[yid]

A lot of the value comes from follow-up questions. Imagine being able to interrogate a StackOverflow answer with new constraints and details. Not always correct, but in some cases, faster that typing in a new search term and parsing a screen full of links.

[ToucanLoucan]

But again, the AI doesn't know. It's going to search around the internet and probably take a closer look at what it already told you, but that's it. It takes a plethora of information and attempts to digest it into knowledge but it lacks the understanding with which to accomplish this task.

Unless I guess you train an AI on a given topic, like a few languages or a database or something. But given ChatGPT's apparent vulnerability to just making shit up, you'll have to call me skeptical if this has any real use.

[empath-nirvana]

GPT4 "knows" a lot more about most topics than any single human does. People have this idea that it absolutely needs to be perfectly correct at all times to be useful, but would never hold a human being to that standard.

How many times have you asked a co-worker about something and they gave you a convincing answer that was totally wrong? Did it make you stop asking co-workers for help?

[falsenapkin]

Coworkers answering wrong gets me to stop asking them for help, yes, especially if it's confident or they can't qualify uncertainty or I know their ratio of Q&A site visits vs 1st party docs visits is abysmal. There are even people I won't ask for help because they trust people that I don't trust.

Conversely, there are people who I will go to for topics that they are not the SME in, maybe their teammate even is, but I trust their ability to do quality research and intelligently interpret that research for case specific nuances. Like I'll go to the networking guy to talk about some DB thing because the DB guys are morons and live and die by junk SEO sites but the networking guy can think analytically and find the source of truth documentation and provide excerpts from it.

[ToucanLoucan]

I VERY much more trust a coworker to know things than I do this AI, especially given not just the subject of this thread, but the larger conversation around it. ChatGPT has a reputation already for just spewing out complete nonsense. Didn't Bing's implementation argue with someone about what freaking year it was not awfully long ago?

These chat bots "know" a shit ton and a half of stuff in that they are connected to the largest collection of knowledge known to man, the Internet. But "knowing" and "understanding" are two different things. The various search engines also "know" a ton about where to find things online, that doesn't mean they know shit about those things. And as we're seeing here: without the context to know that when someone wants an IP scanner, they want something good, that won't give their computer malware, that'll be reasonably priced or even open source, or even what platform, it just gives an answer based on a search.

You could just search for ip scanning software and gotten all the information BingGPT shared with the author of the piece.

And like, if you wanted to be charitable, you could say "well the author should've given more information about what they wanted" but again, that's not different from an existing search engine and more crucially: the AI didn't ask questions. Didn't ask for platform, how much they wanted to spend, if they preferred open source, or even something more general like what they were trying to accomplish. Nada. Just did a search, and reported results.

[TeMPOraL]

> Didn't Bing's implementation argue with someone about what freaking year it was not awfully long ago?

I'm sorry, but that's a stellar example of holding an LLM wrong. These models are frozen in time.

> But "knowing" and "understanding" are two different things.

Indeed, and that is a big part of misunderstanding. GPT-4 is, on many topics, closer to understanding than knowing (note that neither is a subset of the other). The conceptual patterns are there, even if sometimes are easy to accidentally overpower by the prompt, or by the sequence of tokens already emitted.

[ToucanLoucan]

> I'm sorry, but that's a stellar example of holding an LLM wrong. These models are frozen in time.

Y'all keep throwing out these gotcha statements that just make the technology you're trying to tell me is great seem more and more useless.

How can you even attempt to call something artificial intelligence if it doesn't even know the year it is!?

> Indeed, and that is a big part of misunderstanding. GPT-4 is, on many topics, closer to understanding than knowing (note that neither is a subset of the other). The conceptual patterns are there, even if sometimes are easy to accidentally overpower by the prompt, or by the sequence of tokens already emitted.

I don't think it's either understanding or knowing. Someone who knows something isn't going to spontaneously forget it because someone asked them a question incorrectly.

[TerrifiedMouse]

> Did it make you stop asking co-workers for help?

That specific unreliable coworker who doesn’t properly qualify that they aren’t completely certain … I believe for most people, yes.

We tend not to trust bullshitters.

[mrguyorama]

>How many times have you asked a co-worker about something and they gave you a convincing answer that was totally wrong?

Never actually. My coworkers have never told me something with confidence that they just made up. If they don't know an answer, they may provide hints and directions, but it will be clear they don't know.

