311–320 of 427 posts
"Why did you do this insane thing?"
"IDK, claude suggested it and it works."
When will people give up this archaic practice of sending patches over emails?
When enough people don't want to do it anymore. Feel free to step up, live with email patches, and add to the numbers of those who don't like it and say so. Why is it archaic if it works? I get there might be other ways to do patch sharing and discussion but what exactly is your problem with email as a transport? You might as well describe voice and ears as archaic!
Very old or old fashioned
Earlier quoted context omitted.
Seems like a fake problem. Who would sue QEMU for using AI-generated code? OpenAI? Anthropic?
Anyone whose code is in a used model's training set.* This is about future existential tail risk, not current risk. * Depending on future court decisions in different jurisdictions
Earlier quoted context omitted.
My company hired a new CTO and he asked chatgpt to write some lengthy documents about "how engineering gets done in our company". He also writes all his emails with chatgpt. I don't bother reading. Oddly enough he recently promoted a guy who has been fucking around with LLMs for years instead of working as his right hand man.
That's directly lethal, in a limited sympathy with engineers that don't immediately head for the exit sort of fashion. Best of luck
I think under current management immigrants have no chance of getting promoted.
Earlier quoted context omitted.
Quality contributions to OSS are rare unless the project is huge.
Historically the opposite of quality contributions has been no contributions, not net-negative contributions (random slop that costs more in review than it provides benefit).
The person got upset at me for saying I could not accept such a thing.
There's other examples.
Earlier quoted context omitted.
Had someone higher up ask about something in my area of expertise. I said I didn't think is was possible, he followed up with a chatGPT conversation he had where it "gave him some ideas that we could use as an approach", as if that was some useful insight. This is the same people that think that "learning to code" is a translation issue they don't have time for as opposed to experience they don't have.
A friend experienced a similar thing at work - he gave a well-informed assessment of why something is difficult to implement and it would take a couple of weeks, based on the knowledge of the system and experience with it - only for the manager to reply within 5 min with a screenshot of an (even surprisingly) idiotic ChatGPT reply, and a message along the lines of "here's how you can do it, I guess by the end of the…
— How about you do it, motherfucker?! If it’s that simple, you do it! And when you can’t, I’ll come down there, push your face on the keyboard, and burn your office to the ground, how about that?
— Well, you don’t have to get mean about it.
— Yeah, I do have to get mean about it. Nothing worse than an ignorant, arrogant, know-it-all.
If Harlan Ellison were a programmer today.
Earlier quoted context omitted.
Can you show these 3 things to us?
For some reason these fully functional ai generated projects that the authors vibe out while playing guitar and clipping their toenails are never open source.
Earlier quoted context omitted.
Mine is. And it is awesome: https://github.com/banagale/FileKitty The most recent release includes a MacOS build in a dmg signed by Apple: https://github.com/banagale/FileKitty/releases/tag/v0.2.3 I vibed that workflow just so more people could have access to this tool. It was a pain and it actually took time away from toenail clipping. And while I didn't lay hands on a guitar much during this period, I did manage to…
This app is concatenating files with an extra line of metadata added? You know this could be done in a few lines of shell script? You can then make it a finder action extension so it’s part of the system file manager app.
It began as an experiment in AI-assisted app design and a cross-platform “cat these files” utility.
Since then it has picked up:
- Snapshot history (and change flags) for any file selection
- A rendered folder tree that LLMs can digest, with per-prompt ignore filters
- String-based ignore rules for both tree and file output, so prompts stay surgical
My recent focus is making that generated context modular, so additional inputs (logs, design docs, architecture notes) can plug in cleanly. Apple’s new on-device foundation models could pair nicely with that.
The bigger point: most AI tooling hides the exact nature of context. FileKitty puts that step in the open and keeps the programmer in the loop.
I continue to believe LLMs can solve big problems with appropriate context and that intentionality in context prep is important step in evaluating ideas and implementation suggestions found in LLM outputs.
There's a Homebrew build available and I'd be happy to take contributions: https://github.com/banagale/FileKitty
Earlier quoted context omitted.
Anyone whose code is in a used model's training set.* This is about future existential tail risk, not current risk. * Depending on future court decisions in different jurisdictions
Again, seems so implausible that it's not worth worrying about.
IP disputes aren't trivial, especially for shoestring-funded OSS.