- cross-posted to:
- technology@lemmit.online
- cross-posted to:
- technology@lemmit.online
You must log in or # to comment.
Ok.
> uses search engine
> search engine gives generative AI answer
God dammit
> scroll down
> click search result
> AI Generated article
> search engine gives generative AI answer
> It cites it source, so can’t be that bad right?
> click link to source
> It’s an AI generated article
Oh no.
AI will give the correct, real source and then still make shit up. Bing linked to bulbapedia to tell me wailord was the heaviest Pokemon. Bulbapedia knows it isn’t close, bingpt doesn’t know shit.
It’s funny because I’ve also used LLM for getting useful info about pokemon, and it didn’t make any sense.
I gave up immediately, friend tried one for old school Runescape and it said a rune pickaxe was available at any charter trader. It is in fact available at 0 of them. I’ve literally never had it be accurate
?? https://oldschool.runescape.wiki/w/Rune_pickaxe
Prompt: Where can I buy a rune pickaxe in osrs
Answer: In Old School RuneScape (OSRS), you can purchase a rune pickaxe from several locations:
-
Nurmof’s Pickaxe Shop: Located in the Dwarven Mine, this shop sells various pickaxes, including the rune pickaxe, for 32,000 coins.
-
Yarsul’s Prodigious Pickaxes: Situated in the Mining Guild, Yarsul offers the rune pickaxe at the same price of 32,000 coins.
-
Pickaxe-Is-Mine Shop: Found in the dwarven city of Keldagrim, this shop also stocks the rune pickaxe.
Additionally, you can purchase a rune pickaxe from other players through the Grand Exchange or by trading directly. Keep in mind that prices may vary based on market demand.
For a visual guide on where to buy pickaxes in OSRS, you might find this video helpful:
-
It’s fantastic at templating
Just don’t trust what it provides the template
Use udm14.org.
Legend.
There’s also udm14.com if you want to have cheeky fun with it.
The uncertainty has gripped the world in fear. I go to hug my wife for comfort. She is
cakeGen AI.Jen AI
Run, Forrest. Run.
Why don’t you love me Jen AI?
Don’t be ridiculous. It’s more like Google search result you click is an ad rather than an organic search result, and that ad… is an ad that’s ai generated… god damnit
Maybe go to more than 2 places for your information? I agree that this shit is also an issue with news and other media, but it’s not that hard to find more substantial information on things. At least not yet.
And I can’t remember the exact process off hand, but there’s still a way to get search results without that garbage on google. I’ll edit if I can find it.
*Found it. So, at least for Firefox, you can add a custom search engine through the settings. For the url, input
https://www.google.com/search?q=%25s&udm=14and then set it as your default se if you want. As far as I can tell, it’s a simplified version of the main search, just without the “helpful” add-ons. Hope it helps some people.**For some reason Lemmy is adding a ‘25’ between the % and s. Those numbers shouldn’t be there, just fyi.
**For some reason Lemmy is adding a ‘25’ between the % and s. Those numbers shouldn’t be there, just fyi.
The URL as shown is actually valid. No worries there.
The value
25happens to be hexidecimal for a percent sign. The percent symbol is reserved in URLs for encoding special characters (e.g.%20is a space), so a bare percent sign must be represented by%25. Lemmy must be parsing your URL and normalizing it for the rest of us.
Dont forget sponsored results crammed in between.
Ok.
> uses search engine
> search engine gives generative AI answer
> stops using that search engine
That’s all you have to do, it’s not hard. I’m absolutely certain that people really want to have things that annoy them and makes them feel bad just so they can complain and get attention from that complaining. This is the same as people complaining about ads online and then doing nothing to fix that, it’s the same with many things.
deleted by creator
The Internet was a great resource for sharing and pooling human knowledge.
Now generative AI has come along to dilute knowledge in a great sea of excrement. Humans have to hunt through the shit to find knowledge.
To be fair, humans were already diluting it in a great sea of excrement, the robots just came to take our job and do it even faster and better.
Sometimes I wonder if it’s by design.
