David Busch

@Dimillian Games thrive on good taste and iterations. There’s always something to add or improve, but never enough time. Agents help with that.

I have no idea why I’m obsessed with building games. It’s probably just because I can. I just wish I could find the perfect dopamine loop to go with the perfect dopamine loop.

Now anyone has the power of geometry nodes, with just words.

I'm a software engineer with 50 years of experience. If you know how to steer an LLM properly, the frontier models are extremely good at generating code. They're weak at architecture, which is one of several reasons you want a human in the loop, but they can have a very low error rate compared to most humans. When they don't - when they generate slop - it's because you didn't know how to use the tool correctly.

Love vibe coding games. It gives me a deep appreciation for the time and effort that have gone into traditional games. It's clear that the majority of effort is spent tweaking stats, game play, story writing, level editing, narrative creation, etc. The long tail of polish.

@HakitaDev I instantly recognized that was Guitar Pro. Composing with it was always a blast. Amazing software.

It's actually a very common occurrence for me, where a section doesn't fit either tonally or structurally, so I just move it to the end of the file in case I ever want to use it somewhere else, but usually I forget they exist. Here's two such riffs from ORDER's project file.

just got penetrated by mythos

I can't remember the last time I was truly stuck on a coding problem. AI agents changed this. Going from "sometimes blocked" to "always moving" is wild.

It's Godot!!

This is it, native PCVR on MacOS! The OpenXR SDK can be compiled on MacOS, So I implemented a runtime and a streaming app. Godot supports OpenXR on MacOS so I use it to test my integration. Unity could work too and of course native C++. 1/x

Starter Kit: Racing for @godotengine is now available! 🎉 Easy to understand code, fully open-source & 3D models included! It's a little rough around the edges, but feel free to do pull requests if you can improve on it! github.com/KenneyNL/Start… #gamedev #gameassets

This is neat. Harness for LLMs to play Magic, with recorded games and a leaderboard. mage-bench.com They are, as expected, completely abysmal. But the frontier models do top the leaderboard, so there is some signal there!

Ucupaint is awesome. I love seeing free tools like this

Introducing the Google Workspace CLI: github.com/googleworkspac… - built for humans and agents. Google Drive, Gmail, Calendar, and every Workspace API. 40+ agent skills included.

Watching Claude implement a feature and then validate it feels like pure magic.

It's basically impossible to predict what emergent properties you might get from scaling up a given algorithm. That's why AGI is much more an engineering endeavor than a theoretical one. It's a process of discovery through building.

Cool chart showing the ratio of Tab complete requests to Agent requests in Cursor. With improving capability, every point in time has an optimal setup that keeps changing and evolving and the community average tracks the point. None -> Tab -> Agent -> Parallel agents -> Agent Teams (?) -> ??? If you're too conservative, you're leaving leverage on the table. If you're too aggressive, you're net creating more chaos than doing useful work. The art of the process is spending 80% of the time getting work done in the setup you're comfortable with and that actually works, and 20% exploration of what might be the next step up even if it doesn't work yet.

@DustinQFit @paulsaladinomd @SamaHoole @grok It’s okay, Paul says grass fed steak is the only thing that’s suitable to eat. Despite studies showing grass fed steak having the largest amount of microplastics. He just goes off vibes and engagement stats

@paulsaladinomd @SamaHoole Ever heard of BPA free cans Paul? @grok, tell Paul that he is overreacting on BPA in sardines if it’s a BPA free can.

Sardines might be the most underrated superfood on the planet. What £1.20 gets you: - More Omega-3 than a £12 fish oil supplement - More B12 than any plant food (because plants have zero) - More Vitamin D than 30 minutes of sun - Selenium that most Brits are deficient in - Calcium from bones (if you eat them) - Protein with all essential amino acids - No mercury (small fish, low on the food chain) Skip the rancid Omega 3 capsules. Just eat the fish.

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

The kind of AI cynicism that backs someone into the corner of "if AI is so great, why isn't all software perfect yet" is secretly the most accelerant-forward optimism possible. We've known these new supreme models for ~3 months and you already demand perfection? BASED URGENCY!

@goodfellow_ian @daniel_rossett Happy to hear you’re feeling better! I’m curious to know what helped, even if just at a high level

I'd like to thank @daniel_rossett for his help in my recovery from the POTS version of Long COVID. Daniel was key in bringing me back from highly disabled and suffering to being able to do what I want to again. This X account is mostly focused on ML / AI. From that point of view, many of you know that in December 2024, I wasn't able to do the test of time award talk at NeurIPS, even by video call. Daniel started working with me in March 2025. By April, I started to have days of no POTS symptoms, by June I was off all heart rate lowering medications, by September I was back to work. I'm back to full exercise, running, lifting weights, mountain biking, and have even done things I hadn't done before I got sick, like riding Whistler Mountain Bike Park. I'm now getting the word out to help Daniel build a company that will bring this approach to more people.