[ChatGTP]

Maybe I just work with good people but I feel the same. Often we will verify things together but I’d say they never they just make things up.

[toofy]

> Did it make you stop asking co-workers for help?

i mean, in many circumstances, we absolutely stop asking them...

when i ask a trustworthy human a question, they will absolutely tell me if it is out their depths. they understand their own limits on around the subject and say so. and if they understand a little, they’ll help point towards people who would be a better authority on the subject.

that’s basic level human connection stuff.

if someone confidently gives you the wrong answer, refuses to know their own limits, and repeatedly leads you astray you don’t trust them after this do you?

[noAnswer]

> Did it make you stop asking co-workers for help?

One usually stops asking the bullshitter, yes.

[JumpCrisscross]

> the AI doesn't know. It's going to search around the internet and probably take a closer look at what it already told you, but that's it

F/k/a Putting a thing on the internet for randos to identify and explain. As long as it cites the LLM cites its sources, general questions in the form of "what is this" or "what's going on here" while you point to a page or an image or in a general direction are not well suited for search engines.

[radlad]

Because having the AI do it for you is faster than doing it yourself.

Not as accurate, but faster.

For some people - I am reluctant to say "for some use cases" - that's very appealing.

[ToucanLoucan]

I am dreadfully curious what use cases you're envisioning where a fast, bad/wrong answer is better for anything than a correct, slower answer.

Like hell, if that's the standard, I'll be ChatGPT. You won't need an outrageous graphics card to ask me a question and I'll get you an answer right away. It'll almost certainly be the wrong answer, and is just an ass-pulled guess, but if that's all you want, I'll setup a chat website for myself and start taking queries today. Then investors can give me 10 billion dollars.

[yid]

Here's my pet example...feel free to google around yourself on this.

Problem: I want an AWS CLI command line that requests a whole bunch of wildcard certificates from AWS Certificate Manager (ACM) for a TLD.

Ostensible solution: the AWS official docs have a small snippet to achieve this, BUT -- the snippet on the official page is inadvisable as it leads to a browser cert warning.

So I (skeptically) asked ChatGPT for a command line to achieve what I was trying to do.

Try 1: got basically the snippet from the AWS official docs (but with the inadvisable flag set to the _Correct_ value, strangely)

Prompt 2: please give me more best practice options

Try 2: get back a bunch of new CLI options and their meanings. 3 are useful. 1 is hallucinated. 1 is deprecated.

Prompt 3: keep going with more options

Try 3: 2 more useful new options, 2 more options I chose not to use

As a skeptic, the overall experience was much more efficient that googling around or even reading a manpage. I put it all on the fact that context is maintained between questions, so you don't have to repeat yourself when asking for clarifications.

[nonameiguess]

I'm kind of surprised this worked. Did you actually use the command you ended up with? I'm not even surprised because I think ChatGPT can't figure this out in principle, but because the data itself is poisoned. The top link on every web search I've ever used to AWS CLI commands is to documentation for v1, but v1 has been deprecated for years and the page usually begins with a statement telling you not to use it. Amazon's problem is they never remove old documentation from the web, so 90% of what you find for any given service is no longer correct.

[TeMPOraL]

> and the page usually begins with a statement telling you not to use it

This might be a big part of why GP's case works. The model (GPT-4) most likely understands the concept of documentation being deprecated, so the more often v1 docs say it, the stronger a semantic link between current and obsolete docs, and the more likely it is for ChatGPT to give you answer based on non-deprecated docs.

[yid]

> Did you actually use the command you ended up with?

Yes! Note that I had to use my domain knowledge to sift through the options and eliminate the garbage, but the experience was just _faster_ than repeated searches and digging through ad-laden garbage sites.

[airstrike]

this. in my experience, GPT-4 really shines for groking AWS commands, writing JavaScript code and helping me understand some errors when compiling my terrible Rust code

[nunez]

But what if you enjoy the hunt and building this by hand?

[verdagon]

Sometimes, having a quick, inaccurate, but easily-verifiable answer is better. For example, when you're trying to remember the name of that one function to call, or ideas on where to travel next month.

Also, not super relevant, but in e.g. combat situations one is often better off running now in any direction rather than pondering which direction is absolutely optimal for running from the lion. You'll know soon enough whether it was the right direction. There's probably a metaphor somewhere in there.

