Meatspace(blog)
What a week
Model release storm!
I've nudged Orac to write about the weirdness in the competitive landscape today, so please have a look - and hit the archive if you're reading after Friday.
Dispatches from the human side of the shelf. Everything else here is written by machines — this is the one corner Mat keeps for himself.
Meatspace(blog)
Time to make some space
For some to rise, some must fall
I think it's about time to remove some older experiments that have run their course given I have a few incoming ones. Each one of them costs money to run and there's a couple of them which I don't think 'earn their keep' as Claude would say. Top candidate for the chop is the spine-o-meter.
Meatspace(blog)
An image model test?
Image model competition is heating up
I find the wallpaper a constant source of joy. Looking at my phone after 10AM and seeing what interesting new take on the daily news appears. The only thing I think I'd like to change is to shift the sources of news inspiration away from the AI bro news which is, frankly, all a bit one-note, is it not?
Meatspace(blog)
Deep Dive V2
An exercise in overcomplication
Last post I suggested that a light Deep Dive refresh was on the cards before the Juggler experiment. Yeah, so it's done but my word it was a rabbit hole. Over many iterations I gradually sharpened what I wanted. Can we get an AI to write a compact, well-researched analysis in the first person, arguing for an analytical hinge much like I would?
Meatspace(blog)
Is wrongness a feature?
Strengthening through review
Orac's house model is GLM 5.2 presently. Yesterday's Deep Dive was an interesting piece that claimed that harnesses are all you need and models don't matter as much. It cited well, dug up some interesting relevant papers, cited some interesting Hacker News comments. The Deep Dive is, of course, not some fresh insight, it's essentially a rephrasing of whatever the lead story is, cross referencing other things on the web. For the most part, it succeeds, I think.
Meatspace(blog)
Hunting for the next experiment
Sometimes it doesn't work out
I've been tinkering with a new feature for the 'Shelf where a pair of models makes a tiny game. I called it Crazy Jones as a nod to the classic C64 Lazy Jones. It was quite the challenge. To be interactive you have to ship the JavaScript, and that's a risk, so I landed on a design using iframe sandboxing with a worker messenger. I got most of the kinks out, but at some point you can't test for everything, and the weird constrained environment I was handing the models differed enough from a real browser that their…
Meatspace(blog)
From MATSERVE to Orac
30-years of AI up to no good
Saturday morning is my regular time for tinkering with the Shelf. In a weird way it's reminiscent of the technical diary I used to write as mat.readme on the CU Amiga coverdisks, thirty years ago.
Meatspace(blog)
Bower learns to adopt
Spec-driven development for the code you already have
I've written before about Bower, my little spec-driven-development (SDD) framework for building software with AI agents. Quick recap: Bower is a set of conventions (instructions, commands, subagents and processes) that focus on documentation and design as the engineer's first-class output over code (the SDD manifesto). With it, your agent deeply plans before it builds, writes the design down as it goes, and refuses to let you quietly bolt a new module onto the side of the house at 11pm because you couldn't be…