alt Hacker News>AI is certainly not reliable enough for me to jeopardize the quality of my work by using it heavily.
I mean this in sincerity, and not at all snarky, but - have you considered that you haven't used the tools correctly or effectively? I find that I can get what I need from chatbots (and refuse to call them AI until we have general AI just to be contrary) if I spend a couple of minutes considering constraints and being careful with my prompt language.
When I've come across people in my real life who say they get no value from chatbots, it's because they're asking poorly formed questions, or haven't thought through the problem entirely. Working with chatbots is like working with a very bright lab puppy. They're willing to do whatever you want, but they'll definitely piss on the floor unless you tell them not to.
Or am I entirely off base with your experience?
Replies
> have you considered that you haven't used the tools correctly or effectively?
The problem is that this comes off just as tone-deaf as "you're holding it wrong." In my experience, when people promote AI, its sold as just having a regular conversation and then the AI does thing. And when that doesn't work, the promoter goes into system prompts, MCP, agent files, etc and entire workflows that are required to get it to do the correct thing. It ends up feeling like you're being lied to, even if there's some benefit out there.
There's also the fact that all programming workflows are not the same. I've found some areas where AI works well, but a lot of my work it does not. Usually things that wouldn't show up in a simple Google search back before it was enshittified are pretty spotty.
AI is okay (not great) at generating low- to mid-skill code. If you are working in a high-skill software domain that requires pervasive state-of-the-art or first-principles implementation then AI produces consistently terrible code. It frequently is flatly incorrect about esoteric technical details that really matter.
It can't reason from first principles and there isn't training data for a lot of state-of-the-art computer science and code implementations. Nothing you can prompt will make it produce non-naive output because it doesn't have that capability.
AI works for a lot of things because, if we are honest, AI generated slop is replacing human generated slop. But not all software is slop and there are software domains where slop is not even an option.
[dead]
It would be helpful if you would relate your own bad experiences and how you overcame them. Leading off with "do it better" isn't very instructive. Unfortunately there's no useful training for much of anything in our industry, much less AI.
I prefer to use LLM as a sock puppet to filter out implausible options in my problem space and to help me recall how to do boilerplate things. Like you, I think, I also tend to write multi-paragraph prompts repeating myself and calling back on every aspect to continuously hone in on the true subject I am interested in.
I don't trust LLM's enough to operate on my behalf agentically yet. And, LLM is uncreative and hallucinatory as heck whenever it strays into novel territory, which makes it a dangerous tool.