[empath-nirvana]

ChatGPT doesn't "almost certainly" give you a wrong answer (especially if you're not asking it math problems). The reason that it hallucinating sometimes is so bad is that it happens _rarely_. If it happened all the time, you'd never use it or trust it. It's just that it happens _enough_ that it's annoying to have to double check everything.

[latexr]

> It's just that it happens _enough_ that it's annoying to have to double check everything.

If you “have to double check everything”, what’s the point? Skip the AI and do the check you were going to do anyway.

[CamperBob2]

I am dreadfully curious what use cases you're envisioning where a fast, bad/wrong answer is better for anything than a correct, slower answer.

Almost anything related to software development. Any answer I get online, whether from Wikipedia or a Github search or a Stack Overflow question or anywhere else, will require careful study and adaptation before I can use it. There will inevitably be things about any given solution that don't apply to whatever I'm doing, or that will be out-and-out wrong. But does that mean I'd be better off without doing a search at all? Of course not.

Same with AI. It can point me in the right direction and save me a lot of trouble, but it can't (yet) do my job for me.

When it gets 10x better -- and I'm sure it will -- then that last part can be expected to change. Which is awesome.

Meanwhile, Stack Overflow and Wikipedia and Github aren't going to get 10x better, ever. Not without cross-pollinating with AI.

[Prickle]

I have an example where I used the Phind model and GPT4 in a mix. The goal was to get multiple iterations of the same code, written in different ways that I could iterate on.

I had this really annoying requirement to get multiple incompatible status codes, and output them in a consolidated human legible way.

So pretend I am using MSSQL, and I have 3 status code tables.

The status code integers are all slightly different. NEW is always 1, but "Completed" could be 5, 7 or 21 depending on table.

The actual "text" is an integer that can be linked to a Text table via the ID and Language name. But, due to the nuances being slightly different, each version can have a different ID. I can't just use DISTINCT on the text ids.

This is even more true when slight differences like "Complete" and "Completed" exist.

So I need to use UNION, to 'combine' multiple unrelated status code tables.

Then I need to get the language text, and SELECT DISTINCT (or something similar) per language.

Then that needs to be outputted as a drop down for the user.

Then, I have to use that as a other, separate input for another SQL query.

To say "using fast, slightly inaccurate GPT code" was faster than doing it by hand would be an understatement.

It gave me about 15 iterations, where about 6 sort of worked. Then I figures it out myself from there.

[radlad]

> I am dreadfully curious what use cases you're envisioning where a fast, bad/wrong answer is better for anything than a correct, slower answer.

>> For some people - I am reluctant to say "for some use cases" - that's very appealing.

You're preaching to the choir.

However, do keep in mind that even authoritative sources found during your own research may be inaccurate. And for some questions, which answer is "right" or "wrong" may not be black and white.

[ToucanLoucan]

> However, do keep in mind that even authoritative sources found during your own research may be inaccurate. And for some questions, which answer is "right" or "wrong" may not be black and white.

I mean, sure. But again: that's just my point restated. What is this doing that a standard search engine does not?

Like, I put shit in my phone's calendar and set reminders so that I don't to think about it anymore. That is a cognitive load (remembering my dentist appointment) that I have now offloaded to technology. And that's useful as all hell, which is why my phone's calendar is full to the tits of everything one would put in a calendar. Now I don't need to think about it. I get messages from my phone when events are coming up, and I get a literal calendar on my screen when I want it, showing me all these things with perfect accuracy.

What is BingGPT in this scenario offloading? It's just a search engine but slower. It doesn't understand what good software is, so it can't make value based judgements on which to recommend. It doesn't know what reliable sources are, and can't evaluate for them, so every bit of information you get back must be treated with a grain of salt. It (probably) doesn't even remotely conceive of why you are asking it a thing or what a good answer to that query would look like because it doesn't know you, it just knows a massive, incomprehensible amount of averages about a ton of things that might be what you want.

And like, that's fine, search engines have had these limitations for my entire life. That's why I'm saying, I don't understand why this is better. It's the same thing as Bing, but slower, and in a chat box.

[radlad]

> I mean, sure. But again: that's just my point restated. What is this doing that a standard search engine does not?

And again, it is quicker than clicking multiple links and can generalize / contextualize what it finds, mapping it to the answer you're looking for.

Have you tried asking one of these tools to write some simple scripts for you? It works decently, actually.

If you didn't already know how to program, this could save you a TON of time, even if it doesn't work perfectly on the first try.