Viewing profile — sroerick

It would be extremely interesting to me if the usgov produces a model which honors copyright and is also useful. This would give them extreme leverage over the labs, who may be vio…

They are both the differentiator. AI previously provided speed but not quality. As soon as quality reached an acceptable threshold, the speed became the reigning factor. In my opin…

Solution is simple, run slower!

Even if you're sour on American exceptionalism, this seems like a valid and good product to me, both from a privacy standpoint and from an ethical labor standpoint? Am I the only o…

My approach has been an interpreted Lisp running on a web server backend and it basically does everything described here

Pi and XMPP is excellent

I stuck a lisp interpreter inside a web server and its a pretty cool pattern. I do have a basic harness but I'm still kind of just using the REPL from an external agent over REST, …

I'm curious to learn more about your experiences here, what you've learned, if you've enjoyed using the REPL with agents

Isn't React specifically an attempt to build an immediate mode UI on top of the DOM?

Isn't that literally React? I find it so immeasurably funny that in his effort to simplify code and invent immediate mode UI, Casey Muratori accidentally invented React

My understanding is that js_of_ocaml has been around longer and likely has a stronger ecosystem, but Melange was designed more specifically to play nice with the JS ecosystem.

I honestly don't really get MCPs. They're like all the bad design choices of LSP multiplied by 5

So I'm very seriously considering making my language indentation based. You're saying you wouldn't like that?

They definitely are - but also people are using them pretty extensively for work. So ultimately you can't really fake "is it good". But there's no real measurements of that when a …

I can't really understand what this dude says but it sounds like he called Open AI and Anthropic a bunch of commies and said they're going to war for Enterprise AI

I'm going pretty deep on Lisp on accident - can anybody give me more context on this?

lol

lol you're talking to the guy who coded it

Crazy how much things have shifted since a few years ago

Sir, it's 3X cheaper on coding. 3X cheaper in any industry is earth shattering. 10% is significant. 3X is really big.

Okay, I think that's fair, but I'm not convinced there's anybody actually doing large amounts of compute on office tasks? Do you know anybody? Can you point to anybody publicly doc…

I find them to be about comparable, but I use them both for coding tasks and I'm happy with each. I like K3

I was actually shocked to see that much improvement on GLM 5.2. I am getting pretty great rates in GLM5.2 right now and I'm extremely happy with the output. I have found Kimi to be…

Not to mention - If you switch the view to "coding tasks" on this website: Kimi K3: $3.18 per task GLM 5.2: $6.51 per task GPT 5.6 Sol: $7.02 per task Opus 5: 8.23 per task Fable: …