“We took the C code that existed and ported it to Rust using an LLM and then using differential fuzzing to ensure that the ported code to Rust was correct.”
♫
Said on "The Cognitive Revolution"
“We had a hypothesis about where to look for bugs… focused on device drivers… then differential fuzzing… ported to Rust using an LLM… formal verification.”
"The Cognitive Revolution" · AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs
Play from 41:10
41:10
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
used a hypothesis-driven methodology focusing on low-scrutiny kernel components (device drivers), wrote formal specs, then applied differential fuzzing, LLM-assisted porting to Rust, and finally formal verification
Said nearby on the same subject
“‘One of the biggest news is GPT 5.6 wrote more efficient kernels. So Terra and Luna could be 80% cheaper.’”
♫
Said on Latent Space: The AI Engineer Podcast
“Property manager raises rent every quarter… if you can predict when those rent increases are going to happen, then that can help also with your pro forma and cash flow.”
JW
Jason Williams
Ironclad Underwriting Podcast ·
“Asked Gemini for Argon for an interactive museum… it scraped archival Mac photos, wrote a tool to clean the images, pulled 50 years of specs, and built a 3-D cover flow”
♫
Said on The AI Daily Brief: Artificial Intelligence News and Analysis
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.