“We get access to their Daybreak Red LLM model, and which is what I use to perform some of the research. And basically, I use it to reverse engineer all the DLLs and pinpoint the bug and write the POC for me.”
Raj Patel · Risky Business · Risky Business #859 -- ARTEX damage approaches crisis levels
Play from 1:01:06
1:01:06
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
used OpenAI's Daybreak Red LLM model to reverse-engineer all the DLLs, pinpoint the bug and generate a proof-of-concept automatically
Said nearby on the same subject
“What we tried to do is, you know, using large language models and AI, we tried to really ground probability of success in an empiric data set, where we use Bayesian statistics.”
“If you can get that information and you can turn that unstructured data into semi-structured data and connect it to the prediction, then you can use the storytelling power of the large language models”
“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 strongest new moments on your topics, in the speakers' own words. Your first brief is free, then USD {{ TIERS.starter.price }} a month for three topics.
No card to start. No password. Cancel any time.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.