Sveriges mest populära poddar
Risky Business Features
Teknologi

Feature Interview: Nicholas Carlini, Anthropic

43 min•24 april 2026

In this episode, Anthropic’s Nicholas Carlini joins Patrick Gray and James Wilson to talk about advancements in AI-driven vulnerability research and exploit development.

Nicholas’ talk at the recent [un]prompted conference demonstrated how Anthropic’s Opus 4.6 could find and exploit vulnerabilities in popular open source projects. In the short few weeks since then, Anthropic announced a new model that’s already identifying hundreds of bug fixes across critical software. Nicholas talks us through the work he does at Anthropic, what’s possible and the limitations with current frontier models, and where this goes from here.

This episode is also available on YouTube

Show notes

Fler avsnitt av Risky Business Features

Visa alla avsnitt av Risky Business Features
A deep dive on AI model distillation attacks
•1 tim 12 min
A builder's perspective on Mythos and frontier models
•33 min
Mythos and 0day: Fixing exploits is not safety
•21 min
Mythos and 0day: A hacker’s perspective
•33 min
What happens after North Korea infiltrates?
•52 min
Why CISOs need to be more flexible in the AI era
•19 min
A Risky Biz Experiment: Hunting for iOS 0day with AI
•56 min
Interview: Former NSA and CIA cyber leaders on offensive AI
•15 min
When disaster strykes
•40 min
MCP is Dead
•37 min

Risky Business Features med Risky Business Media finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.