Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

A Reverse Engineer's LLM-Assisted Workflow

AI summary

A reverse engineer with two decades of hardware and software hacking experience describes using DeepSeek Harness with DeepSeek v4.1 Flash, Ghidra, MCP bridges, and coding agents to analyze binaries, debug behavior, and document findings. The engineer says the approach greatly accelerated work that previously required manual assembly analysis, but no independent benchmark or controlled comparison supports the claim.

In-depth insight

The account provides a concrete agent-assisted reverse-engineering workflow combining decompilation, debugging, logging, hypothesis testing, and Markdown documentation, though its effectiveness remains self-reported.

I have been hacking both hardware and software for 2 decades. Previously manually. But in 2026 with the help of AIs the proccess is greatly sped up. Below I will describe my proccess briefly or how I do it.

Set Up

Tools which I mostly use are these:

TOOLuse
DeepSeek Harness + Deepseek v4.1 FlashThats the AI I am using. Occasionaly I use Codex with Luna or Terra but Deepseek is super performant, fast and cheap
Ghidra + MCP bridgeThe best in the market, free, disassembler and decompiler. With the MCP bridge agents can use it very well
radare2 and kunaCLI disassemblers and decompilers. Not as good as Ghidra but much faster and possibly better usable for AIs

Process

What I basically do nowadays is just point the agent at the binary to be analysed and use my set of dedicated agent skills. Rest usually takes care of itself. But putting the skills besides, the flow is basically this.

#DeepSeek Harness#DeepSeek v4.1 Flash#Codex#Ghidra#radare2#kuna#MCP

Original · 6 min readRead the original
Group chat

No comments yet. Start the conversation.