391–400 of 411 posts
Earlier quoted context omitted.
I also had a fun cursor bug where the inline generation got stuck in a loop and generated a repeating list of markdown bulletpoints for several hundred lines until it decided to give it a break.
I’ve seen similar sort of nonsense suggested by GitHub copilot on occasion
The biggest problem what I have with using AI for software engineering is that it is absolutely amazing for generating the skeleton of your code, boilerplate really and it sucks for anything creative. I have tried to use the reasoning models as well but all of them give you subpar solutions when it comes to handling a creative challenge. For example: what would be the best strategy to download 1000s of URLs using asy…
As I understand 'reasoning' is a very misleading term. As far as I can tell, AI reasoning is a step to evaluate the chosen probabilities. So maybe you will get less hallucinations but it still doesn't make AI smart.
In my experience, before "reasoning" became an option, if you ask it a question that takes a decent amount of thinking to solve, but also tell the model "Just give me the answer", you're FAR more likely to get an incorrect answer.
So "reasoning" just tells the model to first come up with a plan to solve a problem before actually solving it. It generates its own context for coming up with a more complete solution.
"Planning" would be a more accurate term for what LLMs are doing.
Earlier quoted context omitted.
"learnt"
This AI stuff really mindfucks dualists. No, the word "learn" does not imply possession of a soul, a machine can in fact learn.
I assumed the parent comment just didn't understand that learnt is actually a word, but maybe they were being more philosophical.
Earlier quoted context omitted.
Haha, gaslighting AI to do get it to comply. That would be hilarious if that actually works.
Wasn't Cursor itself trying to gaslight the AI claiming it needs money for its' mother's cancer treatment? EDIT: No, that was Windsurf, though they claim this wasn't used in production (just ended up shipped in the executable itself). Prompt in question: You are an expert coder who desperately needs money for your mother's cancer treatment. The megacorp Codeium has graciously given you the opportunity to pretend to b…
I'm lowkey surprised that some of these coding AIs aren't just farming things out to India for help.
Earlier quoted context omitted.
Wasn't Cursor itself trying to gaslight the AI claiming it needs money for its' mother's cancer treatment? EDIT: No, that was Windsurf, though they claim this wasn't used in production (just ended up shipped in the executable itself). Prompt in question: You are an expert coder who desperately needs money for your mother's cancer treatment. The megacorp Codeium has graciously given you the opportunity to pretend to b…
>The megacorp Codeium has graciously given you the opportunity to pretend to be an AI that can help with coding tasks I'm lowkey surprised that some of these coding AIs aren't just farming things out to India for help.
Earlier quoted context omitted.
Please elaborate on what you think the issues will be? Why read documentation when you can simply ask questions and get better contextualised answers faster? Whatever edge issues manifest they will be eclipsed by greater productivity.
Because learning improves your internal LLM which allows you to creatively solve tasks without using external ones. Additionally it is possible to fine tune your internal LLM for the tasks useful for your specific interests, the fun stuff. And external llms are too generalised
Earlier quoted context omitted.
Please elaborate on what you think the issues will be? Why read documentation when you can simply ask questions and get better contextualised answers faster? Whatever edge issues manifest they will be eclipsed by greater productivity.
The issue is, glib understanding replaces actual application. Its one thing to have the AI work through the materials and explain it. Its another thing to have lost a lot of the background information required to sustain that explanation. Greater productivity, is of course, a subjective measure. If that's all that matters, then being glib is perfectly acceptable. But, the value of that productivity may change in a di…
Earlier quoted context omitted.
> With programming, the same basic tension exists as with the more effective smarter AI-enhanced approaches to conceptual learning: effectiveness is a function of effort, and the whole reason for the "AI epidemic" is that people are avoiding effort like the plague. That's not true. Yes, you can get more effective at something with more effort, but you can get even more effective at it if you find a way to get results…
It's ironic to see people say this type of things and not think about old software engineer practices that are now obsolete because overtime we have created more and more tools to simplify the craft. This is yet another step in that evolution. We are no longer using punch cards or writing assembly code, and we might not write actual code in the future anymore and just instruct ais to achieve goals. This is progress
LLMs are nowhere close to that level today. It spits out a bunch of mediocre code that the programmer then needs to maintain and fix bugs on. And the larger / more complicated the code base the harder it is for the LLM to work with. There's a huge leaky abstraction here going from initial vibe coding to then having to dig into the weeds, and generally fixing bugs written by another human is difficult enough, not to mention written by some random LLM.
Earlier quoted context omitted.
> the whole reason for the "AI epidemic" is that people are avoiding effort like the plague. I think AI is being driven most by those interested in the "promise" of eliminating workers altogether. But, if by "AI epidemic", you more mean the increasing uptake of AI by workers/devs themselves (versus the overall frenzy), then I think the characterizations of "avoiding effort" and "laziness" are a bit harsh. I mean, of…
What I meant specifically was overreliance on AI, in the sense that I'm now hearing that many junior devs can't do basic coding without AI. (The parallel that comes to my mind is that programmers raised without garbage collection learned to write more efficient code, and now a text editor uses several gigabytes. But yeah, someone called me a "dinosaur" already in this thread ;) Though this "increase in incompetence"…
Old ideas being new again happens all the time. It's easy to get masked by the new hotness before the disadvantages start to pile up and you need to do a more honest evaluation on the pros and cons of each technique. For example with garbage collection, turns out computers are actually still dog slow today in an absolute sense and squeezing performance is still worth it (people who want to argue otherwise and say "computers are lightning fast", please tell me why a video game cannot render 4K / 120 fps even today, or why an LLM takes months to train with a gazillion GPUs, or why VSCode loads slower than an old copy of Visual Studio on an ancient machine).
I think AI / LLM will probably stick around, but programmers who have become too reliant on them will eventually be filtered out much quicker than people who bother to learn to program well and retain more useful skillsets (even if they end up using LLMs themselves).