Hacker News Reader

Comment by _ea1k | Hacker News Reader

> It was definitely useful for making sure I was doing it the correct way, kind of like have an expert on call for any questions.

I've found it to be shockingly good at this. I end up asking a lot of questions like, "what is the best directory structure for a project on {foo} platform?" or "What is the idiomatic way to do {x} in {language y}?" It has the advantage of having seen lots of projects in every language, and for some questions that automatically leads to a good answer.

View on HN

Be careful and don't trust all it says. Sometimes it invents API functions which are not there, or doesn't see existing. And always very confident till you point it.

And then it’s like, “thank you for telling me about this, I’ll remember that for next time,” which is how a human ought to respond but not how ChatGPT actually learns.

Hah, yeah that's so frustrating. It's memory is reset every time you start a new conversation, but it doesn't make that at all clear to people.

It also resets inside a single conversation if you go beyond a certain number of tokens, and as far as I know there is no warning whatsoever to the user when it happens.

The obvious next thing to try would be to continuously fine tune the model on these conversations, so it actually fulfills the promises most of these models make about "learning continuously". I haven't yet seen any actual implementations of this, though. I'm sure someone's tried it, I wonder how it went.

Which models make promises about "learning continuously"?

I’ve had statements along that line from Bing, dolphin2.1 and I think maybe Wizard Vicuna.

I'm finding that code is the area where hallucinations matter the least... because if it hallucinates an API function that doesn't exist, the mistake becomes apparent the moment you actually try to run it.

It's like having an automated fact checker! I wish I had the same thing for the other kinds of output it produces.

It will, however from time to time insert lines and variables that do nothing, but could result in bugs or confusion if not removed. I’ve encountered these hallucinations a few times. Overall, I agree with your sentiment, but I think it’s important to note that running isn’t always the indicator or correctness we think it to be.

You're still supposed to read it, like you hopefully wouldn't blindly paste a big code block from SO. A useless/unused line or variable doesn't seem that hard to spot?

Of course, but ease of detection can vary relative to the complexity of the code being returned. GPT-4, correctly prompted, can produce some pretty complicated stuff. But it also hallucinates in ways that are more subtle than one might think. The example I’m thinking of, it created an unused variable in a set of fairly complex ML training set up scripts that I mostly caught because I was familiar with all the proper inputs. But the unused variable was quite plausible if you were not familiar, new to the domain etc.

Compilers automatically detect unused variables. Unused variables are the last of your problems. You should be far, far more worried about all the misused variables.

Don't IDEs highlight variables that aren't read/written to?

In this case “unused” might mean declaring or initializing a variable and then assigning or reassigning a value to it later. In this case, it is technically used, so most linters won’t pick that up. But it actually does nothing so it’s wasted cycles.

No decent compiler would waste a cycle on that.

I've noticed some other funny things, maybe harmless but undesirable.

One example was really really hard to spot. Once I queried GPT 3.5 for a function to do X, and it did pretty well, when I looked closer though, it had wrapped 90% of the code in an unnecessary if statement. I looked at the code an thought something was off until I realized.

My point here is, if that was easy to spot, who knows what else people are missing because even in a simple case, unless you're actually trying to spot issues, you likely won't see them.

If it imagines a function it's fine. You can fix it in one prompt. But when it doesn't see it may move in the wrong way and produce limited solution. And you wouldn't know.

You would know in a similar way to a colleague of yours having done this code the previous day, or you joining a company with legacy code. It either has tests or you can't really trust it anyway regardless. You can ask the AI to also write tests for you, inspecting tests is usually much faster than understanding all the nuances of the code.

> because if it hallucinates an API function that doesn't exist

Yes, absolutely agree.

And also I’m no fanboy but when it does this and I only notice because the code doesn’t run, half the time I’m thinking to myself that the API function really should exist because it’s so logical!

I see it all the time. Even more annoying is when the API exists, but in a different class or with different parameters and outputs than you need, and the model would claim it does exactly what you need right until the time you try to use it and discover it can't work in your case.

Often I find that the hallucinations is how the API or lib should have been if it was more sane. Maybe someone could turn this into a virtual API critique.

I always get the classic “It really depends on your use case and neither pattern is exactly better than the other” when asking gpt about programming patterns

Put something in your system prompt along the lines of "don't waffle"

it has such a completionist fetish, I have found it works much better when you basically tell it to pick a side and not go out of its way to be balanced.

Even when it says that it always continues with "but" and gives me an answer.

this is how exactly how i use gpt4, i find it very useful

I use Sourcegraph a lot for this when GPT can't get a satisfying answer.

Reply on news.ycombinator.com