williamcotton

Will MacAskill responds to our cover story on effective altruism

https://www.economist.com/by-invitation/2026/10/04/will-maca...

Here’s an example:

https://williamcotton.github.io/datafarm-studio

Some demos of the above charting language:

https://williamcotton.github.io/algraf/demos

WASM, in browser editor, LSP, and more.

I’ve had the best luck by spending quite a bit of time going over the big picture architecture up front and then diving into the modules to further refine the details, making sure to generate step-by-step chunks of work in Markdown format for implementation. I’ll spend literally a couple of days doing this before starting any coding.

Edit: My latest project is all GPT-6 Astra High. It takes a lot of steering to keep it from adding a bunch of, while useful, features that are not strictly enough to the point. That main issue is it’ll use a lot of extra tokens in the process!

What was your process?

No one reads my blog, should I never post my own articles?

I've been playing around with a new DSL, and I've had good luck adding a "describe" feature, eg,

  newdsl describe some_feature

This returns the docs for that language feature. So instead of a giant SKILL.md containing the language spec, it exposes a way for an LLM to introspect.

DSLs climb the ladder of abstraction and constrain the solution space at the language level, which IMO provides tighter feedback to both humans and machines.

ACX has been on the Georgist tip for awhile.

Why is LLM code always harder to audit?

So LLMs might decide to add backdoors without prompting?

How sure are you that any printer driver didn’t include a backdoor? What’s the difference between the LLM code with the backdoor and the human code with the backdoor?

There’s some level of irony around the fact that McDonalds spends quite a lot on branding and design.

Is there truly anything new under the sun? Hasn't all of existence alway been here? All math, all physics? We could have merely discovered it. Intuition might be nothing more than combinations of what already exists rather than some sort of divine insight that unlocks previously unknowable mysteries.

Ok, so, “gibberish” in this case?

Honestly, this word has lost all meaning, outside of perhaps “any use of AI”.

Well at least I know where team “lawslop” is coming from. Thanks, I guess?

I’m honestly looking for an actual example of something other than hallucinations! There are no examples in this entire thread! It’s just cynicism.

Why be so unkind?

So is there other “lawslop” or is it just hallucinations in this context?

Aren’t hallucinations different than slop?

So no, I don’t know what they mean.

What do you mean by “lawslop”?

Additional tip:

In the macOS terminal you can...

  Ctrl + Option + -

...and it'll undo your typing.

Dunno about other OS keys!

Here's an in-depth explanation with an interactive demo that I made many moons ago:

https://web.archive.org/web/20130728183938/williamcotton.com...

What an utterly unconvincing call to action.

You’re not offering a rebuttal, just making another metaphysical claim about “intelligence.”

You don’t even attempt to explain what practical distinction your use of the word is supposed to capture.

Most of these arguments are over some metaphysical definition of the word “intelligence”.

As per later era Wittgenstein, I prefer to ignore these engagements and focus more on the meaning-as-use approach.

What is the use of intelligence? What are the concrete outcomes of intelligence?

Pick up a copy of Crime and Punishment ASAP.

Vivian, the commercial baker, learned a different set of skills. She might have deskilled with regards to hand-rolling dough but she gained new skills related to industrial production.

I've made a half-dozen or so DSLs with LLM tools over the last couple of years. I've learned a lot about the architecture of parsers, semantic analysis, editor services, LSPs, DAP, etc. I have a new set of skills! I'm able to focus more on the syntax and semantics languages themselves and the overall developer experience. This would have taken literal man-years of development to do otherwise.

For my hand-rolled craft I'd much rather sit down at the piano or pick up my guitar!

Makes sense, thanks for the clarification.

I settled on starting with a CST using rowan, doing semantic analysis, having an agnostic editor services, exposing both an LSP interface with tower, and a WASM interface (for Monaco in the browser [non-LSP!!]) and having the runtime binary doing the interpretation/compilation with the same pathway, with a slight jog, as the editor services. Phew!

Ah, so does the LSP just call out to the Buf binary?

I looked at the dependencies and noticed that it wasn’t using an existing Protobuf parser which means they reimplemented the parser from scratch. Perhaps due to a lack of error recovery in the existing implementations? I don’t have the energy right now for further inspection.

It is definitely best to reuse the parser for the runtime when implementing an LSP but to do so properly means implementing the parser itself as a standalone library. Even better is shipping the semantic analysis as well!

Implementation drift is definitely an issue.

But great project anyways, just wanted to put my thoughts on the matter into the conversation!

At least later-era Wittgenstein would disagree with you.

It is still in their interest to not report "false or misleading statements that you or others on your behalf make regarding your company."

https://www.sec.gov/resources-small-businesses/exempt-offeri...

Sure. So does this diminish the role of Rembrandt? Or is this some semantic black hole you’re drawing us into?

There have been plenty of workshops where artists hire assistant painters while maintaining authorship over the works themselves, from Rembrandt to Warhol to Hirst.