wild_egg

I'm sure we are going to have to wait for some actual court cases to establish precedent but I don't really see why this is the case.

If I use a fancy brush in Photoshop to paint flowers into a PNG — do I own the resulting image? Code is bytes of text on disk, not much different from bytes of pixel data in a BMP.

If I have to type every character by hand in order to own the bytes, then it would stand that I would have to input every pixel by hand in Paint to own a graphic. No? Even using the Fill tool is automating the creation of those bytes and would mean I don't own them. Right?

I have an intention for some bytes of data to be set. If I use an LLM to set them instead of my own fingers, why are the bytes suddenly not mine?

I do not understand.

Relative few that have been around a long time? There is a plethora of 10+ year old incrementals with virtually endless content at this point.

Right... That's exactly the kind of nonsense that turns people away from ecosystems.

Good luck with that.

I feel like you just directly contradicted yourself so there must be some nuance I am missing. Or is the key word "mostly"? Like I can use LLMs to help the work but still have to type most of the code myself?

I have not written more than maybe 10 lines of code in the last year so it seems I am prohibited from hosting on codeberg?

Or is the key word "share" and that's somehow different from "host"?

I've been using LLMs for Common Lisp since Sonnet 3.7 and have never experienced that. Did you have a mixture of other lisps nearby to confuse it? Seems like an odd failure mode.

Who is talking about limiting to one technology?

I'm saying websockets are not fit to purpose and I can't see a compelling reason to ever reach for that particular technology any more than I'd reach for COBOL. Sadly, the browser environment gives us very few choices for streaming data connections.

Really though, I suppose I am limiting to a single technology: HTTP. Which kind of makes sense, I am putting hypertext content in a hypertext client over the hypertext transport protocol. If browsers spoke SSH, maybe I'd use that instead. I can't see a use case where adding a second protocol to my apps justifies the large increase in complexity when the capabilities are already better provided by the protocol that I'm already using.

> With HTMX, I'm writing several server-side functions to mutate the DOM imperatively and using HTML attributes to call them. Its great for forms but that shopping cart example needs code scattered across multiple functions and templates.

That's a weird way to use htmx. I've built a number of large apps with htmx over the last few years and never done this. Seems a great way to have a bad time.

Would really love to read this in your own words. In any case, I find the rationale for each of your points to actually better support the SSE approach. Your post actually sold me more on why I should not use websockets. Interesting.

Do you need to pipe the ruby output to bash? Ruby could just run the mv directly by wrapping in backticks instead of quotes.

This one does agentic search instead of compaction: https://github.com/wedow/harness

Generally works quite well but it allows nested subagents and that can use a lot of tokens if the agent prompts are too open-ended.

All messages are persisted as separate markdown files under a session directory, which makes them much more friendly to grep and such than the common jsonl files are. Agents can search them rapidly without messing around with jq.

Also written in Bash so it runs on any old potato you have laying around.

> Shouldn't this be a pretty fundamental part of a degree? If you're in school right now for a CS or SWE related degree, I would imagine you're learning how code actually works, how the math actually works, etc.

CS and SWE are radically different subjects. Science vs Engineering. I'm sure it varies by school but many CS grads will have approximately zero exposure to engineering concepts or any of the latest and greatest frameworks.

I do understand that's what they have in mind. But that's not what immediate mode means. Function application is not the only criteria.

We are talking about rendering into a browser by twiddling DOM APIs. That's definitely retained mode rendering and repeatedly claiming it's immediate mode doesn't make it true

> immediate mode

You keep using that word. I do not think it means what you think it means.

React most definitely falls under what would be called a "retained mode" of some sort. And the UI library described here is also.

What's wrong with the Tailscale free tier?

There is also Headscale if you want to self host.

https://headscale.net

He says here that they have a direct Tailscale integration of the type that requires using the `tsnet` package, which is Go. Or at least would pull in the Go runtime as part of a shared library.

https://x.com/i/status/2082634453474795885

> Yes, tmux should be good enough for agents tomorrow. But here we are, today.

tmux is good enough for agents today. they're great at driving it, they're great at customizing it, what's the problem people have with it? i am confused.

I don't understand what is broken with the browser's management of typed content. Do you have an example of UX that requires a custom state management layer on top?

Would love to hear about which of those listed examples does not currently have native browser support.

I've had decent results telling agents to use emacs for structural editing operations. Pretty rare that I need to move a function across files verbatim but that should only be a few extra lines of elisp.

more context beyond the changelog? what would you like to know?

No auto-vectorization yet, but you may find this illuminating: https://www.stylewarning.com/posts/nbody

Every one of those are things that the browser manages for you if you are using semantic markup and embracing web standards.

Based on skimming the couple sibling comments, I believe the issue you have had with htmx is precisely that you have somehow conflated it with angular. If you think they're the same, you will use them the same and have the same poor outcomes.

In another comment, you mentioned State Management. If this is on your mind then you are using htmx wrong. You should not be managing any client side state with htmx. State is on the server or in your database. Interactions on the client should immediately reflect the updated server state. If you have separate state on the client that needs to be managed, you are going to have a bad time regardless of framework.

As someone who wrote a lot of angular back in the day, and who writes a lot of htmx in the current day... That comparison makes absolutely no sense.

The only thing the 2 have in common is the use of HTML attributes for functionality. Completely different on every other axis that matters.

I'm doing a bunch of x86_64 assembly these days and Fable is simply not allowed to debug it. Hoping Opus 5 has a bit more freedom.

Ah, I see the goal posts shifted. I thought the topic was whether an AI could "give you something truly original in the way many high-quality fictional stories are." Which was then followed by the idea that you cannot have "truly original" outputs unless you also have the corresponding original experiences.

Implication is that virtually none of the novels ever written which include wars are actually original works, since vanishingly few novelists have been in active wars.

Maybe originality just doesn't mean much then?

So only people who have fought in wars can write novels about fighting in wars?

Is there a link anywhere for a docs site for this? Really curious to know what "deep data sources" they have set up for the Native Global Market Data feature.

"The most amazing achievement of the computer software industry is its continuing cancellation of the steady and staggering gains made by the computer hardware industry."

— Henry Petroski

> If you are streaming in markdown and code and then doing syntax highlighting on this code in real time, then rendering it on the screen you are doing actual work.

You are really, really not. Not at LLM inference speeds at least. Frontier models output maybe 200 bytes per second on the fast end. I guarantee you that idle BSD box is still processing more than 200 bytes of whatever at any point in time. Streaming 200 bytes of LLM output through syntax highlighting, markdown rendering, and diff formatting, will still leave the box basically idle if done correctly. Claude Code has not done it correctly.