From 836215de2e774cbb57b310ffba737e04a03f6358 Mon Sep 17 00:00:00 2001 From: Paul Buetow Date: Sun, 31 May 2026 22:32:39 +0300 Subject: Update content for gemtext --- gemfeed/2026-06-01-gt-calculator.gmi | 4 ++-- gemfeed/2026-06-01-gt-calculator.gmi.tpl | 4 ++-- gemfeed/atom.xml | 8 ++++---- index.gmi | 2 +- uptime-stats.gmi | 18 +++++++++--------- 5 files changed, 18 insertions(+), 18 deletions(-) diff --git a/gemfeed/2026-06-01-gt-calculator.gmi b/gemfeed/2026-06-01-gt-calculator.gmi index ee5241e7..a208d244 100644 --- a/gemfeed/2026-06-01-gt-calculator.gmi +++ b/gemfeed/2026-06-01-gt-calculator.gmi @@ -2,7 +2,7 @@ > Published at 2026-05-31T14:24:10+03:00 -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 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. The answer is: well enough for small projects like this. @@ -13,7 +13,7 @@ If you want the full feature guide, the README links to a detailed doc for every => https://codeberg.org/snonux/gt gt on Codeberg => ./gt-calculator/logo.svg gt logo -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. +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. => https://www.hyperstack.cloud/ diff --git a/gemfeed/2026-06-01-gt-calculator.gmi.tpl b/gemfeed/2026-06-01-gt-calculator.gmi.tpl index d0824a9c..6bf93e12 100644 --- a/gemfeed/2026-06-01-gt-calculator.gmi.tpl +++ b/gemfeed/2026-06-01-gt-calculator.gmi.tpl @@ -2,7 +2,7 @@ > Published at 2026-05-31T14:24:10+03:00 -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 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. The answer is: well enough for small projects like this. @@ -13,7 +13,7 @@ If you want the full feature guide, the README links to a detailed doc for every => https://codeberg.org/snonux/gt gt on Codeberg => ./gt-calculator/logo.svg gt logo -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. +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. => https://www.hyperstack.cloud/ diff --git a/gemfeed/atom.xml b/gemfeed/atom.xml index f0ba0336..e16f13bd 100644 --- a/gemfeed/atom.xml +++ b/gemfeed/atom.xml @@ -1,6 +1,6 @@ - 2026-05-31T18:38:04+03:00 + 2026-05-31T22:32:28+03:00 foo.zone feed To be in the .zone! @@ -15,14 +15,14 @@ Paul Buetow aka snonux paul@dev.buetow.org - 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 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.

gt calculator - a calculator built with local LLMs



Published at 2026-05-31T14:24:10+03:00

-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 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.

The answer is: well enough for small projects like this.

@@ -33,7 +33,7 @@ gt on Codeberg
gt logo

-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.
+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.

https://www.hyperstack.cloud/

diff --git a/index.gmi b/index.gmi index e36f3f0a..3c848191 100644 --- a/index.gmi +++ b/index.gmi @@ -1,6 +1,6 @@ # Hello! -> This site was generated at 2026-05-31T18:40:26+03:00 by `Gemtexter` +> This site was generated at 2026-05-31T22:32:28+03:00 by `Gemtexter` Welcome to the foo.zone! diff --git a/uptime-stats.gmi b/uptime-stats.gmi index 3391caf2..82761b58 100644 --- a/uptime-stats.gmi +++ b/uptime-stats.gmi @@ -1,6 +1,6 @@ # My machine uptime stats -> This site was last updated at 2026-05-31T18:40:25+03:00 +> This site was last updated at 2026-05-31T22:32:27+03:00 The following stats were collected via `uptimed` on all of my personal computers over many years and the output was generated by `goprecords`, the global uptime records stats analyser of mine. @@ -13,7 +13,7 @@ Also check out my blog post: => ./gemfeed/2023-05-01-unveiling-guprecords:-uptime-records-with-raku.gmi Unveiling `guprecords.raku`: Uptime records with Raku (and also there is a version in Go now) -> Uptime stats were last updated Sun 31 May 18:40:26 EEST 2026 +> Uptime stats were last updated Sun 31 May 22:32:28 EEST 2026 ## Top 20 Uptime's by Host @@ -128,13 +128,13 @@ Boots is the total number of host boots over the entire lifespan. | 10. | makemake | 81 | Linux 6.9.9-200.fc40.x86_64 | | 11. | uranus | 59 | NetBSD 10.1 | | 12. | pluto | 51 | Linux 3.2.0-4-amd64 | -| 13. | *fishfinger | 50 | OpenBSD 7.8 | -| 14. | mega15289 | 50 | Darwin 23.4.0 | +| 13. | mega15289 | 50 | Darwin 23.4.0 | +| 14. | *blowfish | 50 | OpenBSD 7.8 | | 15. | *mega-m3-pro | 50 | Darwin 25.3.0 | -| 16. | *blowfish | 50 | OpenBSD 7.8 | +| 16. | *fishfinger | 50 | OpenBSD 7.8 | | 17. | t450 | 46 | FreeBSD 14.2-RELEASE | -| 18. | mega8477 | 40 | Darwin 13.4.0 | -| 19. | phobos | 40 | Linux 3.4.0-CM-g1dd7cdf | +| 18. | phobos | 40 | Linux 3.4.0-CM-g1dd7cdf | +| 19. | mega8477 | 40 | Darwin 13.4.0 | | 20. | *pi0 | 34 | Linux 6.1.31-v8.1.el9.altarch | +-----+----------------+-------+-------------------------------+ ``` @@ -197,7 +197,7 @@ Boots is the total number of host boots over the entire lifespan. | 17. | Darwin 15... | 15 | | 18. | Darwin 22... | 12 | | 19. | Darwin 18... | 11 | -| 20. | OpenBSD 4... | 10 | +| 20. | FreeBSD 7... | 10 | +-----+----------------+-------+ ``` @@ -288,7 +288,7 @@ Uptime is the total uptime of a host over the entire lifespan. | Pos | KernelName | Uptime | +-----+------------+------------------------------+ | 1. | *Linux | 28 years, 10 months, 10 days | -| 2. | *FreeBSD | 13 years, 5 months, 9 days | +| 2. | *FreeBSD | 13 years, 5 months, 10 days | | 3. | *OpenBSD | 9 years, 6 months, 6 days | | 4. | *Darwin | 5 years, 5 months, 16 days | | 5. | NetBSD | 0 years, 1 months, 1 days | -- cgit v1.2.3