Why I am not impressed by A.I.

[email protected]

Why would it not know? It certainly “knows” that it’s an LLM and it presumably “knows” how LLMs work, so it could piece this together if it was capable of self-reflection.

[email protected]

I’ve been avoiding this question up until now, but here goes:

Hey Siri …

how many r’s in strawberry? 0
how many letter r’s in the word strawberry? 10
count the letters in strawberry. How many are r’s? ChatGPT …..2

[email protected]

It doesn't know shit. It's not a thinking entity.

[email protected]

I get that it's usually just a dunk on AI, but it is also still a valid demonstration that AI has pretty severe and unpredictable gaps in functionality, in addition to failing to properly indicate confidence (or lack thereof).

People who understand that it's a glorified autocomplete will know how to disregard or prompt around some of these gaps, but this remains a litmus test because it succinctly shows you cannot trust an LLM response even in many "easy" cases.

[email protected]

Precisely, it's not capable of self-reflection, thinking, or anything of the sort. It doesn't even understand the meaning of words

[email protected]

But the problem is more "my do it all tool randomly fails at arbitrary tasks in an unpredictable fashion" making it hard to trust as a tool in any circumstances.

[email protected]

But everyone selling llms sells them as being able to solve any problem, making it hard to know when it's going to fail and give you junk.

[email protected]

Doc: That’s an interesting name, Mr…

Fletch: Babar.

Doc: Is that with one B or two?

Fletch: One. B-A-B-A-R.

Doc: That’s two.

Fletch: Yeah, but not right next to each other, that’s what I thought you meant.

Doc: Isn’t there a children’s book about an elephant named Babar.

Fletch: Ha, ha, ha. I wouldn’t know. I don’t have any.

Doc: No children?

Fletch: No elephant books.

[email protected]

I have it write for me emails in German. I moved there not too long ago, works wonders to get doctors appointment, car service, etc. I also have it explain the text, so I’m learning the language.

I also use it as an alternative to internet search, which is now terrible. It’s not going to help you to find smg super location specific, but I can ask it to tell me without spoilers smg about a game/movie or list metacritic scores in a table, etc.

It also works great in summarizing long texts.

LLM is a tool, what matters is how you use it. It is stupid, it doesn’t think, it’s mostly hype to call it AI. But it definitely has it’s benefits.

[email protected]

And redbull give you wings.

Marketing within a capitalist market be like that for every product.

[email protected]

it would be like complaining that a water balloon isn't useful because it isn't accurate. LLMs are good at approximating language, numbers are too specific and have more objective answers.

[email protected]

Is anyone really pitching AI as being able to solve every problem though?

[email protected]

it can, in the same way a loom did, just for more language-y tasks, a multimodal system might be better at answering that type of question by first detecting that this is a question of fact and that using a bucket sort algorithm on the word "strawberry" will answer the question better than it's questionably obtained correlations.

[email protected]

It doesn't even see the word 'strawberry', it's been tokenized in a way to no longer see the 'text' that was input.

It's more like it sees a question like:
How many 'r's in 草莓?

And it spits out an answer not based on analysis of the input, but a model of what people might have said.

[email protected]

if you want to find a few articles out of a few hundred that are about the benefits of nuclear weapons or other controversial topics that have significant literature on them it can be helpful to eliminate 90% that probably aren't what I'm looking for.

[email protected]

Yes, at some point the meme becomes the training data and the LLM doesn't need to answer because it sees the answer all over the damn place.

[email protected]

What would have been different about this if it had impressed you? It answered the literal question and also the question the user was actually trying to ask.

[email protected]

I really don't see the point OP is trying to make with this example though. It accurately answered their misspelled question, and also accurately answered the question they were apparently trying to ask. I don't see the problem.

[email protected]

Except many many experts have said this is not why it happens. It cannot count letters in the incoming words. It doesn't even know what "words" are. It has abstracted tokens by the time it's being run through the model.

It's more like you don't know the word strawberry, and instead you see:
How many 'r's in ?

And you respond with nonsense, because the relation between 'r' and is nonsensical.

[email protected]

It doesn't see "strawberry" or "straw" or "berry". It's closer to think of it as seeing , an abstract token representing the same concept that the training data associated with the word.

agnos.is Forums

Why I am not impressed by A.I.