dilap

It was fine until a few releases ago, then they rewrote it, and it sucks now. Had to give it that SwiftUI magic.

Yeah that's fair, though my understanding (perhaps wrong!) is Tesla unlike Waymo doesn't need super-detailed maps; it could in theory go across the state right now (but it doesn't have legal authorization).

(In Austin it covers what looks to me like the whole city but not the surrounding smaller towns.)

Yeah that's a good point -- I'm not sure, but it definitely felt like there was no remote control going on, just based on smoothness and speed. But for sure the ability exists, so good pts re true autonmy and scaling.

Isn't Tesla already there?

I took a fully-autonomyous Cybercab to a coffee shop yesterday; it doesn't even have a steering wheel. It was just a short drive, but it handled various complications (a garbage truck, double-parked cars, construction, unpainted speed bumps) with aplomb. The driving felt extremely smooth and human-like (better, in my experience, than Waymo, which can still be a bit jerky).

GLM 4.7 is gone (at least for us), with no suitable replacement from Cerebras. I think all they care about now is hardware and OpenAI hosting.

This is neat! Would love the ability to make "true noon" be at the top of the clock, instead of 12.

Years and years ago I saw this story on k5 when it came out and never read it -- but from commentary I always thought was some sort of hard sci-fi exploration of what happens when we get AGI/ASI.

So all these years later AI is real, I see the story again, and I figure, hey, why not read it. And how very surprised I was to find out it's basically a horny kink story with a little bit of AI/SF window dressing!

It's exactly because everyone's tone is different that I'm confident it's AI.

Granted, a bit of AI-influencing phrasing in human writing is common, but the idea that someone sat down, worked hard, and came back with an entire page of a pitch-perfect AI slop is simply incredible.

You're too kind. It's obviously AI copy, and a huge negative signal (to me, anyway).

Don't worry, we'll get there soon enough.

Have you tried iterating on style feedback in AGENTS.md? I've been reasonably successful using this to get it to output code in a terse, non-defensive style that matches my hand-written code.

Reload should fix (did for me).

Doesn't look minified, just very dense, almost like progcomp code. First time I've seen an LLM spit out that style of code, I'm impressed!

It's just Claudeslop. It's everywhere. An epidemic. If you're familiar it stands out instantly. (Would you let someone else talk for you? In real life? Like open up your mouth and let a TTS system spit out the sounds and pick the words? No? Then you shouldn't do the same thing with writing!)

Why Codex GPT-5.5 High instead of Extra High, I wonder?

Yeah, it has a tendency to default to "smallest local hack that will work" and code as defensively as possible.

BUT I have had great success using AGENTS.md and becoming better at prompting to get it to not be like this.

Basic approach in AGENTS.md: don't code defensively, yada yada, we have a validation layer at X, no need to check for anything behind that layer. Works well.

An approach I've found helpful when prompting: What would be the best architecture for this change? If you say "do X" it'll tend to just do the hackiest, shortest path thing. If you say, "what's the best way to do X?" it will think more holistically.

That said, who knows, maybe when it's PHP it just really wants to hack ;-)

(Also, yes, you still need to review the code -- it will still do stupid things, so you can't just be pure hands off w/o ending up with quality degredations. The same is true of humans too though in my experience...)

Personally I don't find this to be true anymore! It's not always great and does still will often tend towards unneeded complexity (especially if not pushed a bit), but I often find GPT 5.5 writing code I would have written myself. This was very much not true with earlier models (who make something that worked, but I'd always have to rewrite to make it "good code").

way easier to work on a focussed c codebase you own than a mature unwieldy c++ codebase you don't. but it's fine, people will take that work and port to llamacpp and everyone wins.

(the ux of ds4 is fantastic too -- it's dead-easy to get a known-good model, great quant. llamacpp you're much more hacking in the wilderness, w/ many many knobs.)

FWIW, I've found Codex with GPT-5.4 to be better than Opus-4.6; I would say it's at least worth checking out for your use case.

Deepseek R1 was a publically-available, MoE model that was getting a ton of attention before llama4. Llama4 didn't get much attention because it wasn't good.

i use a an auto-layout tool, so having windows stacked on top of each other is super-common for me, and the fact that they all peak thru each other (like the screenshot in the blog) looking absolutely terrible drives me crazy

I wish I could remember the details -- I know I got annoyed with things being slow and when I got a new computer decided to go the no-homebrew route. I'm using nix, and it seems fine so far, but I also really don't understand it at all, which is a little concerning. :-)

Horses for courses, but I've stopped using brew 'cuz it's too slow, so this might bring me back!

Edit: no, it won't...

I thought this was parody until the last sentence.

I still remember the very first time I saw an emoji -- just an old-school dumb phone, and my friend sent me a message with an emoji, which the phone, amazingly, was able to display. I had no idea such a capability even existed, and wondered for a second if I was dreaming.

Welllll I'm not so sure that phrase is well-suited for your intended meaning, then. (Also, tangentially, I think could argue thinking models w/ the elided thought prelude satisfy "having hidden state where it first forms an opinion.")

Ha, thanks!

I don't know for a fact, but I'd bet a few digits of cold hard cash it's a SwiftUI rewrite that is to blame. (Any1 in the know want to chime in?)

And yeah, it's terrible. Apple doesn't make good apps anymore.

(This is part of why I think electron does so well -- it's not as good as a really good native app [e.g. Sublime Text], but it's way better than the sort of default whatever you'll get doing native. You get a lot of niceness that's built into the web stack.)

The fundamental nature of the model is that it consumes tokens as input and produces token probabilities as output, but there's nothing inherently "predictive" about it -- that's just perspective hangover from the historical development of how LLMs were trained. It is, fundamentally, I think, a general-purpose thinking machine, operating over the inputs and outputs of tokens.

(With this perspective, I can feel my own brain subtly oferring up a panoply of possible responses in a similar way. I can even turn up the temperature on my own brain, making it more likely to decide to say the less-obvious words in response, by having a drink or two.)

(Similarly, mimicry is in humans too a very good learning technique to get started -- kids learning to speak are little parrots, artists just starting out will often copy existing works, etc. Before going on to develop further into their own style.)

That description is really only fair for base models†. Something like Opus 4.6 has all kinds of other training on top of that which teach it behaviors beyond "predict most probable token," like problem-solving and being a good chatbot.

(†And even then is kind of overly-dismissive and underspecified. The "most probable word" is defined over some training data set. So imagine if you train on e.g. mathematicians solving problems... To do a good job at predicting [w/o overfitting] your model will have to in fact get good at thinking like a mathematician. In general "to be able to predict what is likely to happen next" is probably one pretty good definition of intelligence.)