vnglst
Waiting for Anthropic Support
GenAI in the Wild
Code Doesn't Speak for Itself
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @07:59AM (#48516410)
Direct API access I’m afraid, it was not my intention to spent it all in one go on this. But after 12€ I didn’t want to stop anymore
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @07:56AM (#48516385)
Would love a PR with this!
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @03:15AM (#48514352)
Not sure if it would've gone to the front page of Hackernews with that title! I was also trying to make a little fun about the drama around Mythos/Fable: Even though Fable did this really well, to me it does not appear to be fundamentally different from other top models.
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @03:11AM (#48514327)
This was my second attempt, I'm still learning! Besides, the wolf was freaking me out.
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @02:46AM (#48514146)
I also realized this, a quick Google search would’ve told me that this game has been made several times before, also way before I ever had this idea. Apparently it’s a pretty obvious game idea.
Ah well, it’s still fun and it does appear to measure how good AI is in creating these kind of games.
Re:Shepherd's Dog: A Game by the Most Dangerous AI Model
on Saturday June 13, 2026 @02:24AM (#48514000)
Thanks for that, I messed up copying the links into the article!
Shepherd's Dog: A Game by the Most Dangerous AI Model
Re:Notes from the Mistral AI Now Summit in Paris
on Friday May 29, 2026 @01:35PM (#48326468)
Maybe, but using state-of-the-art large language models to solve customer support queries with agentic can quickly use a lot of tokens. What I understood from the talk is that they used agents with limited responsibility and (assumption from me) smaller models, to the make sure the answers were quick, reliable and not too costly.
Notes from the Mistral AI Now Summit in Paris
Growing a better world together with AI
Software for One
Computer Says No
Re:Show HN: Stacked Game of Life
on Saturday February 28, 2026 @05:00PM (#47200746)
Yes, that's right, it's https://github.com/vnglst/stacked-game-of-life
The link was broken indeed. Should be fixed now. Glad you like it!
Show HN: Stacked Game of Life
Re:Gemini 3.1 Pro Preview
on Thursday February 19, 2026 @03:49PM (#47079104)
I asked Gemini 3.1 Pro Preview to generate the modern artworks as SVG for my Pelican Art Gallery. I particularly like the rendition of the Sunflowers: https://pelican.koenvangilst.nl/gallery/category/modern
Re:Gemini 3.1 Pro Preview
on Thursday February 19, 2026 @02:51PM (#47078265)
I asked Gemini 3.1 Pro to generate some of the modern artworks in my "Pelican Art Gallery". I particularly like the rendition of the Sunflowers: https://pelican.koenvangilst.nl/gallery/category/modern
Show HN: Researching politics with Claude Code and 55 years of UN speeches
https://un.koenvangilst.nl/research
I've been experimenting with using Claude Code for researching political topics using the archive of UN General Assembly speeches provided by the University of Birmingham (https://www.ungdc.bham.ac.uk/). Here are some initial results.
Coding Is Dead
Building Tetris Time with Claude Code
Re:Show HN: Tetris Time
on Tuesday December 30, 2025 @10:46AM (#46434457)
Oh that's weird. Are you sure it was the basic link and not the one with count down mode?
The one I shared in the parent is for the New Year's countdown: https://tetris-time.koenvangilst.nl/?mode=countdown&to=2026-...
The basic link should show the current time, even at high speeds: https://tetris-time.koenvangilst.nl/?speed=10
Oh wait, I just tested it on a higher speed (20) and I see what you mean. It's drawing over the existing Tetrominoes! I'm going to max the speed at 10.
Re:Show HN: Tetris Time
on Tuesday December 30, 2025 @06:53AM (#46432394)
The year is coming to an end, and looking back I had a lot of fun building quirky, fun, and insightful visualizations. Agentic coding agents have been hugely empowering for me. In 2024 it was “just” autocomplete on steroids. Now it feels more like conducting, directing the agents to go where I please. Often they’re impressive; sometimes they fail at the simplest tasks.
What worked particularly well here was a test-driven (TDD) approach. I asked Claude Code to focus only on the algorithm for selecting the next Tetromino (the Tetris blocks), starting with tests. After that, things went smoothly, though it still took many follow-up prompts (around 100) to reach the final result.
Show HN: Tetris Time
https://tetris-time.koenvangilst.nl/?mode=countdown&to=2026-01-01T00:00:00.000Z&speed=3
It's almost New Year's and here's an original way to show the countdown using Tetris. I'm sure something similar has been done before, but I had a lot of fun building this (TDD style) using Claude Code.After New Year's it can also function as a regular clock:https://tetris-time.koenvangilst.nl/For the impatient, it's possible to increase the speed using url...
A Brief History of Large Language Models
Re:Show HN: Land use visualization for European countries
on Saturday October 18, 2025 @01:43PM (#45629092)
Thanks I love the suggestions! Great ideas for the next iteration.
Show HN: Land use visualization for European countries
https://onsland.koenvangilst.nl/
We have another election coming up at the end of this month here in the Netherlands, and how we use our limited land is a hotly debated topic.Last year also I shared this animated hexagonal map of Dutch land use. I've now expanded this to include several more European countries, so you can see what makes Dutch land use so special - or not.If you want to help add more countries, I'd appreciate...
Show HN: Which LLM draws the best Starry Night? (using SVG)
https://pelican.koenvangilst.nl/
Here's an experiment I did around the following question: Can AI models like ChatGPT recreate Van Gogh's Starry Night using SVG? I created a website to test this across multiple large language models, from 2022 to 2025. The results show how much models have improved, but also that their interpretations show a kind of beauty. It's almost like... art?I tested this across multiple paintings: The...