<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on Arthur's blog</title><link>https://blog.aheymans.xyz/tags/llm/</link><description>Recent content in Llm on Arthur's blog</description><generator>Hugo</generator><language>en</language><copyright>Copyright © 2018–2024, Arthur Heymans; all rights reserved.</copyright><lastBuildDate>Thu, 03 Jul 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.aheymans.xyz/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Porting the ThinkPad x61 to coreboot</title><link>https://blog.aheymans.xyz/post/thinkpad_x61/</link><pubDate>Thu, 04 Jun 2026 11:51:11 +0200</pubDate><guid>https://blog.aheymans.xyz/post/thinkpad_x61/</guid><description>&lt;div id="outline-container-headline-1" class="outline-2"&gt;
&lt;h2 id="headline-1"&gt;
An introduction to my IBM/Lenovo ThinkPad addiction
&lt;/h2&gt;
&lt;div id="outline-text-headline-1" class="outline-text-2"&gt;
&lt;p&gt;
Over 10 years ago I got my first ThinkPad x60. I got interested in free software by reading the &lt;a href="https://www.gnu.org/gnu/thegnuproject.html"&gt;about GNU&lt;/a&gt; page in the GNU Emacs editor.
Free software back then and certainly now is quite usable, typically without much closed-source software.
One area where free software is lacking is firmware and this led me to want to try libreboot on that ThinkPad x60.
A few years forward and I became a coreboot contributor and eventually got a job at 9elements because of this.
In that journey I amassed quite a hefty ThinkPad collection.
I wanted something that was speedier and 64-bit so I got a ThinkPad x200 which I ran for a few years.
I got a ThinkPad x220 a few years later, as the Sandy Bridge chip is substantially faster than the Core 2 Duo inside the x200.
To port or improve existing coreboot ports I received a ThinkPad x201 and R500.
A few years back someone figured out a way to get past Boot Guard (&lt;a href="https://github.com/coreboot/deguard"&gt;deguard&lt;/a&gt;
) on Intel Skylake/Kabylake, so I got myself a ThinkPad t480 and I&amp;#39;m very happy with it.&lt;/p&gt;</description></item><item><title>Adding MCP support to Aider via NixOS overrides</title><link>https://blog.aheymans.xyz/post/aider_with_mcp/</link><pubDate>Thu, 03 Jul 2025 16:29:32 +0200</pubDate><guid>https://blog.aheymans.xyz/post/aider_with_mcp/</guid><description>&lt;p&gt;
In software engineering the part I like the least is the actual typing of coding.
LLMs provide a nice solution to this problem. With very precise prompting and the right documentation, code, text, … in the context the code output is very close to how I would write it.&lt;/p&gt;
&lt;p&gt;
My preferred tool until now was &lt;a href="https://aider.chat/"&gt;aider&lt;/a&gt;. It works great, but the development pace seems to have slowed sadly.
One of the latest innovation in the vibe coding space has been &lt;a href="https://modelcontextprotocol.io/introduction"&gt;model context protocol&lt;/a&gt;.
MCP is basically a standardized way to provide tools to LLMs and the majority of the AI coding agents are using it.&lt;/p&gt;</description></item><item><title>Using LLMs in emacs</title><link>https://blog.aheymans.xyz/post/llm_in_emacs/</link><pubDate>Wed, 06 Nov 2024 08:34:52 +0100</pubDate><guid>https://blog.aheymans.xyz/post/llm_in_emacs/</guid><description>&lt;p&gt;
This post will review 2 llm options in emacs how I set them up.&lt;/p&gt;
&lt;div id="outline-container-headline-1" class="outline-2"&gt;
&lt;h2 id="headline-1"&gt;
Ellama
&lt;/h2&gt;
&lt;div id="outline-text-headline-1" class="outline-text-2"&gt;
&lt;video width=100% controls autoplay&gt;
 &lt;source src="https://blog.aheymans.xyz/ellama.webm" type="video/webm"&gt;
 Your browser does not support the video tag.
&lt;/video&gt;
&lt;p&gt;
From &lt;a href="https://github.com/s-kostyaev/ellama"&gt;ellama&lt;/a&gt;&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;Ellama is a tool for interacting with large language models from Emacs. It allows you to ask questions and receive responses from the LLMs. Ellama can perform various tasks such as translation, code review, summarization, enhancing grammar/spelling or wording and more through the Emacs interface. Ellama natively supports streaming output, making it effortless to use with your preferred text editor.&lt;/p&gt;</description></item></channel></rss>