Nimo 🏳️🌈
@nimobeeren.com
Building cool things with or without AI — 🧪🎹💻🌸📷🔧📔
🌐 nimobeeren.com
📍 Eindhoven
🌐 nimobeeren.com
📍 Eindhoven
Some really interesting patterns for making coding agents do long and complex tasks!
They use the Claude Agent SDK, but I wonder how a coding agent like Claude Code could work across multiple context windows? Maybe it could spawn a sub-agent once the window is almost full?
They use the Claude Agent SDK, but I wonder how a coding agent like Claude Code could work across multiple context windows? Maybe it could spawn a sub-agent once the window is almost full?
Claude Code is starting to write out functional requirements as part of the planning process
www.anthropic.com/engineering/...
www.anthropic.com/engineering/...
November 27, 2025 at 9:10 PM
Some really interesting patterns for making coding agents do long and complex tasks!
They use the Claude Agent SDK, but I wonder how a coding agent like Claude Code could work across multiple context windows? Maybe it could spawn a sub-agent once the window is almost full?
They use the Claude Agent SDK, but I wonder how a coding agent like Claude Code could work across multiple context windows? Maybe it could spawn a sub-agent once the window is almost full?
I did some data analysis for the first time in a while today, and boy do LLMs make that a lot easier.
I don’t need to look at the code at all, just need to think about what I want to know and maybe give a hint on how to find out. Feels very productive!
I don’t need to look at the code at all, just need to think about what I want to know and maybe give a hint on how to find out. Feels very productive!
November 27, 2025 at 6:18 PM
I did some data analysis for the first time in a while today, and boy do LLMs make that a lot easier.
I don’t need to look at the code at all, just need to think about what I want to know and maybe give a hint on how to find out. Feels very productive!
I don’t need to look at the code at all, just need to think about what I want to know and maybe give a hint on how to find out. Feels very productive!
Absolutely true. This is why greenfield projects built with AI from the start are so much more fun.
Software 2.0 relies on validation
If your code base doesn’t have verification & controls that are as good or better than your senior dev, you’ll get slop
If your code base doesn’t have verification & controls that are as good or better than your senior dev, you’ll get slop
November 21, 2025 at 7:24 PM
Absolutely true. This is why greenfield projects built with AI from the start are so much more fun.
Reposted by Nimo 🏳️🌈
You know how the existence of cars and power tools makes it necessary to have “exercise” and “manual crafts” as a deliberately chosen part of a balanced life?
We’re probably going to need something like that cognitively, for adults.
We’re probably going to need something like that cognitively, for adults.
November 6, 2025 at 4:18 AM
You know how the existence of cars and power tools makes it necessary to have “exercise” and “manual crafts” as a deliberately chosen part of a balanced life?
We’re probably going to need something like that cognitively, for adults.
We’re probably going to need something like that cognitively, for adults.
The DeepSeek OCR paper shows something interesting: encoding text as an image is more computationally efficient for LLMs than raw text (ie UTF).
I’m tempted to make an analogy with humans “glancing” at text and still understanding it, but I’m not sure it holds up.
I’m tempted to make an analogy with humans “glancing” at text and still understanding it, but I’m not sure it holds up.
October 21, 2025 at 4:12 PM
The DeepSeek OCR paper shows something interesting: encoding text as an image is more computationally efficient for LLMs than raw text (ie UTF).
I’m tempted to make an analogy with humans “glancing” at text and still understanding it, but I’m not sure it holds up.
I’m tempted to make an analogy with humans “glancing” at text and still understanding it, but I’m not sure it holds up.
How do you all go about curating your feeds? I realized I haven’t followed anyone new in a while
October 11, 2025 at 8:25 AM
How do you all go about curating your feeds? I realized I haven’t followed anyone new in a while
Reposted by Nimo 🏳️🌈
not to reveal myself as cringe (again), but I do have that thought when confronted with electric space heaters that generate heat and do nothing else
'this device could have been a GPU making heat _and_ doing math'
'this device could have been a GPU making heat _and_ doing math'
Have to admit there are pro-ai takes on the other site that are as cringe as anti-ai folks on here.
October 7, 2025 at 6:12 PM
not to reveal myself as cringe (again), but I do have that thought when confronted with electric space heaters that generate heat and do nothing else
'this device could have been a GPU making heat _and_ doing math'
'this device could have been a GPU making heat _and_ doing math'
This is exactly how I feel. Coding agents just got good enough for me to enjoy using them.
i’m less concerned about this now. i experienced deep flow vibecoding yesterday. in some ways it was actually deeper than manual coding because (when it worked well) i was able to explore ideas and directions that would normally take me days (due to lack of domain knowledge, boilerplate etc)
the thing i'm worried about is whether AI will decimate the "flow states" of knowledge work. i realize this is very selfish. i enjoy being in a flow state. i don't want to constantly be babysitting an unlearning intern who repeatedly violates instructions. even if they eventually produce good work
October 7, 2025 at 11:22 AM
This is exactly how I feel. Coding agents just got good enough for me to enjoy using them.
Been working on a little algorithm to solve NYT Strands puzzles. I totally underestimated the challenge but it’s been so much fun to iterate on!
