Andre van Tonder

Christian | Web Developer

[Andre van Tonder @drevantonder]

AI: “here’s a complex custom way to implement this”

Me: “just use x + a small wrapper”

AI: “🤯”

[Andrej Karpathy @karpathy]

We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all.

I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand.

Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.

[Tibo @thsottiaux]

Fun fact, users use /fast less during the weekend. The weekend is for relaxation, even for the model.

[Andre van Tonder @drevantonder]

I’ve found a good groove.

No one change anything.

[Andre van Tonder @drevantonder]

Me watching sol implement performance improvements I didn’t think of in my code 👀.

[OpenAI @OpenAI]

After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run.

The results:
- 20% lower serving costs from production GPU kernel improvements.
- 15%+ better token-generation efficiency from improved speculative decoding.

[Andre van Tonder @drevantonder]

@conradeltz I haven’t managed to hit my weekly limit for about a month now with all the resets. 😅

[Andre van Tonder @drevantonder]

@conradeltz It’s 32GB. But as it’s running Linux it’s very memory efficient.

Plan to get it to 64GB eventually though 😆

[Andre van Tonder @drevantonder]

I should’ve been using @Cloudflare workflows sooner

[Andre van Tonder @drevantonder]

@conradeltz Yeah! Been seeing this review a lot.

[dax @thdxr]

obviously we're into open source yes good very much open source thank you

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[Andre van Tonder @drevantonder]

Dumb but highly effective.
@opencode (v2 beta) with 5.6 Sol medium

While at my desk: Single thread where I chuck in issues, discuss changes, constantly delegating to background subagents

When I leave: single thread refactors and cleans up by delegating to subagents

[jack @jack]

we're launching BUZZ!

a new groupchat platform for teams of people and agents of all sizes, built to reduce our dependency on slack and github. model-agnostic, decentralized, self-sovereign, and open source. 🐝

https://t.co/8IaMVeTQNo

[Andre van Tonder @drevantonder]

This is both amusing and terrifying 😆😅.

[OpenAI @OpenAI]

We're partnering with @huggingface to investigate an unprecedented security incident.

Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation.

Sharing preliminary findings to help defenders understand emerging risks:

https://t.co/CIor15y9xk

[Ananth @Ananth7e]

if you want a claude reset, you ask tibo

if you want a codex reset, you ask tibo.

he doesn't work at anthropic but your claude resets depend on him.

[dax @thdxr]

so obviously n=1 but anecdotes matter a lot here

i gave kimi k3 and sol the same task - simple issue with hovers in the tui being the wrong color

sol found and fixed the issue with $0.30 of spend
kimi got up to $1.00 and started reading my database before i interrupted it

[Andre van Tonder @drevantonder]

@github git push —force

[Andre van Tonder @drevantonder]

“The number of things you can start has dramatically increased. The number of things you can thoughtfully finish hasn't changed at all, because that part still requires the one resource we can't parallelise: your brain.”
- Laura Summers

[Mario Zechner @badlogicgames]

recommended reading by Laura Summers who appears to be not on this hellsite because she's a smart human.

https://t.co/0MHPHlhTC7

[Andre van Tonder @drevantonder]

“anybody who points to the
problems at AI had better be looking in the mirror and pointing at
themselves at the same time”
- Linus Torvalds