>Can we make an entirely new programming language?

This is trivial in a few hours with Claude Code

I am designing one, aimed at Claude Code and other AI Coding Agents, and getting the first version lex/parser/compiler was an afternoon project. It was initially a TypeScript toolchain generating TypeScript code.

I keep adding things here and there, a couple hours everyday. Then after about a week I decided to switch the toolchain from TypeScript to Rust, how much work? A 5 minute planning session and a ~20 minutes implementation phase.

Trivial stuff indeed.

Stars have become completely meaningless in the last year or two. It's a shame, because having a few thousand Github stars used to be a really big deal, and was a quality marker for libraries that had reached a level of maturity and production grade. Now it's just social media bot driven nonsense.

The game is all about content now. Forget software. Games, movies, books, music, etc. Things that people will always want regardless of how much there already is. Look at the success of AI slop authors and YouTube channels. That's our future.

I mean it makes sense, all you really need are cows and wives to turn sunshine into children. What more could a man need.

A lot of grass land for the cows.

>There's a pretty popular project https://www.conductor.build that looks pretty similar, was there anything that you were missing from that one (if you were aware of it)?

There's probably a dozen new ones of these per week. It's the obvious idea at this point. Eventually the model providers will do it, and that's what we'll all use.

Yeah probably. Then again, opencode is not provider-specific && I prefer it to claude code (though I do use CC for personal stuff outside work because $$) and I missed their zen black or whatever the opencode $200 is.

My dream is a more indie world, so I'm glad to see you building too.

But we don't all need to share our personal, custom agent setups like we are going to be the new sliced bread. I have my own, I think it's great and better than most out there, but I'm not going to Show HN it amidst the Claw HN submissions, if ever. I generally link to interesting pieces in comments when someone asks how I implement a particular feature.

My custom agent setup is a component in a larger developer "swiss army knife" I have been building for 8ish years. Same handle on github if your are curious, project is "hof" with a rename imminent.

The agent part is built on ADK, which I believe is relatively on par with opencode, which I also see is highly regarded. The multi-workspace feature is built on Dagger and the VS Code virtualized FS and SCM interfaces. I can browse or get a diff at any turn-to-turn span, make edits that go right back in.

This is not a helpful comment, please see the Guidelines linked at the bottom of the page.

> Eventually the model providers will do it, and that's what we'll all use.

Haven't they already, to varying degrees?

Does anyone have experience with professional Brightscript dev? I'm fascinated by it as a web developer looking to find a new niche, but it's like impossible to get into. Seems like every major streaming platform is going to need some experts for the foreseeable future given the install base of Roku at this point, and LLMs are horrible at it.

This is precisely how the newly released Claude agent teams work.

Well this is probably why KFC chicken has become inedible. I don't know what they are doing to those things but they are practically a different species at this point. I love fast food and eat it all the time, but KFC "chicken" is just a disgusting grey slimey pile of garbage.

has it ever not been inedible?

>has it ever not been inedible?

No restaurant ever makes it big without being good to begin with. I remember the chicken being on par with any other fast food as a kid, they just fell off hard in the 2000s. I'm really not sure who is still buying their buckets.

To be fair, KFC "made it big" 3/4 of a century ago.

>"Somewhere along the way, too many of us learned to sand off our weird edges, to preemptively remove anything that might make someone uncomfortable or make us seem difficult to be around."

As an adult you learn that showing your true self can be dangerous in an environment where you don't know who can be trusted. We don't get the allowance of children to be weird or awkward. Others are gunning for us, and looking for any possible weakness. One wrong impression can drastically affect your life. So you curate yourself in a way that keeps your personality for those who can be trusted to accept and understand it, and others may see that as boring until they've been let in. It's just maturity; you have to earn the right to have me let my guard down around you.

Dangerous how?

You can simply...not care.

Unless it's a context with a minimum required codex such as work.

But in your relationships, if you want to have meaningful ones, you need to find those where you can be yourself.

It's better to have 1 or 2 true friends (hell, most people don't have that many, you're lucky if you do) than knowing and being popular among dozens for a filtered/fake persona you built so others like you.

Doesn't almost every situation have a minimum required codex? Sure, you should be yourself with your friends. But if they are already your friends, then you are likely already interesting enough. I thought the article was more about how to be interesting to people who don't already know you.

Well said, this was similar to what I was thinking while reading this. Acting in a completely unfiltered way can get you into fights, arrested, or worse.

Tailwind is crucial. You can get OK results with stylesheets, but Tailwind adds a semantic layer to the styling that lets the LLM understand much better what it's building.