I may need to bring out LLMs/embeddings to bridge the final gaps.
github.com/nimobeeren/s...
I may need to bring out LLMs/embeddings to bridge the final gaps.
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
October 6, 2025 at 8:10 PM
Been working on a little algorithm to solve NYT Strands puzzles. I totally underestimated the challenge but it’s been so much fun to iterate on!
I may need to bring out LLMs/embeddings to bridge the final gaps.
github.com/nimobeeren/s...
I may need to bring out LLMs/embeddings to bridge the final gaps.
github.com/nimobeeren/s...
I’m really ready to churn on Cursor. Once I figure out how to set up Claude Code through my company’s LLM platform that’ll probably be my main coding agent.
The only thing keeping me there is the autocomplete. Maybe it’s time to give copilot another try?
The only thing keeping me there is the autocomplete. Maybe it’s time to give copilot another try?
October 6, 2025 at 8:08 PM
I’m really ready to churn on Cursor. Once I figure out how to set up Claude Code through my company’s LLM platform that’ll probably be my main coding agent.
The only thing keeping me there is the autocomplete. Maybe it’s time to give copilot another try?
The only thing keeping me there is the autocomplete. Maybe it’s time to give copilot another try?
It really feels like we’ve passed an inflection point on coding agents. They now feel reliable enough but also fast enough to not make me lose focus every time I use them.
Been working on a side project together with Claude and it’s been so much fun!
Been working on a side project together with Claude and it’s been so much fun!
October 6, 2025 at 8:06 PM
It really feels like we’ve passed an inflection point on coding agents. They now feel reliable enough but also fast enough to not make me lose focus every time I use them.
Been working on a side project together with Claude and it’s been so much fun!
Been working on a side project together with Claude and it’s been so much fun!
Stacked
We're excited to announce React Conf's first AI-related talk: a discussion panel with @vjeux.bsky.social @kentcdodds.com @swyx.io @t3.gg moderated by @leerob.com
September 25, 2025 at 7:39 PM
Stacked
Awesome to see my dressme project featured in the AI Tinkerers newsletter!
It's a virtual wardrobe that lets you try on any clothes on a selfie ✨
Check out the post here: post-training.aitinkerers.org/p/practical-...
It's a virtual wardrobe that lets you try on any clothes on a selfie ✨
Check out the post here: post-training.aitinkerers.org/p/practical-...
🛠 Practical AI Builds: Scheduling Agents, MoE Assembly, Virtual Try-On, and More – August 11 [AI Tinkerers - Post-Training]
🛠 Practical AI Builds: Scheduling Agents, MoE Assembly, Virtual Try-On, and More – August 11 August 11, 2025 Joe Heitzeberg • Founder at AI Tinkerers • ⏱️ 1 min read Creating space for leading builder...
post-training.aitinkerers.org
August 11, 2025 at 5:01 PM
Awesome to see my dressme project featured in the AI Tinkerers newsletter!
It's a virtual wardrobe that lets you try on any clothes on a selfie ✨
Check out the post here: post-training.aitinkerers.org/p/practical-...
It's a virtual wardrobe that lets you try on any clothes on a selfie ✨
Check out the post here: post-training.aitinkerers.org/p/practical-...
I'm a little confused by OpenAI saying "GPT-5 is a unified system with [...] a real-time router".
While ChatGPT does provide a unified interface, the API still has separate models. Wouldn't it be more fair to say that ChatGPT is the unified system, rather than the model?
openai.com/index/gpt-5-...
While ChatGPT does provide a unified interface, the API still has separate models. Wouldn't it be more fair to say that ChatGPT is the unified system, rather than the model?
openai.com/index/gpt-5-...
GPT-5 System Card
GPT-5 offers high reasoning performance, new controls for devs, and best-in-class results on real coding tasks.
openai.com
August 8, 2025 at 9:31 AM
I'm a little confused by OpenAI saying "GPT-5 is a unified system with [...] a real-time router".
While ChatGPT does provide a unified interface, the API still has separate models. Wouldn't it be more fair to say that ChatGPT is the unified system, rather than the model?
openai.com/index/gpt-5-...
While ChatGPT does provide a unified interface, the API still has separate models. Wouldn't it be more fair to say that ChatGPT is the unified system, rather than the model?
openai.com/index/gpt-5-...
After reading it seems obvious that selling unlimited intelligence for a fixed price is unsustainable. But there are so many useful things to build even with last year’s intelligence. Don’t sell intelligence, sell products.
August 4, 2025 at 5:33 PM
After reading it seems obvious that selling unlimited intelligence for a fixed price is unsustainable. But there are so many useful things to build even with last year’s intelligence. Don’t sell intelligence, sell products.
Recording of my talk at AI Tinkerers is up!
Check out this demo of how I made my virtual wardrobe app with Gemini Flash and IDM-VTON.
youtu.be/dZK3X6fogv8
Check out this demo of how I made my virtual wardrobe app with Gemini Flash and IDM-VTON.
youtu.be/dZK3X6fogv8
Nimo Beeren: Outfit-maxxing with virtual try-on + Gemini Flash @ AI Tinkerers Amsterdam
YouTube video by AI Tinkerers Amsterdam
youtu.be
August 1, 2025 at 2:53 PM
Recording of my talk at AI Tinkerers is up!
