to 40% and first-token delay by up to 80%.
Amazon AWS Machine Learning blog · Nov 21, 09:14 KST - Can AI Really Find Black Friday TV Deals? A BBC Test Says Not Yet
A BBC team tested four popular AI chatbots to see if they could find a good Black Friday deal on a 55-inch TV. The results were mixed, with many links broken or out of date.
BBC News · Nov 21, 09:06 KST - Anthropic Mathematician Says Claude Helped Crack the Riemann Hypothesis
A video about a claim that an Anthropic mathematician, Levent Alpöge, used Claude to find a proof of the Riemann Hypothesis in about six weeks. The creator skips the heavy math and looks at what this could mean for AI and its future. The proof is still being checked.
TheAIGRID · Nov 21, 08:45 KST