If so, one benefit is you can quickly and safely mix up your set of agents (a la Inverse Conway Manoeuvre) without the downsides that normally entails (people being forced to move teams or change how they work).

It's already been linked in comments here but there's been a bit of exploration in that area with Hedy. There's some good references to prior work and comments of relevance in this paper https://hedy.org/research/A_Framework_for_the_Localization_o....

In a live conversation context you can mention the term NFTs/web3 and if the far end is human they'll wince a little.

This made me laugh far too hard for far too long.

It's a good thing governments (https://www.ato.gov.au/online-services/voice-authentication) and banks (https://www.anz.com.au/security/how-we-protect-you/voice-id/) haven't gone all in on using voice as an authentication mechanism.

> It is possible to use the language server for syntax highlighting. I am not aware of any particularly strong reasons why one would want to (or not want to) do this.

This is an area where TS excels. It also supports nesting of different languages so a query can inject other languages [0] and compose different parsers.

As an example, this can be a straight forward as a simple comment parser [1], jsdoc [2], regex [3] etc. Or in more complex cases various DSLs. Each of these can then define their own injections too. When working with CI pipelines in particular it transforms an opaque wall of YAML into slightly more manageable CST which is incredible useful for both humans (syntax highlighting) and any machine parsing you may want to do.

[0]: https://tree-sitter.github.io/tree-sitter/3-syntax-highlight...

[1]: https://github.com/stsewd/tree-sitter-comment

[2]: https://github.com/tree-sitter/tree-sitter-jsdoc

[3]: https://github.com/tree-sitter/tree-sitter-regex

And here I was excited to see disjoint subtrees of Wikipedia's articles.

That is not novel - see language/framework choice, OS (or even distro) preferences, editor wars, indentation. People develop strong opinions about tools, technology, and techniques regardless of domain. LLM maximalists just have the unfortunate capability to generate infinite content about their specific shiny thing.

Check out LXC and the wider Incus set of projects: https://linuxcontainers.org/incus/.

Running IncusOS on some local hardware with ZFS underneath is a phenomenally powerful sandbox.

Yeah I can make an lxc container called "ai" that has an ssh read key and then a few pre cloned projects. When I want to work I can clone and start it then get the same effect on my own hardware and for free. Just need a small little wrapper to make this a bit more streamlined

AIstrology is a term I can get behind.

I think that really captures what I find most irksome about the fanaticism. It's not prompt engineering, it's a statistical 8-ball being shaken until useful output appears.

Just as with any pseudoscience, it can offer a glimmer of usefulness by framing problems in a different way. Just be cautious of who's offering that enlightenment and how much money you may be paying for it.

https://tixy.land/ is another where the constraints encourage creativity. A lot of these tools are a little like tiny demoscene.