<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>pedro.dev.br</title><link>https://pedro.dev.br/</link><description>Things I’ve worked on, written down.</description><language>en-US</language><atom:link href="https://pedro.dev.br/en/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Reverse Engineering with AI: Give the Agent a Way to Be Wrong</title><link>https://pedro.dev.br/posts/reverse-engineering-with-ai/</link><guid>https://pedro.dev.br/posts/reverse-engineering-with-ai/</guid><pubDate>Fri, 13 Nov 2026 00:00:00 -0300</pubDate><description>&lt;p&gt;“What does this function do?” can take you through half a binary before you have an answer. I was doing that work long before coding agents existed, and I still enjoy following the clues. With an agent, though, I can spend less time chasing each one myself. It can investigate a call, suggest a structure, or recognize a compiler idiom while I work on the larger question. That change in pace made me want to try more ambitious projects.&lt;/p&gt;</description></item></channel></rss>