That's only part of the problem. Yes, JavaScript is a fragmented clusterfuck. Typescript is leagues better, but by no means perfect. Still, that doesn't explain why the LLM can't recall that I'm using Yarn while it's processing the instruction that specifically told it to use Yarn. Or why it tries to start editing code when I tell it not to. Those are still issues that aren't specific to the language.
But it still manages to fuck it up.
I've been experimenting with using Claude's Sonnet model in Copilot in agent mode for my job, and one of the things that's become abundantly clear is that it has certain types of behavior that are heavily represented in the model, so it assumes you want that behavior even if you explicitly tell it you don't.
Say you're working in a yarn workspaces project, and you instruct Copilot to build and test a new dashboard using an instruction file. You'll need to include explicit and repeated reminders all throughout the file to use yarn, not NPM, because even though yarn is very popular today, there are so many older examples of using NPM in its model that it's just going to assume that's what you actually want - thereby fucking up your codebase.
I've also had lots of cases where I tell it I don't want it to edit any code, just to analyze and explain something that's there and how to update it... and then I have to stop it from editing code anyway, because halfway through it forgot that I didn't want edits, just explanations.
I can envision a system where an LLM becomes one part of a reasoning AI, acting as a kind of fuzzy "dataset" that a proper neural network incorporates and reasons with, and the LLM could be kept real-time updated (sort of) with MCP servers that incorporate anything new it learns.
But I don't think we're anywhere near there yet.
The (presumably) bot that posted it is now extremely banned from the community.
Yep. And to think I used to admire him. I've had some modest success as a published science fiction and fantasy writer, and I specifically cited him as inspiration for one of my published stories.
Wish I could take it back.
Came here for this one. Fuck "separate the art from the artist." I will never read one of his books again.
The message is clear: Do not come to the United States as a tourist. Do not spend your money in the United States. Do not support businesses that operate from the United States. Our borders are closed, our economy crumbling, our government falling to fascism, and our culture dominated by a relatively small minority of aggressively ignorant morons.
Don't come. We've gotten unfathomably stupid over here, and it's no longer safe.
Suggesting that a war should be waged against the democratically-elected government of the United States seems... Well, it seems kinda treason-y to me. Just a smidge.
Hey, uhh, Europe? Can we talk?
Look, I know the way the left has been handling immigration has you upset, but could you please take a closer look at the absolute freaks you're electing today?
I mean, just take a good look at the United States, circa 2017 through 2020. Did we look like electing an absolute freak worked out for us? Did it fix our own immigration problems? Did it make electing your own Donald Trumps look like a good idea?
My son is trans. Please vote for Joe Biden so he can have the protections he needs and I don't have to stay up at night worrying about him.
Revolting that this is now a "crime."
Well, technically, yes. You're right. But they're a specific, narrow type of neural network, while I was thinking of the broader class and more traditional applications, like data analysis. I should have been more specific.