Has anyone used agents to decompile binary executables?

<!-- SC_OFF --><div class="md"><p>I've been thinking about this as local models get better at </p> <p>tool use — shell access, file system, HTTP requests, MCP. </p> <p>If a prompt

<!-- SC_OFF --><div class="md"><p>I’ve been using Fable and Codex a lot lately and keep hitting usage limits. For a while I had Fable call Codex as a sub-agent to spread usage

<!-- SC_OFF --><div class="md"><p>I’ve been in QA for almost a decade. My mental model for quality was always: given input X, assert output Y. Now I’m on a team that’s shipping an

<!-- SC_OFF --><div class="md"><p>Hi, I'm an ML person, that's been doing a bit more engineering and a bit less research for a while. And now for a thesis I'm researching models

<!-- SC_OFF --><div class="md"><p>I have been building a framework that captures HTTP traffic from websites and generates Python CLIs. Currently uses Claude Opus, but curious

<!-- SC_OFF --><div class="md"><p>I’ve been using <code>claude code -p</code> to execute workflows inside an agent and process tasks in a non-interactive way, which has been

<!-- SC_OFF --><div class="md"><p>Thoughts on implementing additional security to Nanobot/Nanoclaw. If anyone has a fully developed system, would love to hear more!</p> </div><!--

<!-- SC_OFF --><div class="md"><p>With all this talk about Mythos being able to hack into. US government systems, I was wondering if anyone has tried to get root on their own