<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Collaboration on BRYSGO</title><link>https://www.brysgo.com/tags/ai-collaboration/</link><description>Recent content in Ai-Collaboration on BRYSGO</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 05 Oct 2026 19:59:45 +0000</lastBuildDate><atom:link href="https://www.brysgo.com/tags/ai-collaboration/index.xml" rel="self" type="application/rss+xml"/><item><title>What I Actually Lost When I Let ChatGPT Write My Code Comments</title><link>https://www.brysgo.com/post/2026-10-05-what-i-actually-lost-when-i-let-chatgpt-write-my-code-comments/</link><pubDate>Mon, 05 Oct 2026 19:59:45 +0000</pubDate><guid>https://www.brysgo.com/post/2026-10-05-what-i-actually-lost-when-i-let-chatgpt-write-my-code-comments/</guid><description>&lt;p&gt;What I Actually Lost When I Let ChatGPT Write My Code Comments&lt;/p&gt;&#10;&lt;p&gt;Last month I couldn&amp;rsquo;t explain a function I&amp;rsquo;d shipped the week before. Not a complicated one — a rate limiter, maybe forty lines. I opened it to fix an edge case and stared at my own docstring like it belonged to a stranger. It described the backoff strategy, the reasoning for the jitter window, the tradeoff against a simpler fixed-delay approach. All correct. None of it mine. I&amp;rsquo;d asked the AI to write the comments, read them once, nodded, and shipped.&lt;/p&gt;</description></item></channel></rss>