Nimo 🏳️🌈
@nimobeeren.com
Building cool things with or without AI (mostly with) — 🧪🎹💻🌸📷🔧📔
🌐 nimobeeren.com
📍 Eindhoven
🌐 nimobeeren.com
📍 Eindhoven
Pinned
Nimo 🏳️🌈
@nimobeeren.com
· 1d
GitHub - nimobeeren/strands-solver: A solver for Strands, the New York Times puzzle game.
A solver for Strands, the New York Times puzzle game. - nimobeeren/strands-solver
github.com
Finally published strands-solver 1.0.0 🚀
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
Claude + GitHub CLI is so useful for finding out the actual status of a long issue thread.
Just had it navigate through 3 connected issues to find out I can remove a workaround in my code after upgrading some dependencies 🎯
Just had it navigate through 3 connected issues to find out I can remove a workaround in my code after upgrading some dependencies 🎯
January 12, 2026 at 8:07 PM
Claude + GitHub CLI is so useful for finding out the actual status of a long issue thread.
Just had it navigate through 3 connected issues to find out I can remove a workaround in my code after upgrading some dependencies 🎯
Just had it navigate through 3 connected issues to find out I can remove a workaround in my code after upgrading some dependencies 🎯
Building the NYT Strands solver has been such a fun project since I started nearly 4 months ago. It was addicting to see the progress with each new idea.
Experiencing the advancement of LLMs/coding agents was awesome too. I simply could not have done this without those tools.
Here's how it works 🧵
Experiencing the advancement of LLMs/coding agents was awesome too. I simply could not have done this without those tools.
Here's how it works 🧵
January 11, 2026 at 8:01 PM
Building the NYT Strands solver has been such a fun project since I started nearly 4 months ago. It was addicting to see the progress with each new idea.
Experiencing the advancement of LLMs/coding agents was awesome too. I simply could not have done this without those tools.
Here's how it works 🧵
Experiencing the advancement of LLMs/coding agents was awesome too. I simply could not have done this without those tools.
Here's how it works 🧵
Calling a side project “done” is a hard but liberating act
(I reserve the right to call it “undone” at any future moment)
(I reserve the right to call it “undone” at any future moment)
January 11, 2026 at 6:15 PM
Calling a side project “done” is a hard but liberating act
(I reserve the right to call it “undone” at any future moment)
(I reserve the right to call it “undone” at any future moment)
Finally published strands-solver 1.0.0 🚀
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
GitHub - nimobeeren/strands-solver: A solver for Strands, the New York Times puzzle game.
A solver for Strands, the New York Times puzzle game. - nimobeeren/strands-solver
github.com
January 11, 2026 at 5:39 PM
Finally published strands-solver 1.0.0 🚀
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
It solves NY Times Strands puzzles using a backtracking algorithm and word embeddings.
Try it with `uvx strands-solver solve today` (free tier GEMINI_API_KEY optional)
github.com/nimobeeren/s...
I personally haven't run into the issue of Claude bailing out before finishing its work (at least not recently), but the principles and great examples make this valuable to anyone using coding agents.
I'm glad someone put this together and did it so well 🧡
I'm glad someone put this together and did it so well 🧡
Ralph Wiggum - Iterative AI Development Loop
Official Anthropic plugin for iterative AI coding. Ship 6 repos overnight. $50k contract for $297 in API costs.
awesomeclaude.ai
January 11, 2026 at 5:20 PM
I personally haven't run into the issue of Claude bailing out before finishing its work (at least not recently), but the principles and great examples make this valuable to anyone using coding agents.
I'm glad someone put this together and did it so well 🧡
I'm glad someone put this together and did it so well 🧡
We love predictable optimizations. Easy puzzles got a bit slower, hard puzzles got a lot faster 🚀
This was the result of integrating strand crossing checks into the search, rather than post-filtering them.
This was the result of integrating strand crossing checks into the search, rather than post-filtering them.
January 11, 2026 at 5:06 PM
We love predictable optimizations. Easy puzzles got a bit slower, hard puzzles got a lot faster 🚀
This was the result of integrating strand crossing checks into the search, rather than post-filtering them.
This was the result of integrating strand crossing checks into the search, rather than post-filtering them.
