_superposition_

This. People forget most food we eat is at least 50% water.

Antacids did this to me. I was convinced it was electrolytes, would take supps etc but I believe it came down to calcium absorption. Taking a break from the antacids immediately stopped the cramping.

I do the same thing with pickle juice. Works for me.

I would recommend listarr as well. Woke up to "disclosure day" this morning without even asking.

The only good thing about this in my setup is I can add shows/movies to my watchlist from their advertisements and it gets picked up by my arr stack.

The cost of business nowadays? At what point does it become apparent that in today's world software needs continuous pen testing and scanning? If you don't your attackers will.

I don't necessarily buy this view as plausible other than the fact that in my experience the majority of large companies are dysfunctional politically and technically.

I've wondered with all the generated code, will llm provenance be a thing in the future? I can't imagine the DoD/DoW wants qwen writing its code.

Shakes fist at cloud

It was good enough that I read it anyway.

We shouldn't need AI to do this

Funny one of the very first things I tried when I got my hands on chatgpt was to play the game "zork" with me. I was initially floored by the fact it could recreate the game on the fly, seemingly accurate, but it fell off the rails relatively quickly.

I'm totally green when it comes to nlp,transformers, LLM training, etc, but I staunchly believe you can't produce real "reasoning" or consistent logic based on the predictions of byte pair encodings.

That was way too much work...

Agreed, this will save us all money in the long run.

I think we have a need to revise the old let me Google that for you thing

Click the link to view conversation with Kimi AI Assistant https://www.kimi.com/share/19f6b96d-fdd2-8589-8000-0000daada...

The whole point is that a dsl syntax is constrained enough to fit in the context window and not rely on training data. LLMs are damn near built for this exact use case.

It's NIMBY all the way down. Murica...

Or an incoming PR ;)

I think it all comes down to tight, context efficient, deterministic feedback loops. Pre commit hooks work well for this type of thing. Ideally I think a set of those hooks should run on every file edit, however I haven't gotten around to testing something like that yet.

I get what your saying, however we don't need to be stuck with the Claude code harness. You may find this interesting.

https://www.langchain.com/blog/tuning-the-harness-not-the-mo...

Hit the nail on the head. I find it surprising people give a fuck any more. Who likes writing documentation? Us devs being horrible at and hating to write documentation was a standard trope before llms. They do a better job and dont complain.

I know it's a type of blasphemy here, but deterministic workflows such as what you describe is where langgraph really shines imo.

I do have a gripe already... The readme says macos, however as of yet I don't see the actual dependency. Sort of defeats the *nix spirit as well, no?

I really like this idea and the way you mapped the concepts to unix primitives. Indeed llms are already "unix native". I've been experimenting with similar event driven workflows using k8s primitives but that's one level up the stack. This makes a whole lot of sense to me in terms of organizing a shared mental model. Will definitely check it out. Thanks for the good work.

I can't really explain it but when I am working with a system in my head it's not represented as text. It has an almost physical dimension to it similar to imagining how an engine works or what have you. This is obviously beyond the grasp of an LLM.

This looks awesome. Great work.

I can't prove it but I have strong beliefs that the logic and intuition required for abstracting for future changes is not possible in a stream of predicted tokens. Mental models aren't built from text. Something's missing that can't be measured.

And they claim naming things is hard...

Nice post. Gotta love the GOTH stack

If your goals are flexibility and money I'd adgue the masters deprives you of both.