LLMs are using the corpus of existing software source code.
Most software source code is just North of unworkable garbage.
Garbage in, garbage out.
Human coders are still better than LLMs
321–330 of 762 posts
Re: Human coders are still better than LLMs
#322LLMs can be very creative, when pushed. In order to find a creative solution, like antirez needed, there are several tricks I use: Increase the temperature of the LLMs. Ask several LLMs, each several time the same question, with tiny variations. Then collect all answers, and do a second/third round asking each LLM to review all collected answers and improve. Add random constraints, one constraints per question. For e…
Definitely a lot to be said for these ideas, even just that it helps to start a fresh chat and ask the same question in a better way a few times (using the quality of response to gauge what might be "better"). I have found if I do this a few times and Gemini strikes out, I've manually optimized the question by this point that I can drop it into Claude and get a good working solution. Conversely, having a discussion with the LLM about the potential solution, letting it hold on to the context as described in TFA, has in my experience caused the models to pretty universally end up stuck in a rut sooner or later and become counterproductive to work with. Not to mention that way eats up a ton of api usage allotment.
Re: Human coders are still better than LLMs
#323Earlier quoted context omitted.
> hallucinate whole APIs for D3 on multiple occasions, which should be really well represented in the training sets With many existing systems, you can pull documentation into context pretty quickly to prevent the hallucination of APIs. In the near future it's obvious how that could be done automatically. I put my engine on the ground, ran it and it didn't even go anywhere; Ford will never beat horses.
It's true that manually constraining an LLM with contextual data increases their performance on that data (and reduces performance elsewhere), but that conflicts with the promise of AI as an everything machine. We were promised an everything machine but if we have to not only provide it the proper context, but already know what constitutes the proper context , then it is not in any way an everything machine. Which me…
>Which means it's back to being a very useful tool, but not the earth-shattering disruptor we hoped (or worried) it would be.
Yet?
Re: Human coders are still better than LLMs
#324This matches my experience. I actually think a fair amount of value from LLM assistants to me is having a reasonably intelligent rubber duck to talk to. Now the duck can occasionally disagree and sometimes even refine. https://en.m.wikipedia.org/wiki/Rubber_duck_debugging I think the big question everyone wants to skip right to and past this conversation is, will this continue to be true 2 years from now? I don’t kno…
It's a damning assertive duck, completely out of proportion to its competence. I've seen enough people led astray by talking to it.
Some humans are the same.
Re: Human coders are still better than LLMs
#325I suspect humans will always be critical to programming. Improved technology won't matter if the economics isn't there. LLMs are great as assistants. Just today, Copilot told me it's there to do the "tedious and repetitive" parts so I can focus my energy on the "interesting" parts. That's great. They do the things every programmer hates having to do. I'm more productive in the best possible way. But ask it to do too…
Sure, it's just that the era of super high paying programming jobs may be over.
And also, manufacturing jobs have greatly changed. And the effect is not even, I imagine. Some types of manufacturing jobs are just gone.
Re: Human coders are still better than LLMs
#326Earlier quoted context omitted.
It's a damning assertive duck, completely out of proportion to its competence. I've seen enough people led astray by talking to it.
Same here. When I'm teaching coding I've noticed that LLMs will confuse the heck out of students. They will accept what it suggests without realizing that it is suggesting nonsense.
This was what promptly led me to turning off Jetbrains AI assistant: the multiline completion was incredibly distracting to my chain of thought, particularly when it would suggest things that looked right but weren't. Stopping and parsing the suggestion to realize if it was right or wrong would completely kill my flow.
Re: Human coders are still better than LLMs
#327Earlier quoted context omitted.
It's a damning assertive duck, completely out of proportion to its competence. I've seen enough people led astray by talking to it.
Some humans are the same.
We also don't aim to elevate them. We instead try not to give them responsibility until they're able to handle it.
Re: Human coders are still better than LLMs
#328Earlier quoted context omitted.
I would argue that they are never led astray by chatting, but rather by accepting the projection of their own prompt passed through the model as some kind of truth. When talking with reasonable people, they have an intuition of what you want even if you don't say it, because there is a lot of non-verbal context. LLMs lack the ability to understand the person, but behave as if they had it.
> When talking with reasonable people When talking with reasonable people, they will tell you if they don't understand what you're saying. When talking with reasonable people, they will tell you if they don't know the answer or if they are unsure about their answer. LLMs do none of that. They will very happily, and very confidently, spout complete bullshit at you. It is essentially a lotto draw as to whether the answ…
You can use prompts to fix some of these problematic tendencies.
Re: Human coders are still better than LLMs
#329Earlier quoted context omitted.
It's true that manually constraining an LLM with contextual data increases their performance on that data (and reduces performance elsewhere), but that conflicts with the promise of AI as an everything machine. We were promised an everything machine but if we have to not only provide it the proper context, but already know what constitutes the proper context , then it is not in any way an everything machine. Which me…
>Which means it's back to being a very useful tool, but not the earth-shattering disruptor we hoped (or worried) it would be. Yet?
That could require another breakthrough. Or ten more.
Fun to consider but that much uncertainty isn't worth much.
Re: Human coders are still better than LLMs
#330Earlier quoted context omitted.
They will also not be offended or harbor ill will when you completely reject their "pull request" and rephrase the requirements.
They will also keep going in circles when you rephrase the requirements, unless with every prompt you keep adding to it and mentioning everything they've already suggested that got rejected. While humans occasionally also do this (hey, short memories), LLMs are infuriatingly more prone to it. A typical interaction with an LLM: "Hey, how do I do X in Y?" "That's a great question! A good way to do X in Y is Z!" "No, Z…
Which LLMs and which versions?