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.

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.

How do you all go about curating your feeds? I realized I haven’t followed anyone new in a while

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 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’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?

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!

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-...

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-...

RIP temperature?

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

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

I'll show how I built this at AI Tinkerers Amsterdam this Thursday ✨ 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?

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...

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

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...

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!

Wow, very thought provoking. Going from speaking to writing let us inspect, interrogate and remix our ideas much more. Language models are letting us do this with our entire culture, or at least a collection of ideas far greater than any single text can contain.

Vibe coded a couple CTF challenges that I can run locally. Gemini taught me about Traefik which lets me run multiple apps on subdomains of localhost, didn't know that was possible!

My talk at AI Tinkerers is up! It's a demo + discussion of my simple CTF agent. It does SQL injection and cookie spoofing attacks against a live web app in less than 100 lines. www.youtube.com/watch?v=sBLu...

Is there any way to get reasoning summaries from o4-mini if it decides to use a tool? I always just get "summary": [] but it works when it doesn't use a tool.

I guess I haven't posted about this! I made a very simple agent that solves Capture-The-Flag (CTF) cybersecurity challenges. It's less than 100 lines of code and it has only one tool: making HTTP requests. It was able to do several cookie spoofing and SQL injection attacks. Check out what it did!

the IT person when setting the session expiry to 30 mins and forcing 2fa on every login

I think I want to do more side projects, but worse

Signed up last-minute to give a demo at AI Tinkerers Amsterdam tonight! Excited to talk about reasoning models and CTF challenges ✨

You have more in common with the average Iranian citizen than you do with the people that run this country

Writing prompts for AI to write code that prompts AI to write prompts for AI to write code to write prompts that I can use to prompt an AI to review code that AI wrote. The future is now.

I confess I don't get font ligatures. I don't mean turning => into ⇒ (fine if you want that I guess). But things like pic attached. Why did the t get stuck to the i? Where did its extra length come from? Does it hurt when it stretches like that?

Sorry about the OpenAI outage guys, I had a demo this morning

More expressiveness in voice models is great, but it’s never going to feel natural unless turn-taking is improved. I find myself rambling when talking to a voice AI, because if I pause to think I’ll immediately be interrupted.

applying for jobs again

Sometimes the hard part isn't the 80 laborious steps you took in order to fix a problem, it's being able to tell which 2 of those steps mattered, which did nothing, and which ones only fixed new problems that the others introduced.

Playing with Gemini 2.5 Flash image segmentation feels like going back to the early days of LLMs. Prompt needs to contain magic words, response contains ```json tags, randomly getting 400s, infinite loading, choppy masks. But it's dirt cheap and pretty good when it works. Need to figure it out!

Made a little nicer UI for uploading clothing items 👖

Chatty G is being so cheeky today! It’s just saying things that are not true, then correcting itself. Kind of feels like a form of reasoning? Or at least self-talk.

Being surrounded by amazing AI tools has me feeling like I need to look for shortcuts all the time. That feeling prevents flow. I think it stems from the tools not being reliable enough yet. I don’t spend mental energy deciding to use a calculator or not. But AI tools aren’t there yet for me.

referring to the UK as "eurodivergent" from now on

I love Koningsdag, but not for the parties. I love it for the kids. It feels like this holiday should be for them 🧡

SORRY. Sorry. Have we seen this *incredible* news video coming out of Queensland? Wait for the witness/witnesses statement

Today I'm learning that SQLAlchemy and Python type checking don't go so well together. I need a type ignore and a cast to make joinedload work, ouch 😟

Always trying to balance time between learning new tools and actually building things. Building new tools lets you do a bit of both, but I’m not sure it provides as much value to the world.

Agents are much more effective when there is some kind of feedback loop. Good example for coding agents are tests. But existing tools don’t often do this well, especially when the feedback is visual. I want the agent to look at my ppt after inserting text and look at my app after changing code.

“we and our 176 partners…” i dont need to know that

What's the best source for model cost/quality comparison these days? I want to generate some charts with my own selection of models. ArtificialAnalysis really fell off, half the models don't even show up on the chart. LMArena doesn't let me pick models. Is there a dataset I can download?

Interesting announcement when you're just starting a multi-agent project 👀 Don't think I'll be using it immediately since it's not production-ready yet, but I don't mind that we're giving the multi-agent concept a little more shape. developers.googleblog.com/en/a2a-a-new...