[mordymoop]

I am frankly tired of seeing this kind of post on HN. I feel like the population of programmers is bifurcating into those who are committed to mastering these tools, learning to work around their limitations and working to leverage their strengths… and those who are committed to complaining about how they aren’t already perfect Culture Ship Minds.

We get it. They’re not superintelligent at everything yet. They couldn’t infer what you must’ve really meant in your heart from your initial unskillful prompt. They couldn’t foresee every possible bug and edge case from the first moment of conceptualizing the design, a flaw which I’m sure you don’t have.

The thing that pushes me over the line into ranting territory is that computer programmers, of all people, should know that computers do what you tell them to.

[rglover]

> computer programmers, of all people, should know that computers do what you tell them to.

Right. The problem isn't that the tool isn't perfect, it's that you get a lot of excitable people with incentives pretending that it is or will soon be perfect (while simultaneously scaring non-technical people into thinking they'll be replaced with a chat bot soon).

There are certainly luddite types who are outright rejecting these tools, but if you have hands-on, daily experience, you can see the forest for the trees. You quickly realize that all of the "omg this thing is sentient" or "we can't let what we've got into the world, it's too dangerous" fodder like the Google panic memo are just covert marketing.

[suddenlybananas]

>The thing that pushes me over the line into ranting territory is that computer programmers, of all people, should know that computers do what you tell them to.

are you claiming LLMs function like computer program instructions? like they clearly don't operate like that at all.

[mordymoop]

They are closer to being deterministic machines that comply exactly with your instructions, for better or worse, than they are to magical pixies that guess what you must’ve actually meant. The implicit expectation demonstrated by many in the “loudly disappointed in LLMs” contingent seems to be that LLMs should just know what you meant, and then blame them for not correctly guessing it and delivering it.

I think LLMs have uncovered what we have always known in this industry: that people are, by default, bad at communicating their intent clearly and unambiguously.

If you express your intent to an LLM with sufficient clarity and disambiguation, it will rarely screw up. Often, we don’t have time to do this, and instead we aim for the sweet spot of sufficient but not exhaustive clarity. This can be fine if you are experienced with that particular LLM and you have a good feel for where its sweet spot actually is. If you miss that target, though, the LLM will not correctly infer your intended subtext. This is one of the things that requires experience. In fact, even the “same” LLM will change in its behavior and capabilities as it undergoes fine tuning. Sometimes it will even get worse at certain things.

All of this is to say, of course, you’re right that it’s not a compiler. But I think people fail in their application of LLMs for much the same reason that novice coders fail to get compilers to guess what they intended.

[Dylan16807]

> They are closer to being deterministic machines that comply exactly with your instructions, for better or worse, than they are to magical pixies that guess what you must’ve actually meant.

If those are your only two reference points, yes they're closer to the former.

But the biggest problem is how much "pixie that does something you neither wanted nor asked for" gets mixed in. And I think a lot of the complaints you're saying are about lack of mind reading are actually about that problem instead.

[dambi0]

What part of the comment makes you think they are claiming that?

[suddenlybananas]

The part I quoted? I don't really see how to interpret it any other way.

[dambi0]

Thanks, I’m not thinking clearly at all. I had it in my head that programming instruction are not the only way that a computer might do as it’s told. For example, if we delete a folder in a UI by accident we shouldn’t be surprised the folder is gone. But it doesn’t really quite fit the parent analogy. Sorry about that.

[bigstrat2003]

Nobody is complaining that LLMs aren't perfect Culture minds. People disagree with the premise that they are useful tools given their current capabilities. Your portrayal of those with whom you disagree is such a strawman that it might as well be set to a soy-vs-wojak meme.

[mordymoop]

They clearly are useful tools given their current capabilities. It just depends on what you’re using them for. You don’t use a screwdriver to drive nails, and you don’t go to HardwareNews to complain when your screwdriver isn’t working as a hammer.

I’m currently using them to port a client-side API SDK into multiple languages. This would be a pain in the ass time consuming task but is a breeze with LLMs because the exact behavior I want is clearly defined and relatively deterministic, and it’s also straightforward to test that I’m getting what I intend. The LLM thus gets done in 3 days what would take me 3 weeks (or more) to do by hand.

If the complaint is that it can’t do X, where X is something that would clearly require full AGI and likely true superintelligence — in this case expecting instantaneous, correct code that solves novel problems on the first try - then I have to insist that people are actually expecting Claude to be a Culture Ship Mind, implicitly. They just don’t realize that what they’re asking for his hard, which is itself a psychologically interesting fact, I suppose.

[simonw]

"People disagree with the premise that they are useful tools given their current capabilities."

I will argue the opposite of that forever. They're very evidently useful, if you take the time to learn how to apply them.

[satvikpendem]

Use uBlock Origin to block posts with the keywords you don't want in the title, like AI or LLM.

[antigeox]

> I am frankly tired of seeing this kind of post on HN.

You've been here since 2016 and this is the kind of posting that finally gets to you? How in the world have you avoided all the shitposts in the last decade? What is your secret?

[mordymoop]

It’s the fact that it’s the same thing over and over. The 100th case of “Well I had a bad experience using LLM for coding!” is not interesting.