1472
Dreams of AI
(lemmy.world)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 03 Jun 2024
1472 points (97.9% liked)
People Twitter
5171 readers
1001 users here now
People tweeting stuff. We allow tweets from anyone.
RULES:
- Mark NSFW content.
- No doxxing people.
- Must be a tweet or similar
- No bullying or international politcs
- Be excellent to each other.
founded 1 year ago
MODERATORS
It’s honestly not that far off I bet. Though I bet once it does become viable, we’ll find that the best option is buying all your groceries from Amazon, or something like that.
Or, it wouldn't ever be truly accurate. That would be an anti-capitalism tool and mangled or completely killed in order to ensure profit
The thing is, you don't need technological advances for that. Someone could have built that ten years ago. No one did, because it's a lot of individual, non-trivial steps.
Those stores may have that data online somewhere, but how you request it and in which format you get it, that's going to be different for each store. Then you also need information where those stores are and need to integrate some navigation functionality between them.
And ultimately, your target users aren't exactly willing to spend money, so good luck covering costs for your service.
You are basically giving all the reasons for why this hasn’t been done yet without AI, but none of the reasons for why this can’t be done with AI.
I know we like to be cynical about the advances of things like chat gpt, but I have found many uses that are very similar to what you describe below. Taking a problem that could be solved with tedious brute force and combining data from multiple sources and knowledge of a scripting language, but instead I ask chat gpt in just the right way and it will get me the answer.
Also worth noting, grocery store prices are easily accessible online now whereas 10 years ago they were not. It’s just a matter of time before AI gets access to this data and can integrate into whatever models it uses.
Well, no, I'm just saying the text generation stuff did not change anything about that process.
It can try to generate the right text for the requests to grab this data, but since there's going to be practically no documentation for that out there, it will struggle to do so from just its training data alone.
So, what you do instead is that you have a human figure out the API of each store that needs to be integrated + ideally a transformation of the returned data into a shared, documented format. And then you tell the text generation a trivial way for it to generate the text to make use of that.
So, basically you preface the whole user conversation with "If I ask for prices of Todd's Tater Tots, run
./prices_todds_tater_tots.shfor that and use the result according to the JSON schema inprices_store.schema.json.".And then you repeat that for all the other stores, for some math API and some navigation API and then you've got a chance that the text generation figures out the right semantics of how these things should be called.
Semantics is what it's good at. But the rest is still the same process as ten years ago.
I think you’re under selling what chat gpt is capable of. It is able to take outside data in and use it with the rest of the model. Bing does it with its web index data. I was able to ask what the cheapest gas station near me is and bing gave me a list, likely coming from gas buddy.
Yeah, it can easily do that, if such a comparison service already exists. Then it's just yet another API that it calls, or in this case, it more likely just does a Bing search and recounts the top results. But I haven't yet heard of such a service existing for groceries, so it would still need to be built.
I understand what you're saying. In theory, it's possible. But in practice, it is not just a matter of linearly improving LLMs and then at some point, they'll just do it on their own. Any task that takes more than a few steps means that the error rate of the LLM multiplies.
The error rate would need to get magnitudes lower for that multiplication to not explode with many steps. The alternative is removing steps that the LLM needs to do, as I described. Some colleagues at my dayjob do basically nothing else now.