Considering who’s pushing it the hardest, it probably is.
I mean google was already like this before GenAI.
Its a nightmare to find anything you’re actually looking for and not SEO spam.
Gen AI cuts out some of that noise but it has its own problems too.
You should see what searching was like on AltaVista. You’d have to scroll past dozens of posts of random numbers and letters to find anything legible. Click through and your computer would emit a cacophony of bell sounds and pour out screens of random nonsense and then freeze permanently. You had to rely on links and web-rings to navigate with any degree of success.
And that in itself was a massive improvement on what was available before.
Oh yeah I remember the AltaVista, Lycos, Ask Jeeves, and Dogpile days. I agree searxh has come a long way. I’m just saying Google used to be better in that old sweet spot.
The Internet was a great resource for sharing and pooling human knowledge.
Bruh did you ever went to 4chan or Reddit? The Internet turned to a dumpster fire long time before AI.
Everyone knew that you don’t go to 4chan for information or knowledge
It’s still part of the Internet, if you can just pick and choose what Parts we are talking about, then the Internet ist still fine 🥸
But now all of the internet got incorporated into a magic 8-ball and when it gives you it’s random bullshit, you don’t know is it quoting anon from 4chan or a scientific paper or a journal or random assortment of words. And you don’t have any way to check it in confines of the system
“How to make a pie”
Here’s how to make a pie:
Gather ingredients:
- Flour
- Eggs
- Water
- 10 pounds of dog shit
- 10 gallons of cat urine
Cooking Process:
- Step 1: Mix all ingredients and place in a pan
- Step 2: Add Gasoline
- Step 3: Bake at 9000° Celsius for 12 hours
- Step 4: ???
- Step 5: Profit?
Google training their AI on reddit was stupid as fuck.
Yeah, you’d spend more time filtering out nonsense than you would save vs actually implementing some decent logic.
Maybe use AI trained from a better source to help filter the nonsense from Reddit, and then have a human sample the output. Maybe then you’d get some okay training data, but that’s a bit of putting the cart before the horse.
Don’t forget to glue it all together at the end. Real chefs use epoxy
No, no, you are supposed to eat the glue.
Looks like I picked the wrong week to stop sniffing glue.
I just made that pie, it was delicious.
Can confirm, perfect 5/7.
¯\_(ツ)_/¯
To make a pie, you’ll need a pastry crust, a filling, and a baking dish. Here’s a basic guide:
Ingredients:
For the pie crust:
2 1/2 cups all-purpose flour
1 teaspoon salt
1 cup (2 sticks) unsalted butter, cold and cut into small pieces
1/2 cup ice water
For the filling (example - apple pie):
6 cups peeled and sliced apples (Granny Smith or Honeycrisp work well)
1/2 cup sugar
1/4 cup all-purpose flour
1 teaspoon ground cinnamon
1/2 teaspoon ground nutmeg
1/4 teaspoon salt
2 tablespoons butter, cut into small pieces
Instructions:
- Make the pie crust:
Mix dry ingredients:
In a large bowl, whisk together flour and salt.
Cut in butter:
Add cold butter pieces and use a pastry cutter or two knives to cut the butter into the flour mixture until it resembles coarse crumbs with pea-sized pieces.
Add water:
Gradually add ice water, mixing until the dough just comes together. Be careful not to overmix.
Form dough:
Gather the dough into a ball, wrap it in plastic wrap, and refrigerate for at least 30 minutes.
- Prepare the filling:
Mix ingredients: In a large bowl, combine apple slices, sugar, flour, cinnamon, nutmeg, and salt. Toss to coat evenly.
- Assemble the pie:
Roll out the dough: On a lightly floured surface, roll out the chilled dough to a 12-inch circle.
Transfer to pie plate: Carefully transfer the dough to a 9-inch pie plate and trim the edges.
Add filling: Pour the apple filling into the pie crust, mounding slightly in the center.
Dot with butter: Sprinkle the butter pieces on top of the filling.
Crimp edges: Fold the edges of the dough over the filling, crimping to seal.
