jbwinters

Ah, that’s a tough one. My hope is that Jacquard, or some similar language, can make intent explicit through readable, high-level constructs, giving both the human reviewer and the model a clearer target while the details are filled in. But it still can’t tell us whether the original intent was right.

Coincidentally, you reminded me of one of my favorite Charles Babbage quotes:

> “On two occasions I have been asked, ‘Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?’ I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.”

I suppose catching that kind of mistake is how humans prove to our future AI overlords that we should be kept around.

That’s a fair concern. I’d expect multi-shot handlers to be relatively rare and mostly something library code uses rather than a day-to-day utility. But an LLM given free rein may decide to behave differently.

For now, I am looking into making a clearer distinction between one-shot and multi-shot handlers so we can reject cases where resuming again would be unsafe, like around filesystem writes.

More to explore here, certainly.

You're right, an LLM doesn't have preferences. As shorthand, I thought it a useful concept though, as they do have particular ways of writing that can be tuned for.

The effect system here is part of a type system (technically a type-and-effect system). Where a value type typically describes what value a computation returns, an effect describes which operations it can perform during evaluation.

The difference is that effects propagate through the call graph, so lower-level code cannot access disallowed resources without that authority appearing higher up. At runtime, world effects also require an explicit grant. In a typical value type system, lower-level code can introduce side effects without them appearing in the caller’s type.

It's a good name regardless! Don't stop on my account.

Thanks for the pointer to Jai! I will check it out.

Yes, Jacquard uses content-addressed definitions and it should be possible to set up a process for 'review again if this changes' on top of it. Warp, the testing framework, already uses this to avoid rerunning pure tests when neither the definition or dependencies have changed.

Jacquard does not currently implement proof or strictness levels, but binding those to a definition’s content identity is interesting and definitely worth exploring.

What are you building that people keep comparing to Ada?

I dug into the Stargate data center Michigan just approved. 1.4 gigawatts of load, roughly 11% of the state's entire retail electricity consumption. It's been controversial locally but most of the debate has been about farmland and water. I think the more interesting question is what this kind of infrastructure buildout means for the region's industrial capacity. The same grid upgrades, trades workers, and construction pipelines you need for data centers are what you need to build anything else heavy.