Why not have the LLM go straight to LLVM IR? What would a program look like when you remove all (or most) of the layers of abstraction needed by humans? Or are LLMs too contaminated by the training data to do this? I almost wish I could try this.
I have an experimental project where I was asking various LLMs/tools (ChatGPT, Cursor, Google, Lovable) to implement an old game for me. They all failed spectacularly in various ways. For example, when trying to debug an issue, got into a loop making the same sets of mistakes over and over again. Or "solving" a problem by removing an implementation, or claiming something was fixed but all it did was stop checking the error. It's been disastrous.
I've had better success with LLMs as just a supercharged search engine, but only after I went through several rounds of adding instructions to prevent hallucinations and lies.
I also asked one to create a tutorial for me to follow in regards to a complicated game I'm trying to understand. It lied repeatedly, making up features and telling me to set options that just didn't exist.
My boss loves LLMs and claims it really improved his productivity, but the stuff he's talking about is JS stuff. When he (and I as well) try to use it with Java the viability of the results drops off dramatically.
As I commented in the other post, it killed mine at work, because my boss is pushing "AI" really hard on the devs. Fortunately, he's now seeing enough evidence to counteract the hype, but it's still going to be present and dragging down my work. But it my off time, I only experiment with LLMs to see if they're getting better. Spoiler alert: they aren't, at least not for the kind of things I want to do.
I'm 62, and it's had the opposite effect on me. I've never stopped loving writing code, learning new things, trying random stuff, etc. I code all day, and spend more time playing with stuff in the evenings (the main difference is I'm sipping some scotch while I do it). Having to use LLM's at work has sucked most of the joy out of my work. Fighting with them, keeping them on track, catching hallucinations before they go too far, wasted effort...it's exhausting me like nothing else in my 40+ year career.
> No, setting an agenda is a way to give people a chance to prepare for a meeting and to keep the meeting on track. A meeting with an agenda sent out ahead of time is far more efficient than a meeting where people just show up and think of things to chat about.
I go so far as to reject meetings that don't have an agenda specified. Either that, or (if I'm feeling generous) reply to the meeting invite with a "Maybe" and ask specifically for an agenda.
Speaking as someone who experiences this, it's because you're tuned out. It's non-technical, and you fundamentally don't care. You haven't invested (wasted) the time to learn all of this trivia because you don't feel it's pertinent to your actual job function and getting real work done. In many ways, you're probably 100% correct. You're a tactical, hands-on keyboard type, and all of this high level strategy means exactly nothing to how you do your day-to-day job. It's the flavor of the month, and the next time a new executive shuffles in, they'll lift their leg and spray out another "transformation strategy" to mark their territory. All while you still have to get stuff done.
The problem is that the non-technical people think this stuff is important. They're so invested that they feel the need to call big meetings and talk about it, instead of letting you get actual work done. And they notice that you don't care about it. So, be aware that this could hinder your career.
When the company I work at decided to become "agile", it all went to hell. Every "innovation" just makes it more and more miserable to work there. Standups are a real pain, and I have yet to see any value whatsoever from this daily ritual that interrupts key work time.