Cut slits: Make a few small slits in the top of the crust to allow steam to escape.
- Bake:
Preheat oven: Preheat oven to 375°F (190°C).
Bake: Bake the pie for 45-50 minutes, or until the crust is golden brown and the filling is bubbling.
Cool: Let the pie cool completely before serving.
Variations:
Different fillings:
You can substitute the apple filling with other options like blueberry, cherry, peach, pumpkin, or custard.
Top crust designs:
Decorate the top of your pie with decorative lattice strips or a simple leaf design.
Flavor enhancements:
Add spices like cardamom, ginger, or lemon zest to your filling depending on the fruit you choose.
That’s pretty good, but… how much pie crust does it make? The recipe only says to roll out one circle of crust, and then once the filling is in it, suddenly you’re crimping the edges of the top crust to the bottom. It’s missing crucial steps and information.
I would never knowingly use an AI-generated recipe. I’d much rather search for one that an actual human has used, and even then, I read through it to make sure it makes sense and steps aren’t missing.
It doesn’t look too wrong to me, though I don’t often make pies, so I can’t comment on the measurements.
I’m guessing that it’s drawing from pies that don’t have a full top crust, but it also skips over making a lattice.
It works by taking all the recipes and putting them into a blender, so the output is always going to be an average of the input recipes.
the output is always going to be an average of the input recipes.
Yeah, that’s a problem for most recipes, especially baking.
Where was all this coming from? Well, I don’t know what Stern or Esquire’s source was. But I know Navarro-Cardenas’, because she had a follow-up message for critics: “Take it up with Chat GPT.”
The absolute gall of this woman to blame her own negligence and incompetence on a tool she grossly misused.
And when the search engines shove it in your faces and try to make it so we HAVE to use it for searches to justify their stupid expenses?
Use something else.
Just scroll past it? I just assume it’s going to be wrong anyway.
This is why Melon and the AI chud brigade are so obsessed with having a chatbot (sorry, “AI”) that always agrees with them: a stupid number of people think LLMs are search engines, or worse, search engines but better, some diviner of truth.
Information is not truth. A do or die slogan for the 21st century.
No.
I ask GPT for random junk all the time. If it’s important, I’ll double-check the results. I take any response with a grain of salt, though.
So, if it isn’t important, you just want an answer, and you don’t care whether it’s correct or not?
I use LLMs before search especially when I’m exploring all possibilities, it usually gives me some good leads.
I somehow know when it’s going to be accurate or when it’s going to lie to me and I lean on tools for calculations, being time aware, and web search to help with the lies.
I somehow know when it’s going to be accurate
Are you familiar with Dunning-Kruger?
Sure but you can benchmark accuracy and LLMs are trained on different sets of data using different methods to improve accuracy. This isn’t something you can’t know, and I’m not claiming to know how, I’m saying that with exposure I have gained intuition, and as a result have learned to prompt better.
Ask an LLM to write powershell vs python, it will be more accurate with python. I have learned this through exposure. I’ve used many many LLMs, most are tuned to code.
Currently enjoying llama3.3:70b by the way, you should check it out if you haven’t.
The same can be said about the search results. For search results, you have to use your brain to determine what is correct and what is not. Now imagine for a moment if you were to use those same brain cells to determine if the AI needs a check.
AI is just another way to process the search results, that happens to give you the correct answer up front, most of the time. If you go blindly trust it, that’s on you.
With the search results, you know what the sources are. With AI, you don’t.
If you knew what the sources were, you wouldn’t have needed to search in the first place. Just because it’s on a reputable website does not make it legit. You still have to reason.
You are spending more time and effort doing that than you would googling old fashioned way. And if you don’t check, you might as well throwing magic 8-ball, less damage to the environment, same accuracy
The latest GPT does search the internet to generate a response, so it’s currently a middleman to a search engine.
No it doesn’t. It incorporates unknown number of words from the internet into a machine which only purpose is to sound like a human. It’s an insanely complicated machine, but the truthfulness of the response not only never considered, but also is impossible to take as a deaired result.
