In September I gave a talk at [un]prompted.au in Sydney called To the Frontier and Back Again. The question behind it was simple. What does vulnerability research look like at the frontier right now, and how much of that can I bring back to models I can run myself?

The frontier half is two Windows system-service 0-days, found with Claude Code and Opus 4.8. The first confirmed root cause landed 1 hour, 16 minutes, and 5 seconds after my first request. The back-again half replays the same hunt on open-weight models: same target, same context, same tools.

Thanks to the [un]prompted.au organizers for a really well-run conference. A lot of the program circled the same thing I was there to talk about: agents, local models, and the feedback loops that make them useful.

A small model on a laptop found the bug. The system around it is what told the real one from the thirty that looked just as convincing.

I taught two four-hour workshops at DEF CON 34, both built around one question: how close can local AI models get to frontier-level reverse engineering, and what do I have to build around them to close the gap?

Both workshops came at that question from opposite ends and landed in the same place. The model is rarely what decides whether you find the bug. What decides it is everything around the model: how you feed it evidence, which tools it can reach, where you make it stop, and whether or not you can validate the result.

Clearseclabs is bringing a workshop to REcon 2026 in Montreal: Agentic Reverse Engineering: Building Custom AI Skills with Coding Agents.

We're coming back to REcon. Last year's session focused on MCP-based Ghidra integration, where MCP gave coding agents tool access. This time, Agent Skills give them structured, reusable workflows. We're going to build one end to end.

What I Keep Hearing​

Lately, the same conversation keeps coming up with colleagues, students, and fellow researchers. The shape of it is roughly:

I've started reading and experimenting with AI, and honestly, it's really good. In some areas it's already faster than me. The more I use it, the less I can see what work will be left for us in five years.

The feeling is real, and I've heard it from senior reverse engineers with fifteen years on the keyboard and from people on their first run through Ghidra. The more capable the tools get in your hands, the more your relevance feels uncertain. That's a hard place to operate from.

Here's the part worth holding onto: we've been in this place before. The path out of the worry has been the same every time. Engage with the new tool early. Stay ahead of it by working with it.

If you're curious about how AI can accelerate your reverse engineering workflows, check it out. Especially useful if you're looking to get started with agentic RE.

The video is up from our talk at RE//verse 2026 in Orlando, Agentic Diffing Apple Security Updates.

The powerful AI made it likelier that the consultants "fell asleep at the wheel" and made big errors when it counted. -- Ethan Mollick, Co-Intelligence

Ethan Mollick has a warning for anyone using AI: the better it gets, the easier it is to stop paying attention. When outputs are polished and instant, you stop thinking critically. You stop building skill. You become a passenger.

He's right, but only if you're using AI wrong.

"Reverse engineering workflows are evolving, and local LLMs are reshaping how we analyze binaries, automate tooling, and preserve privacy." – CSL

"It’s exciting to see open-source tools like ghidriff shaping the research frontier. This new paper validates what many of us have been building toward: diffing as the perfect context for LLMs, and agentic pipelines that turn binary changes into actionable security insight." – CSL

"We had an incredible time walking participants through the full arc—from scripting custom CLI tools in Ghidra to launching their own fully functional MCP servers. Watching people connect reverse engineering workflows to natural language interfaces felt like watching the future unfold in real time. The energy in the room was electric and the hands-on breakthroughs made this one of our most rewarding sessions yet. We wrapped up by meeting a ton of brilliant folks at the after party where great ideas and fresh perspectives flowed straight from the community." - CSL

Conference speaking and training opportunity at 44CON, a public event bringing together the best in UK and International information security research and networking opportunities and trainer teaching