I think that what they mean is that instead of ten perfectly orthogonal "unix philosophy" tools (skills) for the agent to compose when solving a problem, each with an API surface (description text) the size of Texas, you'd want to can each composition in a shell script (or a bespoke rust binary, if you enjoy watching your bot perform some heavy lifting) that only solves one problem but solves it so focused that the accompanying skill description barely consumes more context than the tool's self descriptive name.

I still didn't follow, you mean to pipe things between tool calls? Like if you want to query something and then update another without the intermediate getting brought in context?

Is that so surprising? I thought that was a given. And as soon as remote resources are involved, the old "it's in a docker" peace of mind does not apply.

It keeps people employed, yes?

And with people I guess I might actually mean not people but tokens everybody has to spend on keeping their environment self-adapting...

Makes me wonder what the penguins of Heard and McDonald Islands would say about this

We don't see them because they are so good at it, obviously ;)

Yeah, those stealth games never really clicked for me, with their absurdly imperceptive professional guards standing around everywhere.

Read about it back then in what might best be described as a kid's annual hardcover magazine and loved it so much (a few years later they had a long article about the Porsche 959, it's almost a tie for me). "Das Neue Universum": in those years they had an awesome mix of technology, culture, adventure and science - some parts much further from "ELIF" than one might expect.

A part of that young me still seems to live on being mighty disappointed that I'm not living in that future!

> "Das Neue Universum"

Interesting publication (history) [1].

1. [https://de.wikipedia.org/wiki/Das_Neue_Universum]

Can you name the individuals you are betting with on Polymarket? Can they name you?

Gannon Ken Van Dyke has entered the chat.

Do you find it hard to max out, or do you find it hard to productively max out?

It's like paying drivers per gallon of fuel consumed and then acting all surprised that you see them revving their engine while waiting at a red light.

Same thoughts exactly.

I wonder if Google is aware of its identity crisis? Even long after "don't be evil", Google was still "we earn so much from a healthy web that making the web a healthy one is almost a straight forward company interest". Now web content is actively relegated to training input and LLM chat replacing delegating to the source, that web that Google made so much money of, as healthy or not one considered it to be, will soon be gone. Could be either at Google, complete lack of awareness or desperate "we can't stop it but we might still try to profit a little from what we can't stop"

So give harder guiderails? Sonarcube and the like. But I guess then the failure mode would be appeasing the linter while slowly forgetting the requirements... (or not so slowly, because the try/fail loop won't be nice to context at all..)