Skip to main content
AmigoFish

Valentina Palmiotti (chompie) on Vulnpocalypse, Matching Mythos on a Budget

From Three Buddy Problem · · 1 hr 8 min

This plays from the publisher's own server. We do not host a copy.

Open at the source

Not rated yet

Description

(Presented by TLPBLACK (https://tlpblack.net): A cybersecurity intelligence platform focused on sharing curated, high-sensitivity threat insights and research with trusted security professionals.)

Three Buddy Problem x Offensive AI Con: Live from OAIC, IBM X-Force's Valentina Palmiotti (chompie) walks us through the autonomous Windows kernel exploit pipeline she built on older Claude models, which landed within a hair of Mythos for about $180 a chain.

Plus, the Pwn2Own bug Claude called unexploitable, why her Pwn2Own bugs still sit unpatched, disappearing exploit techniques, the dread of being a defender, and how Phrack found its way back into print.

Timestamps:

0:00 Intro and Pwn2Own war stories

3:46 What vibe hacking means

8:16 When long agent runs go sideways

10:31 Self-verification in an n-day kernel pipeline

16:11 Matching Mythos for $180 a chain

18:42 The bug Claude called unexploitable

21:49 Unpatched bugs and the defender gap

25:37 Mythos arrives through CVP

27:00 Models only know public techniques

32:01 Testing models on held-back bugs

37:45 Inside chompie's daily workflow

46:07 Where's the exploitpocalypse?

50:07 Pixel drops MTE

53:40 Advice for defenders: design for containment

58:34 Phrack is back

Links:

- Transcript (https://docs.google.com/document/d/1b-8J4ptCzFrNonXJwplyqETPbykOVGGDOrWGUdPmgqE/edit?tab=t.0)

- Valentina Palmiotti (chompie) on Twitter (https://x.com/chompie1337)

- chompie at the bits (https://chomp.ie/Home)

- Valentina Palmiotti | LinkedIn (https://www.linkedin.com/in/valentina-palmiotti-67012273/?isSelfProfile=false)

- Confirmed! @chompie1337 $20,000 Pwn2Own Victory (https://x.com/thezdi/status/2054979210909827293?s=20)

- Interview with Valentina Palmiotti, Pwn2Own Berlin 2026 (https://thecyberwire.com/podcasts/ai-security-brief/5/notes)

- Expanding the Cyber Verification Program \ Anthropic (https://www.anthropic.com/news/cyber-verification-program)

- Racing against the clock -- hitting a tiny kernel race window - Project Zero (https://projectzero.google/2022/03/racing-against-clock-hitting-tiny.html)

- Building an Autonomous N-day Exploit Generation Pipeline (https://cfp.bsidescbr.com.au/bsides-canberra-2026/talk/TFBH8S/)

- Pixel 11 lost a security feature (MTE) (https://www.notebookcheck.net/Leaked-documents-show-Google-planned-and-then-cut-a-key-Pixel-11-security-feature-for-GrapheneOS.1382732.0.html)

- Firecracket - Secure and fast microVMs for serverless computing (https://github.com/firecracker-microvm/firecracker)

- tmp.0ut (https://tmpout.sh/1/0.html)

- Phrack Magazine (https://phrack.org/)

- Offensive AI Conference (https://www.offensiveaicon.com/)

- TLPBLACK (https://tlpblack.net/)

Back to Three Buddy Problem · Report a problem