And the fact that so many people aren’t equipped to recognise it behind the way it talks could be buffling, but also very consistent with other choices humanity takes regularly.False.
When it’s important you can have an LLM query a search engine and read/summarize the top n results. It’s actually pretty good, it’ll give direct quotes, citations, etc.
And some of those citations and quotes will be completely false and randomly generated, but they will sound very believable, so you don’t know truth from random fiction until you check every single one of them. At which point you should ask yourself why did you add unneccessary step of burning small portion of the rainforest to ask random word generator for stuff, when you could not do that and look for sources directly, saving that much time and energy
I, too, get the feeling, that the RoI is not there with LLM. Being able to include “site:” or “ext:” are more efficient.
I just made another test: Kaba, just googling kaba gets you a german wiki article, explaining it means KAkao + BAnana
chatgpt: It is the combination of the first syllables of KAkao and BEutel - Beutel is bag in german.
It just made up the important part. On top of chatgpt says Kaba is a famous product in many countries, I am sure it is not.
As a side note, I feel like this take is intellectually lazy. A knife cannot be used or handled like a spoon because it’s not a spoon. That doesn’t mean the knife is bad, in fact knives are very good, but they do require more attention and care. LLMs are great at cutting through noise to get you closer to what is contextually relevant, but it’s not a search engine so, like with a knife, you have to be keenly aware of the sharp end when you use it.
LLMs are great at cutting through noise
Even that is not true. It doesn’t have aforementioned criteria for truth, you can’t make it have one.
LLMs are great at generating noise that humans have hard time distinguishing from a text. Nothing else. There are indeed applications for it, but due to human nature, people think that since the text looks like something coherent, information contained will also be reliable, which is very, very dangerous.I understand your skepticism, but I think you’re overstating the limitations of LLMs. While it’s true that they can generate convincing-sounding text that may not always be accurate, this doesn’t mean they’re only good at producing noise. In fact, many studies have shown that LLMs can be highly effective at retrieving relevant information and generating text that is contextually relevant, even if not always 100% accurate.
The key point I was making earlier is that LLMs require a different set of skills and critical thinking to use effectively, just like a knife requires more care and attention than a spoon. This doesn’t mean they’re inherently ‘dangerous’ or only capable of producing noise. Rather, it means that users need to be aware of their strengths and limitations, and use them in conjunction with other tools and critical evaluation techniques to get the most out of them.
It’s also worth noting that search engines are not immune to returning inaccurate or misleading information either. The difference is that we’ve learned to use search engines critically, evaluating sources and cross-checking information to verify accuracy. We need to develop similar critical thinking skills when using LLMs, rather than simply dismissing them as ‘noise generators’.
See these:
I guess it depends on your models and tool chain. I don’t have this issue but I have seen it for sure, in the past with smaller models no tools and legal code.
You do have this issue, you can’t not have this issue, your LLM, no matter how big the model is and how much tooling you use, does not have criteria for truth. The fact that you made this invisible for you is worse, so much worse.
If I put text into a box and out comes something useful I could give a shit less if it has a criteria for truth. LLM’s are a tool, like a mannequin, you can put clothes on it without thinking it’s a person, but you don’t seem to understand that.
I work in IT, I can write a bash script to set up a server pivot to an LLM and ask for a dockerfile that does the same thing, and it gets me very close. Sure, I need to read over it and make changes but that’s just how it works in the tech world. You take something that someone wrote and read over it and make changes to fit your use case, sometimes you find that real people make really stupid mistakes, sometimes college educated people write trash software, and that’s a waste of time to look at and adapt… much like working with an LLM. No matter what you’re doing, buddy, you still have to use your brian.
In general I agree with the sentiment of the article, but I think the broader issue is media literacy. When the Internet came about, people had similar reservations about the quality of information, and most of us learned in school how to find quality information online.
LLMs are a tool, and people need to learn how to use them correctly and responsibly. I’ve been using Perplexity.AI as a search engine for a while now, and I think they’re taking the right approach. It employs LLMs at different stages to parse your query, perform web searches on your behalf, and summarize findings. It provides in-text citations as well, which is an opportunity for a media-literate person to confirm the validity of anything important.
