<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Go on Allanderek's blog</title><link>https://blog.poleprediction.com/tags/go/</link><description>Recent content in Go on Allanderek's blog</description><generator>Hugo -- 0.139.0</generator><language>en-us</language><lastBuildDate>Sat, 15 Aug 2026 11:27:15 +0000</lastBuildDate><atom:link href="https://blog.poleprediction.com/tags/go/index.xml" rel="self" type="application/rss+xml"/><item><title>Link: Why Go is an Ideal Language for AI-Assisted Software Engineering</title><link>https://blog.poleprediction.com/posts/link-go-and-ideal-llm-language/</link><pubDate>Sat, 15 Aug 2026 11:27:15 +0000</pubDate><guid>https://blog.poleprediction.com/posts/link-go-and-ideal-llm-language/</guid><description>&lt;p>The Google developers blog has published a post &lt;a href="https://developers.googleblog.com/why-go-is-an-ideal-language-for-ai-assisted-software-engineering/">Why Go is an Ideal Language for AI-Assisted Software Engineering&lt;/a>.&lt;/p>
&lt;p>How to say this nicely, I don&amp;rsquo;t think much of this post.&lt;/p>
&lt;p>First of all, I think this is a great area of active research. Just as we aren&amp;rsquo;t terribly sure about what makes a good programming language for humans, we also do not know exactly what makes a good programming language for LLMs. It does seem that it is useful to have a lot of code from a programming language in the training data for an LLM, but I think that&amp;rsquo;s a slightly different (if more pragmatic) question than what makes a fundamentally good programming language for an LLM. But note also, if we determined some kind of fundamentally good programming language (even a new one) for an LLM we could probably get over the lack of training data in several ways.&lt;/p></description></item></channel></rss>