williamcotton

I’m talking about mechanically editing a Word document, not generating complaints. You can tell it to CRUD paragraphs, images and tables verbatim.

Pro tip: light that cigar with a flame thrower and use ChatGPT Work to create and update Word docs. Never open it again! It’s good at formatting tables, moving images around without the entire document exploding into shards, redlines and comments!

Re: Use it with your agent

An approach I've found useful, albeit for a DSL that ships a binary for execution, is to give a way for the LLM agent to get a high-level topic list so it can drill down all the way to specific language/API implementation details.

Perhaps with this project the author could make a website that does the same?

So a singer-songwriter who plays all the instruments, produces and records all of their material? I mean, do we get down to the details of microphone choice and positioning?

I'm not asserting that human and AI outputs are generally indistinguishable. I'm stipulating that they are in this particular hypothetical to isolate the question of provenance.

Even if AI were entirely incapable of creativity, why would incorporating its output diminish the creativity of the human artist?

What about stock samples, preset drum-machine patterns, or clichéd drum parts played by a human drummer? Do these diminish the artist's creativity, and if so, why?

Why does hiring a known human drummer directly instead of using the black-box "Hire-a-Drummer" make my own creative contribution any more or less significant?

The morality of AI is another discussion entirely.

Or are you suggesting there's a spectrum here? Is the overall creativity of the album greater with a human drummer than with drum samples, a drum machine, or AI-generated drums?

Imagine the attribution for the drum tracks is "Hire-a-Drummer". Neither the artist nor the listener know if the actual drum tracks were from a human drummer, a programmed drum machine, or AI.

Is the issue, "hey, it might be AI, therefore on a metaphysical level I do not enjoy this as much as if I knew for certain that the drums were recorded by a real drummer"?

Or separately and without the complication of "Hire-a-Drummer", what about failing to disclose that drum tracks were hand-sequenced on a drum machine?

Or separately, is the issue that the drums were outsourced in the first place?

That is to say, if a human drummer is hired and the only instruction is to "add some dope beats to this track" and the drum tracks are used thereafter without any further refinement, does/should this affect the listener's perception?

I don't think you've understood, let me clarify.

So the inputs to "Hire-a-Drummer" are always the same. Sometimes the mechanism is an actual drummer, sometimes it is a programmed drum machine, and sometimes it is AI generated. It's impossible to tell from the outputs what the mechanism was.

Does the mere use of "Hire-a-Drummer", even assuming that the drum tracks were recorded by an actual drummer, diminish my creativity in the final songs on the album? Is it neglectful to outsource drumming in the first place?

Thought experiment: I'm producing my own synth-pop solo album. I can play guitar, piano, synth, bass, and some saxophone. I need to hire a drummer. I use a black-box service call "Hire-a-Drummer". At no point do I know if the drums were recorded live by a human drummer, if a human hand-programmed the drums, or if the drums were created by AI.

Is there some kind of metaphysical tainting that takes place based on what happens inside of the "Hire-a-Drummer" black-box?

FYI, a person being deposed is called a deponent!

> code is a liability, not an asset

This is not the case as far as accounting and the law is concerned.

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.