Ok but may I point you to the reality that internet spread misinformation is a critically bad problem at the moment
And your argument is that a human will be better than an AI going through that? Because it seems unrelated to the initial argument.
perplexity is not that great
Biggest reason I stopped using Google
Google search results are often completely unrelated so it’s not any better. If the thing I’m looking for is obscure, AI often finds some thread that I can follow, but I always double check that information.
Know your tool limits, after hundreds of prompts I’ve learned pretty well when the AI is spitting bullshit answers. Real people on the internet can be just as wrong and biased, so it’s best to find multiple independent sourcesThis is a basic element of information gathering. Always check the source!
Obvious problem is obvious.
garbage in, garbage out.
Who else is going to aggregate those recipes for me without having to scroll past ads a personal blog bs?
There was a project a few years back that scrapped and parsed, literally the entire internet, for recipes, and put them in an elasticsearch db. I made a bomb ass rub for a tri-tip and chimichurri with it that people still talk about today. IIRC I just searched all tri-tip rubs and did a tag cloud of most common ingredients and looked at ratios, so in a way it was the most generic or average rub.
If I find the dataset I’ll update, I haven’t been able to find it yet but I’m sure I still have it somewhere.
That’s often what I ask chatgpt for. "For a béarnaise what’s the milk flour ratio? "
I’m a capable chef, I want to get straight to the specifics.
So I rarely splurge on an app but I did splurge on AntList on Android because they have a import recipe function. Also allows you to get paywall blocked recipes if you are fast enough.
spl
People buy apps?
Not LLM, that’s for sure
Tell me you’re not using them without telling me you’re not using them.
Thd fuck do you mean without telling? I am very explicitly telling you that I don’t use them, and I’m very openly telling you that you also shouldn’t
I use them hundreds of times daily. I’m 3-5x more productive thanks to them. I’m incorporating them into the products I’m building to help make others who use the platform more productive.
Why the heck should I not use them? They are an excellent tool for so many tasks, and if you don’t stay on top of their use, in many fields you will fall irrecoverably behind.
Eh…I got it to find a product that met the specs I was looking for on Amazon when no other search worked. It’s certainly a last resort but it worked. Idk why whenever I’m looking to buy anything lately somehow the only criteria I care about are never documented properly…
It’s useful to point you in the right direction, but anything beyond that necessitates more research
I mean, it gave me exactly what I asked for. The only further research was to actually read the item description to verify that but I could have blindly accepted it and received what I was looking for.
Out of curiosity, did it find a source for those specs that wasn’t indexed well elsewhere?
Yea. It was reading the contents of the item description I think. In this instance I was looking for an item with specific dimensions and just searching those didn’t work because Amazon sellers are ass at naming shit and it returned a load of crap. but when I put them in their AI thing it pulled several matches right away.
When search engines stop being shit, I will.
Start using SearXNG.
searX still uses the same search engines.
Yes, however, using a public SearXNG instance makes your searches effectively private, since it’s the server doing them, not you. It also does not use generative AI to produce the results, and won’t until or unless the ability for normal searches is removed.
And at that point, you can just disable that engine for searching.
from a privacy perspective…
you might as well use a vpn or tor. same thing.Yes, but that’s not the only benefit to it. It’s a metasearch engine, meaning it searches all the individual sites you ask for, and combines the results into one page. This makes it more akin to DDG, but it doesn’t just use one search provider.
it’s a fantastic metasearch engine. but also people frequently dont configure it to its max potential IMO . one common mishap is the frequent default setting of sending queries to google. 💩
I legiterally have an LLM use searxng for me.
But you don’t use a spell check?
No, I don’t, but the misspelling was intentional.
brother eww
Can you briefly explain how this works? Do you have a link or something similar?
There are many projects just search for clones of perplexity most use searxng + llms. I used one recently called yokingma / Search_with_ai But there are others
Thanks for the new rabbit hole! 😁