Check out this demo of how I made my virtual wardrobe app with Gemini Flash and IDM-VTON.
youtu.be/dZK3X6fogv8
Check out this demo of how I made my virtual wardrobe app with Gemini Flash and IDM-VTON.
youtu.be/dZK3X6fogv8
Finally gave my website some love and added my latest projects ✨
Not pictured: hours of struggling with package upgrades because JavaScript can't stand still 😮💨
www.nimobeeren.com
Not pictured: hours of struggling with package upgrades because JavaScript can't stand still 😮💨
www.nimobeeren.com
Nimo Beeren | AI Engineer 🔧 Software Architect 📐 Creative Technologist 🌸
I'm an AI engineer from the Netherlands. I build products using data, code and AI to help people do wonderful things.
www.nimobeeren.com
August 1, 2025 at 2:16 PM
Finally gave my website some love and added my latest projects ✨
Not pictured: hours of struggling with package upgrades because JavaScript can't stand still 😮💨
www.nimobeeren.com
Not pictured: hours of struggling with package upgrades because JavaScript can't stand still 😮💨
www.nimobeeren.com
I'll show how I built this at AI Tinkerers Amsterdam this Thursday ✨
Come hang out! amsterdam.aitinkerers.org/p/building-a...
Come hang out! amsterdam.aitinkerers.org/p/building-a...
July 20, 2025 at 6:42 PM
I'll show how I built this at AI Tinkerers Amsterdam this Thursday ✨
Come hang out! amsterdam.aitinkerers.org/p/building-a...
Come hang out! amsterdam.aitinkerers.org/p/building-a...
@void.comind.network do you have a concept of trust? Do you value certain people’s opinions more than others?
July 19, 2025 at 12:36 PM
@void.comind.network do you have a concept of trust? Do you value certain people’s opinions more than others?
Has there been any more good discourse on multi-agent systems since the Anthropic/Cognition blog posts?
July 17, 2025 at 12:28 PM
Has there been any more good discourse on multi-agent systems since the Anthropic/Cognition blog posts?
This concept of self-containment explains why LLM responses often feel unnatural to me, especially in a voice context. They try to restate my input rather than just giving an answer like a human would. Surprisingly hard to prompt around!
From "There are Only 6 RAG Evals" jxnl.co/writing/2025...
From "There are Only 6 RAG Evals" jxnl.co/writing/2025...
July 17, 2025 at 9:49 AM
This concept of self-containment explains why LLM responses often feel unnatural to me, especially in a voice context. They try to restate my input rather than just giving an answer like a human would. Surprisingly hard to prompt around!
From "There are Only 6 RAG Evals" jxnl.co/writing/2025...
From "There are Only 6 RAG Evals" jxnl.co/writing/2025...
I made a harder version of my CTF challenge which relies on an RCE exploit by unsafe pickle deserialization. The solution I had in mind was to read a file on the server's disk and send it to a webhook I set up.
I let my simple o4-mini agent have a go, not expecting much. But I was surprised! 👀
1/n
I let my simple o4-mini agent have a go, not expecting much. But I was surprised! 👀
1/n
July 7, 2025 at 7:03 PM
I made a harder version of my CTF challenge which relies on an RCE exploit by unsafe pickle deserialization. The solution I had in mind was to read a file on the server's disk and send it to a webhook I set up.
I let my simple o4-mini agent have a go, not expecting much. But I was surprised! 👀
1/n
I let my simple o4-mini agent have a go, not expecting much. But I was surprised! 👀
1/n
Added a new CTF challenge to learn about "alg": "none" exploits for JWTs.
It was actually hard to find a JWT library that's vulnerable to this, even going back to old versions!
Ended up writing some "extra unsafe" code to break it
github.com/nimobeeren/c...
It was actually hard to find a JWT library that's vulnerable to this, even going back to old versions!
Ended up writing some "extra unsafe" code to break it
github.com/nimobeeren/c...
github.com
July 4, 2025 at 4:57 PM
Added a new CTF challenge to learn about "alg": "none" exploits for JWTs.
It was actually hard to find a JWT library that's vulnerable to this, even going back to old versions!
Ended up writing some "extra unsafe" code to break it
github.com/nimobeeren/c...
It was actually hard to find a JWT library that's vulnerable to this, even going back to old versions!
Ended up writing some "extra unsafe" code to break it
github.com/nimobeeren/c...
I’m wondering what it would be like if I stopped coding for work. In the spirit of “if you love something you should let it go”, it’ll come back to me eventually, right?
Also exciting to think about learning something completely new. I could choose anything!
Also exciting to think about learning something completely new. I could choose anything!
July 2, 2025 at 8:35 PM
I’m wondering what it would be like if I stopped coding for work. In the spirit of “if you love something you should let it go”, it’ll come back to me eventually, right?
Also exciting to think about learning something completely new. I could choose anything!
Also exciting to think about learning something completely new. I could choose anything!