We had the Roamer, British school, very early 90's.

I remember programming a logo/turtle type thing on the BBC Micro, and then I think there was a way to copy the program on to the Roamer directly from the BBC. Or maybe we did it manually. But it was amazing to me, and I always felt sad we didnt use it more!

Stopped using them when I realized I had stopped seeing posts from my actual friends and family.

It’s mostly endless reels and ads now and I have to scroll for way too long before I see a post from someone I’m connected to/friends with. Bored of it all.

That's so true! Social networking apps stopped focusing on social networking a while ago.

Doesn’t load.

Just noticed this - fixing now!

I feel the same sometimes. I don’t see how this doesn’t lead to massive job losses. The thing we spent our lives/careers learning is now worth basically nothing in comparison.

AI is only going to get better and do more with less humans in the loop over time.

That said, I do also relate to the "coding was never the hard part"-type arguments, and much of my day is spent on the stuff in between writing code.. but still.

I see how it won't lead to massive job loss every day, idk. Now every idiot has a massive slop code cannon they can point at any working system and bombard it and we all have to sift through and find the nuggets and gems in the rough

Do we think that was necessary? What would have happened if OP had just asked it to rewrite and test/validate each piece as it went until everything is verified and complete?

My gut feeling is this is doing way too much, and it would've figured it out.

But we know, Bun was 535496 lines for $165000.

The whole point of this experiment was to try and make the rewrite as cheap as possible.

Oh no, bun had quite a bit of machinery: https://bun.com/blog/bun-in-rust#loops-that-write-review-cod...

True, the main problem is how to split the work. They decided to go file by file.

To be fair, I haven't try exactly "rewrite in Rust" prompt, but I cannot imagine for this to work.

converting code to more abstract and denser representations and then manipulating them makes sense to me. Finding better representations is like half of mathematics.

Is code being converted to / represented in maths that much more helpful for an LLM that deals in language primarily, by definition? I have no idea, interesting though!

Having the LLM run the proprietary app through ghidra (which I think even has an MCP now), would likely give it some useful clues too

First thought; this could be turned into a really cool password generator

Had a moment of nostalgia and started building an IRC client for macOS. It’s totally free/open source. And has been fun to customize / add the features I like to see while avoiding the ones I don’t.

https://github.com/richstokes/Netsplit

Idea: Support providing it the URL to your own / arbitrary git repo, so you can see it type out whatever code you like :-)

Beat you to it! :) Hit the "Load from GitHub" button and type in your repo~

Small caveat: the only current limitation is that it has to be public.

EDIT: Oh I see what you're getting at. Like being able to point to any *.git repository such as from a gitea server, etc.? That's a good idea thanks for the suggestion!

If the AI could understand the save file format for Minecraft, it could manipulate that

There are methods to do custom generation in of itself, so should be possible for AI to write a mod in the same vein as current world generation mods.