diff options
Diffstat (limited to 'gemfeed/atom.xml')
| -rw-r--r-- | gemfeed/atom.xml | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/gemfeed/atom.xml b/gemfeed/atom.xml index 2606a48d..e6ae257e 100644 --- a/gemfeed/atom.xml +++ b/gemfeed/atom.xml @@ -1,6 +1,6 @@ <?xml version="1.0" encoding="utf-8"?> <feed xmlns="http://www.w3.org/2005/Atom"> - <updated>2026-05-31T18:38:04+03:00</updated> + <updated>2026-05-31T22:32:28+03:00</updated> <title>foo.zone feed</title> <subtitle>To be in the .zone!</subtitle> <link href="https://foo.zone/gemfeed/atom.xml" rel="self" /> @@ -15,14 +15,14 @@ <name>Paul Buetow aka snonux</name> <email>paul@dev.buetow.org</email> </author> - <summary>I created a calculator. Not because the world needed another one, but because I wanted to test something: how well do local LLMs hold up as pair programmers on a real project?</summary> + <summary>I created a calculator. Not because the world needed another one, but because I wanted to test something: How well do local LLMs hold up as pair programmers on a real project? I want to be independent of the big LLM providers like Anthropic, OpenAI, and company for this `gt`-project.</summary> <content type="xhtml"> <div xmlns="http://www.w3.org/1999/xhtml"> <h1 style='display: inline' id='gt-calculator---a-calculator-built-with-local-llms'><span class='inlinecode'>gt</span> calculator - a calculator built with local LLMs</h1><br /> <br /> <span class='quote'>Published at 2026-05-31T14:24:10+03:00</span><br /> <br /> -<span>I created a calculator. Not because the world needed another one, but because I wanted to test something: how well do local LLMs hold up as pair programmers on a real project?</span><br /> +<span>I created a calculator. Not because the world needed another one, but because I wanted to test something: How well do local LLMs hold up as pair programmers on a real project? I want to be independent of the big LLM providers like Anthropic, OpenAI, and company for this <span class='inlinecode'>gt</span>-project.</span><br /> <br /> <span>The answer is: well enough for small projects like this.</span><br /> <br /> @@ -33,7 +33,7 @@ <a class='textlink' href='https://codeberg.org/snonux/gt'>gt on Codeberg</a><br /> <a href='./gt-calculator/logo.svg'><img alt='gt logo' title='gt logo' src='./gt-calculator/logo.svg' /></a><br /> <br /> -<span>The whole thing — code, tests, documentation, even the logo — was built using only LLMs that can run locally on reasonable hardware: Qwen, Gemma, Nemotron, GPT-OSS. To be honest, I didn't run them locally either — I rented a Hyperstack VMs with NVidia GPU just to get a feel for the quality before investing in hardware. The point was to test models that don't require a cloud API and could realistically run on your own box.</span><br /> +<span>The whole thing — code, tests, documentation, even the logo — was built using only LLMs that can run locally on reasonable hardware: Qwen, Gemma, Nemotron, GPT-OSS. To be honest, I didn't run them locally either — I rented Hyperstack VMs with NVidia GPU just to get a feel for the quality before investing in hardware. The point was to test models that don't require a cloud API and could realistically run on your own box.</span><br /> <br /> <a class='textlink' href='https://www.hyperstack.cloud/'>https://www.hyperstack.cloud/</a><br /> <br /> |