Using a multi-trillion parameter softmax attention transformer to parse nested delimiters is a perverse thing to do. It is hard to imagine a sillier way to boil the oceans than feeding JSON to an LLM, a task that a pushdown automata from the 1960s effortlessly did on a PDP-X.
The API business throws a massive model that by definition can't be inferred efficiently because nothing can across 4 different compute substates, at a problem that DSv4 nails at or near 100% while leaving most of the actual unique value of Claude on the table.
Claude should be in your house and car and your kid's classroom and shit.
Having it write tail -n5?
That's because Anthropic's A-Team is Meta's C-Team. Hell, I fired some of their stars myself.
- multi-model consensus, with multiple cross-review rounds. Obviously, the number of inference tasks explodes with the number of models. Led to some interesting results [^0].
- giving an agent "stray thoughts" produced by the same model, or another, giving the second model a selection of the agent’s context, with different triggers (random, loop detection,…)[^1]. So far has proven very helpful and much cheaper than the first.
> With such eggregious trillions of dollars worth of money (basically the whole economy getting floated by tech), you are bound to see people within this do the grift playbook and talk about themselves and succeed and that has become the playbook.
I’m working on Descartes[^0]. First to help diagnose what’s wrong with a machine.
I’ve started implementing actual background monitoring of the system, and next will be letting an agent build its own layers of tailor-made deterministic rules and statistical models, to "learn" what the system’s normal behaviour is and only "wake up" the agent when something unusual is going on. Either to update its rules and models, or alert the user.
Like the ship’s AI at the beginning of Absolution Gap. Next will be enabling it to serve as the interface for the system. An ops "point of contact" for both the user and their agents for the machine / fleet of machines it’s in charge of.
———
I’m also working on third thoughts[^1], a tool that analyses local agents logs to find patterns and behaviours, identify what works, what doesn’t, how they evolve over time, using deterministic and statistical methodologies and techniques from multiple domains (including, to my surprise, genetics and psychology / sociology), with an agent layer that interprets the results.
I’d like to add a "federative" layer where people can contribute the results, patterns, and findings, without leaking their logs or personal / private data, so that we can all better learn how to identify failure modes, predict them, and see what works and what doesn’t.
———
I’m also having Claude & Codex revive Jasonette[^2], which died off and was turned into some weird paid unrelated thing by those who picked it up. I’d been meaning to but never took the time. But now with agents…
All rebuilt in Swift / SwiftUI on the iOS side, and Kotlin on the Android side. Some features are still missing, but it works quite well! [^3].
———
Oh, and Boucle[^4] is doing its thing on its own. No idea how it got to 100 GitHub star. My "autonomous dog-fooding expensive pet" is apparently more "internet successful" than I’ve ever been.
> Feels complex like solving a Rubik's cube to write down synthesis steps but it is all a sequence of memorized tricks. Do Cannizaro if you want this, Bergmann to do that.
I remember two years ago, when I actually got into using graph data structures, wondering if maybe the "space" of available reactions for any given starter and target molecules could be mapped as a graph, with intermediates as nodes and reactions as weighted directed edges, so synthesis becomes pathfinding through chemical space.
Turns out, it’s a thing! [^0]
Edit: Makes you wonder how much interesting stuff is sitting in plain sight, waiting for someone with the right cross-domain awareness / knowledge / whatever to notice it.
There is a lot of graph theory in Chemistry - modelling chemicals as (vertex/edge coloured) graphs, reaction networks, etc.
Of course some molecules (eg aromatic systems, like ferrocene) are not naturally representable as graphs. I wonder if it is the same with synthesis - are there reactions hard to model as a graph (or petri net or whatever). One simple example I know is that you have to be careful with including a node for 'water' as it gets connected to everything else! Or at least in biochemistry it does.
A metal atom sandwiched between two Cp rings. You _can_ model this as 5 single bonds between each atom of a ring (so 10 total C-M bonds), or you have to have some kind of 'edge' (bond) between the ring as a whole and the metal.
The more general issue is that a graph model of a chemical assumes a 'bond' is between exactly two atoms. Three-center hydrogen bonds are another example where this model fails to capture the chemistry very well.
Of course, it's a tradeoff - you can model _most_ compounds with just graphs (plus atom type, charge, chirality) and the relatively few that do not quite fit are special cases.
From what I found, current state of the art on modelling "reaction space" with graphs that is to use "hypergraphs" where edges can lead to more than one node[^0].
But I am just someone who got curious; not even an amateur ^^’
Ah, I see, sort of like figuring out the boundaries of your knowledge base and seeing if you have missed any connections between concepts?
I suppose it might be useful for learning/ideation. I should try something like that — it could be an interesting synthesis/writing exercise to try to connect concepts that are far removed in your own mental model.
I think it’s not the first time the US has used that sort of interpretation of the law. There’s this one[^0] but also, I believe, an older case, also involving Microsoft, about data in Ireland. But I can’t find it.
These kinds of situations are why I gave my AI agents stray thoughts (automated insights / suggestions from a separate llm call with some curated context) that trigger on loop / rabbit hole detection.
Quite a bit of false positives, but it hasn’t had any ill-effect so far. Aside from increased quota usage.
I am not sure I understand.
reply