This sounds like someone who hasn't used compilers for long. I remember plenty of fun compiler undefined behavior that had essentially non-deterministic outcomes. And actually using power tools in the real world is pretty uncertain, try running a straight starting cut with a multitool against wood grain and then come back and talk to me.
LLMs aren't remotely like compilers or power tools
51–55 of 55 posts
Re: LLMs aren't remotely like compilers or power tools
#52I've got to give the author credit, it seems like this is written without an LLM. But, there seems to be a lot that is arguable. For example, the article says "Natural language is the interface of last resort." But, is that actually true? Isn't the AI boom happening because N/L is truly available as an interface? Anyway, please keep writing and asking tough questions.
> the article says "Natural language is the interface of last resort." I wonder why he decided to express this thought in natural language though. Should have tried formalising it.
> It's fully general, but it's also furiously ambiguous. Humans fall back to natural language when no other more precise way to describe what we want is available to us, either because it doesn't exist or we don't know it comfortably. We draw diagrams and blueprints and write math equations for a reason!
Re: LLMs aren't remotely like compilers or power tools
#53This person is taking things too literally. By power tool we simply mean speeds up work. And by that definition LLMs are absolutely a power tool of epic proprtions! If you ever coded before LLMs existed its like night and day.
Also, if you want me to believe that LLMs have made you that much more productive, please share some links for useful things you've built recently using them. I'm thrilled if actual things can be made, but I haven't seen it yet.
Re: LLMs aren't remotely like compilers or power tools
#54Earlier quoted context omitted.
> the article says "Natural language is the interface of last resort." I wonder why he decided to express this thought in natural language though. Should have tried formalising it.
Original author here. Yes, if I had the capability of writing a computer program or a formal proof that could stand in for this essay full of opinions and metaphors and heuristics, I would have. > It's fully general, but it's also furiously ambiguous. Humans fall back to natural language when no other more precise way to describe what we want is available to us, either because it doesn't exist or we don't know it com…
But I wouldn't say that metaphors, heuristics, slight ambiguities, subtexts, are unnecessary and undesirable elements of language; I think they are probably productive, ans that they reflect what intelligence is and how it works. If you read Terrence Tao's chat with ChatGPT to understand the counterexample to the Jacobian Conjecture, it's a lot of formal math interspersed with dubitative formulas, suggestions, vague intuitions, mental images, imprecise quantifiers, etc., from both sides. Natural language does real work, it's not just a fallback.
Re: LLMs aren't remotely like compilers or power tools
#55Earlier quoted context omitted.
There's actually zero difference between a bottle of water and a river reservoir if you think about it.
I am just saying that people have been making these sorts of shallow dismissive comments about people who use different tooling since forever. I remember a college professor snided at students who didn't know how to use vi. In the same way that most people are no longer proficient in assembly, but it has not spelled doom for software engineering, some folks are now using AI tools, and it will probably be fine. The da…
It's not about different tools, it's about how the old tools are NOT obsolete either and have their place. One should still use them as well, even in conjunction with LLMs if one wishes to. (hell they could ask the llm to find the correct schema online and add that one comment at the top)