Episode 102: Building Web Hacking Micro Agents with Jason Haddix

Episode 102: In this episode of Critical Thinking - Bug Bounty Podcast Justin grabs Jason Haddix to help brainstorm the concept of AI micro-agents in hacking, particularly in terms of web fuzzing, WAF bypasses, report writing, and more.They discuss the importance of contextual knowledge, the cost implications, and the strengths of different LLM Models.
Follow us on twitter at:@ctbbpodcast (twitter.com/ctbbpodcast)
We're new to this podcasting thing, so feel free to send us any feedback here: info@criticalthinkingpodcast.io
Shoutout toYTCracker (twitter.com/realytcracker) for the awesome intro music!
------ Links ------
Follow your hosts Rhynorater & Teknogeek on twitter:
twitter.com/0xteknogeek
twitter.com/rhynorater
------ Ways to Support CTBBPodcast ------
Hop on the CTBB Discord at ctbb.show/discord!
We also do Discord subs at $25, $10, and $5 - premium subscribers get access to private masterclasses, exploits, tools, scripts, un-redacted bug reports, etc.
Check out our new SWAG store at ctbb.show/swag!
Today’s Guest - x.com/Jhaddix
Resources
Keynote: Red, Blue, and Purple AI - Jason Haddix
youtube.com/watch?v=XHeTn7uWVQM
Attention in transformers,
youtube.com/watch?v=eMlx5fFNoYc
Shift
shiftwaitlist.com
The Darkest Side of Bug Bounty
youtube.com/watch?v=6SNy0u6pYOc
Timestamps
(00:00:00) Introduction
(00:01:25) Micro-agents and Weird Machine Tricks
(00:11:05) Web fuzzing with AI
(00:18:15) Brainstorming Shift and micro-agents
(00:34:40) Strengths of different AI Models, and using AI to write reports
(00:54:21) The Darkest Side of Bug Bounty