Genuine question for Claude Code users: what makes you prefer it over more visual/IDE alternatives like Cursor or GH Copilot?
Is it overall quality of results, ergonomics, specific features, pricing?
Is it overall quality of results, ergonomics, specific features, pricing?
January 11, 2026 at 12:53 PM
Genuine question for Claude Code users: what makes you prefer it over more visual/IDE alternatives like Cursor or GH Copilot?
Is it overall quality of results, ergonomics, specific features, pricing?
Is it overall quality of results, ergonomics, specific features, pricing?
I was experimenting with some battle-tested SAT solvers but found them slower than my Claude-rolled Python (!) implementation.
Surely this is a skill issue? Unless my optimizations are too specific for these solvers to find.
I figured offloading to optimized C++ code would be faster, but no!
Surely this is a skill issue? Unless my optimizations are too specific for these solvers to find.
I figured offloading to optimized C++ code would be faster, but no!
January 11, 2026 at 9:02 AM
I was experimenting with some battle-tested SAT solvers but found them slower than my Claude-rolled Python (!) implementation.
Surely this is a skill issue? Unless my optimizations are too specific for these solvers to find.
I figured offloading to optimized C++ code would be faster, but no!
Surely this is a skill issue? Unless my optimizations are too specific for these solvers to find.
I figured offloading to optimized C++ code would be faster, but no!
This might become a problem in a world of hyper-personalized software.
If you’re the only one using an app, you won’t know it’s broken until it happens to *you*.
There is safety in using software that millions of others use.
If you’re the only one using an app, you won’t know it’s broken until it happens to *you*.
There is safety in using software that millions of others use.
How am I supposed to monitor all these stupid little apps I'm building and kind of depend on?
January 11, 2026 at 8:45 AM
This might become a problem in a world of hyper-personalized software.
If you’re the only one using an app, you won’t know it’s broken until it happens to *you*.
There is safety in using software that millions of others use.
If you’re the only one using an app, you won’t know it’s broken until it happens to *you*.
There is safety in using software that millions of others use.
I was messing around with Opus to generate an evals app for voice AI apps. I asked it to generate some mock audio files and it kinda bops 💿
January 8, 2026 at 7:55 PM
I was messing around with Opus to generate an evals app for voice AI apps. I asked it to generate some mock audio files and it kinda bops 💿
I want my coding agent to run in the cloud for security/sandboxing but also want to interact with the code and run it manually. Maybe it’s time to do the full cloud IDE thing?
January 8, 2026 at 6:49 PM
I want my coding agent to run in the cloud for security/sandboxing but also want to interact with the code and run it manually. Maybe it’s time to do the full cloud IDE thing?
Build a stateful agent that doesn’t talk like a robot challenge
January 7, 2026 at 1:27 PM
Build a stateful agent that doesn’t talk like a robot challenge
I’ve been running my agents with auto-accept on and it’s such a huge productivity jump, but I’m still a bit scared to recommend it to others.
I should really look into better sandboxing options, but I’m having too much fun to stop!
containeruse.com has been on my list for a while
I should really look into better sandboxing options, but I’m having too much fun to stop!
containeruse.com has been on my list for a while
Introduction - Container Use
Sandboxed dev environments for coding agents.
containeruse.com
January 6, 2026 at 5:12 PM
I’ve been running my agents with auto-accept on and it’s such a huge productivity jump, but I’m still a bit scared to recommend it to others.
I should really look into better sandboxing options, but I’m having too much fun to stop!
containeruse.com has been on my list for a while
I should really look into better sandboxing options, but I’m having too much fun to stop!
containeruse.com has been on my list for a while
The roughness of Cursor’s web interface feels more like an exciting opportunity than anything. How is GH Copilot doing with this?
January 4, 2026 at 6:50 PM
The roughness of Cursor’s web interface feels more like an exciting opportunity than anything. How is GH Copilot doing with this?
Claude Opus can do pretty much any well-defined task. The job is now defining the task.
a few years ago everyone thought the new job would be prompt engineer, that only a special few would know the secret whispers to get good results
and now I just say 'do the thing' and it goes off and nails it perfectly
and now I just say 'do the thing' and it goes off and nails it perfectly
January 4, 2026 at 6:30 PM
Claude Opus can do pretty much any well-defined task. The job is now defining the task.
