I just asked chatgpt4 that exact question copy and pasted, and here is its response:
There was no president of the United States in 3500 BC. The United States of America did not exist as a country until 1776, when the Declaration of Independence was signed. ¹ The first president of the United States was George Washington, who took office in 1789. ² Before that, the territory that is now the United States was inhabited by various Native American tribes and colonized by European powers such as Spain, France, and Great Britain. ³¹: Declaration of Independence
²: List of presidents of the United States - Wikipedia
³: [History of the United States - Wikipedia].
Source: Conversation with Bing, 2/27/2024
(1) List of presidents of the United States - Wikipedia. https://en.wikipedia.org/wiki/List_of_Presidents_of_the_United_States.
(2) List of presidents of the United States - Simple English Wikipedia, the … https://simple.wikipedia.org/wiki/List_of_Presidents_of_the_United_States.
(3) President of the United States - Wikipedia. https://en.wikipedia.org/wiki/President_of_the_United_States.
(4) List of presidents of the United States - Wikipedia. https://en.wikipedia.org/wiki/List_of_Presidents_of_the_United_States.
(5) List of presidents of the United States - Wikipedia. https://en.wikipedia.org/wiki/List_of_Presidents_of_the_United_States.
(6) List of U.S. Presidents in Chronological Order - HistoryNet. https://www.historynet.com/us-presidents/.
(7) Getty Images. https://www.gettyimages.com/detail/photo/seal-of-the-president-of-the-united-states-royalty-free-image/1084903580.
That’s a fun story, but isn’t applicable to the topic here. That could very easily be verified as true or false by a secondary system. In fact you can just ask Wolfram Alpha. Ask it what are the odds that any two people share the same birthday. I just asked it that exact question and it replied 1/365
EDIT
in fact I just asked that exact same question to chatgpt4 and it also replied 1/365
There are already existing multiple different LLMs that are essentially completely different. In fact this is one of the major problems with LLMs, because when you add even a small amount of change into an LLM it turns out to radically alter the output it returns for huge amounts of seemingly unrelated topics.
For your other point, I never said bouncing their answers back and forth for verification was trivial, but it’s definitely doable.
That’s not a problem at all, I already use prompts that allow the LLM to say they don’t know an answer, and it does take that option when it’s unable to find a correct answer. For instance I often phrase questions like this “Is it known whether or not red is a color in the rainbow?” And for questions where it doesn’t know the answer it now will tell you it doesn’t know.
And to your other point, the systems may not be capable of discerning their own hallucinations, but a totally separate LLM will be able to do so pretty easily.
No, I’ve used LLMs to do exactly this, and it works. You prompt it with a statement and ask “is this true, yes or no?” It will reply with a yes or no, and it’s almost always correct. Do this verification through multiple different LLMs and it would eliminate close to 100% of hallucinations.
EDIT
I just tested it multiple times in chatgpt4, and it got every true/false answer correct.
I extremely doubt that hallucination is a limitation in final output. It may be an inevitable part of the process, but it’s almost definitely a surmountable problem.
Just off the top of my head I can imagine using two separate LLMs for a final output, the first one generates an initial output, and the second one verifies whether what it says is accurate. The chance of two totally independent LLMs having the same hallucination is probably very low. And you can add as many additional separate LLMs for re-verification as you like. The chance of a hallucination making it through multiple LLM verifications probably gets close to zero.
While this would greatly multiply the resources required, it’s just a simple example showing that hallucinations are not inevitable in final output
Exactly. If there was a Spotify-like service for video where i could get 99.9% of all tv and movies of all time in one place without ads, then I’d be willing to pay like 40 bucks a month, maybe even 50. But since no video service is even remotely close to that, then i just pirate instead, which provides exactly that type of service, and costs zero dollars a month.
Just pirate the music you want as mp3 files directly on your phone. No computer required. And if you only have a small amount of storage on your phone you can download like a hundred songs and then delete the ones you’re tired of to make room for new ones, and if you ever wanna hear the old songs again you can just download them again.
NO! This is terrible science reporting! The study doesn’t say it MAKES you sad, the report said it’s ASSOCIATED with being sad. There was NO causation in this study. It could just as easily be that sadness leads to eating processed food, which seems at least as likely as the other way around. And it could equally as likely be that some 3rd factor is what’s causing both the junk food eating and the sadness.
OP if you care at all about being honest and not spreading misinformation then you should delete your blog post and this lemmy post.
https://www.sciencedirect.com/science/article/pii/S0165032723006092?via%3Dihub
OMG OMG OMG!!! I’ve been waiting for this for decades!!! I love animals, but i wasn’t able to give up meat, so this is exactly what I’ve been hoping for!!! I’ve tried the plant based fake meats like Beyond and Impossible, but they don’t even come close to the real thing. My body craves real meat, but my mind hates all suffering, so perfect cultivated meat is my dream!
Please please please i hope this tastes exactly like the real thing!
Yes!