Viewing profile — 4corners4sides

People have made cool racing education simulators with this too: https://github.com/FT-Autonomous/ft_grandprix .

Ah okay, thanks. We've come a long way since the purple gradients and glowy buttons but I suppose there is still a tell.

This is a pretty unique aesthetic. Does the author have other works / a blog? Can v0 / Claude Design do this these days?

Roblox is the elephant in the room here which fills the niche for freemium, fun 3D experiences that run on basically any platform or device.

This article is a really good summary of current thinking on the “world model” conundrum that a lot of people are talking about, either directly or indirectly with respect to curre…

The benchmarks look good. Slide decks and spreadsheets look better. The people must use Claude Cowork and have their Claude Code moment and figure out the consequences. It will be …

This is OpenAI taking the concept of AI coworkers seriously down to the level of “identity” for these agents. This reminded me of Kairos which came up a few days ago ( https://www.…

Large scale AI deployment has led to a complete change in what signal code actually conveys and what it means for maintainers. Code is no longer a yardstick for effort, care or exp…

A compiler is another thing whose honor and pride that the models have taken from the nerds. In the past, people would debate for hours about the “dragon book” v.s. “writing interp…

The author makes a point that you should redo every manual commit with AI to align you mental model of actions with how models work. This is something that I’m going to need to try…

A 77% score on terminal-bench 2 is really impressive. I remember reading the article about the pi coding agent ( https://mariozechner.at/posts/2025-11-30-pi-coding-agent/ ) getting…

This article convinced me to try to set up OpenClaw locally on the my raspberry pi but I realised that it had no micro SD card installed AND it used micro HDMI instead of a regular…

This is one of those “don’t be evil” like articles that companies remove when the going gets tough but I guess we should be thankful that things are looking rosy enough for Anthrop…

Despite having read articles discussing when to delegate to AI discussing agent completion time, agent success probability and human verification time the thought of genuinely syst…

Cool addiction blocker product. Also ties into a strange concept whereby something has value because you pay for it as opposed to the other way around. This idea probably generalis…

From my perspective he seemed to go through a lot of trauma to end up with an otherwise regular linux install (NVIDIA driver failure, KDE plasma failure, extremely slow downloads, …

This one touches on the metaphysical union of all prior minds and the implicit “natural” element to “artificial” intelligence. Yes, indeed sometimes reading LLM written text you ca…

Mario’s enthusiasm for his coding agent here and the sheer surface area of the pi project reminds me of how in a bygone era people used to fawn over their own text editors, the fea…

The number one principle of the author’s philosophy is that anything that a user can do through a UI an agent should be able to do through a sequence of tool calls. I agree with th…