Okay, cloud agents on your phone are huge for engineers who commute.
Cursor on web is rough, but we’re early.
Cursor on web is rough, but we’re early.
January 4, 2026 at 12:12 PM
Okay, cloud agents on your phone are huge for engineers who commute.
Cursor on web is rough, but we’re early.
Cursor on web is rough, but we’re early.
Cloud agents are really cool, also from a security perspective. There’s no better sandbox than running on a completely different machine.
January 4, 2026 at 11:21 AM
Cloud agents are really cool, also from a security perspective. There’s no better sandbox than running on a completely different machine.
So who is actually building agent skills for coding?
I’ve been fine with a basic AGENTS.md and regular code documentation like a README.
Looking to broaden my view of what’s possible!
I’ve been fine with a basic AGENTS.md and regular code documentation like a README.
Looking to broaden my view of what’s possible!
AGENTS.md
AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.
AGENTS.md
January 4, 2026 at 9:57 AM
So who is actually building agent skills for coding?
I’ve been fine with a basic AGENTS.md and regular code documentation like a README.
Looking to broaden my view of what’s possible!
I’ve been fine with a basic AGENTS.md and regular code documentation like a README.
Looking to broaden my view of what’s possible!
Running things with low but non-zero cost in a loop is still scary. I still feel that resistance when building things with LLMs that I pay for out of my own pocket.
January 3, 2026 at 9:46 PM
Running things with low but non-zero cost in a loop is still scary. I still feel that resistance when building things with LLMs that I pay for out of my own pocket.
In the category of things I wouldn't have done without AI help: I made a benchmark script for my Strands solver!
Now I know how well it does at solving ~100 real puzzles: github.com/nimobeeren/s...
Pass rate of ~19% means there is work to be done!
Now I know how well it does at solving ~100 real puzzles: github.com/nimobeeren/s...
Pass rate of ~19% means there is work to be done!
January 3, 2026 at 9:43 PM
In the category of things I wouldn't have done without AI help: I made a benchmark script for my Strands solver!
Now I know how well it does at solving ~100 real puzzles: github.com/nimobeeren/s...
Pass rate of ~19% means there is work to be done!
Now I know how well it does at solving ~100 real puzzles: github.com/nimobeeren/s...
Pass rate of ~19% means there is work to be done!
It seems inevitable that the UX Designer and Frontend Engineer roles will merge.
Designers can create much richer output by working on the live product. Engineers can offer more value by focusing on the subjective parts of the experience.
AI tools make both these changes possible.
Designers can create much richer output by working on the live product. Engineers can offer more value by focusing on the subjective parts of the experience.
AI tools make both these changes possible.
January 3, 2026 at 9:17 PM
It seems inevitable that the UX Designer and Frontend Engineer roles will merge.
Designers can create much richer output by working on the live product. Engineers can offer more value by focusing on the subjective parts of the experience.
AI tools make both these changes possible.
Designers can create much richer output by working on the live product. Engineers can offer more value by focusing on the subjective parts of the experience.
AI tools make both these changes possible.
Turns out it only costs about $0.10 to embed the entire dictionary with SOTA embedding models (gemini-embedding-001). Neat.
December 30, 2025 at 2:38 PM
Turns out it only costs about $0.10 to embed the entire dictionary with SOTA embedding models (gemini-embedding-001). Neat.
A good For You algo would benefit the entire bsky community because it helps people form valuable connections. Might be the next wave of organic growth after starter packs.
December 27, 2025 at 10:09 AM
A good For You algo would benefit the entire bsky community because it helps people form valuable connections. Might be the next wave of organic growth after starter packs.
By using LLMs to help me optimize my algorithm code, I actually feel like I can now do something I couldn’t do before.
All other use cases have been time saves for me. This actually extends my capabilities.
All other use cases have been time saves for me. This actually extends my capabilities.
December 22, 2025 at 10:05 PM
By using LLMs to help me optimize my algorithm code, I actually feel like I can now do something I couldn’t do before.
All other use cases have been time saves for me. This actually extends my capabilities.
All other use cases have been time saves for me. This actually extends my capabilities.