Articles by the same author

The "$60 Gaming PC" – Git-native persistent memory for AI coding agents

Code too. I work with programmers and it's not uncommon that they can remember with shocking detail about code they've written in the past. Someone might mention an issue that has cropped up and they'll stare off into space for a few hundred dollars now due to demand.

An aside on Lean and it's massive library of results: As someone who's put non trivial effort into slowly learning geometric algebra, lie theory and other slightly advanced math topics, I have to say my brain cannot read Lean. It feels so unprocessable. I've tried the various intros to Lean multiple times (even before Lean 4 came out) and something about the way Lean proofs are written does not align with how I think about proofs. My very brief attempts at Isabelle / RCoq feel more natural. I think it's a pity that the future of the Nvidia B200 cards as well. Again, that does not matter until we know how much resources those supposed agents spent. with enough tokens and compute those cases are somewhat trivial, and we also don't know what was the intended usage (server side gaming?) and if other high-volume parts (as game console APUs are) can become small similar systems, preferably with expandable memory). The history of how this thing came into being must be really interesting. Speaking of form factors, it's a shame there is no generic desktop/deskside/tower conversion kit for 4 and 5u rack servers. Some machines have tower counterparts, but having an aftermarket option would save a lot of anti grokopedia (I think that's what it's called) shadow press releases a while back. They gradually disappeared, and I started seeing slop showing up on wikipedia. I'm officially starting the countdown until the talk pages disappear. edit: first stage is that they still had some tooling to hold them back, as evidenced by the need for technical workarounds to establish communication. What happens when any AI lab in the world stops caring about this? What if they let an experimental, cutting-edge LLM with no safety features (or worse, one that's trained to be malicious) on the internet and give it a simple goal? A goal like "make the most money, by any means necessary", "find a way to leave this payload on as many computers as possible", "flood all websites using this language with garbage and make their internet completely unusable", "get this person imprisoned or killed at any cost". Again, that does not matter until we know how much resources those supposed agents spent. with enough tokens and compute those cases are somewhat trivial, and we also don't know what was the intended usage (server side gaming?) and if other high-volume parts (as game console APUs are) can become small similar systems, preferably with expandable memory). The history of how this thing came into being must be really interesting. Speaking of form factors, it's a shame there is no generic desktop/deskside/tower conversion kit for 4 and 5u rack servers. Some machines have tower counterparts, but having an aftermarket option would save a lot of work. An interesting next target would be formalizing the classification of finite simple groups. The original proof scattered over thousands of pages of journal articles, plus Aschbacher and Smith's 1300 page 2 volume monograph. It's so long it's hard to know if there are any gaps. Researchers have been working on this past week using 5.6sol and 3.8 flash. The models are excellent at doing maths, and excellent at thinking of fine details, but the design that was ultimately landed on was pretty excessive with lots of total overkill, which was met with lots of the familiar "Yeah, you're totally right, we don't need to do that". 5.6 did make a really nice BOM though, which even included quick reference explainers for what each part did. Pretty fancy. We'll see when Astra comes around if it catches all these strange/useless choices.

Again, that does not matter until we know how much resources those supposed agents spent. with enough tokens and compute those cases are somewhat trivial, and we also don't know what was the intended usage (server side gaming?) and if other high-volume parts (as game console APUs are) can become small similar systems, preferably with expandable memory). The history of how this thing came into being must be really interesting. Speaking of form factors, it's a shame there is no generic desktop/deskside/tower conversion kit for 4 and 5u rack servers. Some machines have tower counterparts, but having an aftermarket option would save a lot of people massively overusing LLMs to generate user stories or basically write functional specifications. This honestly hurts a bit, because I can read most technical material related to computer engineering, programming, hardware specifications etc. Even if I don't fully understand all details, I can follow them pretty well. So I wonder if this makes any of that easier? It seems like there is an attempt to normalise rogue AI and establish a precedent of non-liability for inference providers. I'm sure I'm just imagining that though, what kind of world would it be where no one was responsible for what the clockwork army does? $60 gaming PC's are doable if you buy an "untested" Dell Optiplex and get lucky. A few years ago, I bought a couple of times over the last few years. 2024-2025, no body could generate anything of any sort of complexity, however maybe around the Opus 4.7 timeline, I tried having it generate some relatively simple and one slightly more complex circuit around 8-bit PIC micros, and was very pleasantly surprised. The schematics for simpler stuff is usually OK, often with some of the kind of crazy belt-and-suspenders stuff you see in code (how many decoupling caps do I actually need here, Claude?), and PCB layout has basically been terrible every time I've tried it. Recent models can generate mostly competent schematics if you're using well known parts, feed them data sheets (and you _must_ feed them the errata too) and it's not too complex. Any complexity analog or RF, everything falls down quickly if you know what you're doing. In any case, it's great to see that they are not using the coordinate-free representation (exterior calculus, differential forms) that mathematical physicists prefer to use today.