Nimo 🏳️‍🌈
@nimobeeren.com
1.1K followers 250 following 450 posts
Building cool things with or without AI — 🧪🎹💻🌸📷🔧📔 🌐 nimobeeren.com 📍 Eindhoven
Posts Media Videos Starter Packs
Reposted by Nimo 🏳️‍🌈
brennan.computer
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'
dorialexander.bsky.social
Have to admit there are pro-ai takes on the other site that are as cringe as anti-ai folks on here.
nimobeeren.com
This is exactly how I feel. Coding agents just got good enough for me to enjoy using them.
danabra.mov
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)
danabra.mov
dan @danabra.mov · 19d
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
nimobeeren.com
Do you allow the model to see its results and iterate in these tests? Would be really cool to see the difference!
nimobeeren.com
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...
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
nimobeeren.com
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?
nimobeeren.com
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!
nimobeeren.com
I feel like in this case structured output + a retry mechanism would be a good fit so you don’t have to deal with the final unstructured text response
nimobeeren.com
Yes, and tools are very expressive: you can use enums, recursive objects, non-JSON strings and even custom grammars.

Depends on model provider, but OpenAI has all of the above: platform.openai.com/docs/guides/...
OpenAI Platform
Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.
platform.openai.com
nimobeeren.com
I like this, describing the objective is only half the problem. The other half is how to validate the solution.
nimobeeren.com
Stacked
react.dev
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
nimobeeren.com
I think you need a lot of almond paste to have the best flavor and texture. Totally worth the calories though
nimobeeren.com
I love the framing of your app as your neighborhood. There’s a sense of shared responsibility that fosters joyful experiences.
nimobeeren.com
Besides 2d being confusing it’s also way too tempting to context switch. I wouldn’t mind if my email was in another room.
nimobeeren.com
*laughs in Stremio*
nimobeeren.com
Trying to figure out how to map the models named in the system card to the API models.

This seems right, but where is gpt-5-main-mini? Is it just gpt-5-mini with reasoning effort set to minimal?
nimobeeren.com
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-...
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
nimobeeren.com
I love the Tetris/Sudoku analogy! Both are about fitting in the pieces but only Sudoku has a predetermined end goal.
nimobeeren.com
What are some things you have noted down from previous conversations on the platform, but which you doubt are true looking at them now?
nimobeeren.com
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.
nimobeeren.com
Does it help to tell the model not to hallucinate?
nimobeeren.com
Leuk! Volgens mij ligt dit boek ook wel ergens bij m’n vader in huis, misschien moest ik hem maar eens zoeken