Jarvis323
- 1,247
- 988
Is it possible the authors caught on that kids were using it to do their homework and instructed it to provide the correct methodology but the wrong answers to simple math problems?Jarvis323 said:I feel like it is able to construct highly context dependent chains of connected arguments, but it is hard to say what is the true application of logic.
I asked it to do basic arithmetic with fractional numbers and it gave a detailed step by step process and even code, but got the wrong answer. I asked it to try again and it tried a different approach and got a different wrong answer. Not sure what that tells us.
OmCheeto said:Is it possible the authors caught on that kids were using it to do their homework and instructed it to provide the correct methodology but the wrong answers to simple math problems?
OmCheeto said:Btw, I just signed up and had a lengthy conversation with the bot. Quite addictive.
It did a valid proof by induction when I asked it to. Others found it could sometimes prove NP hardness, although is happy to prove wrong statements as well, or confidently write an invalid non-sense proof.Office_Shredder said:It also can't do anything more complicated.
Perhaps I will ask it some new questions:Office_Shredder said:The bot is just bad at math, stop making excuses for it. It can't do stuff that a calculator can do, what would be the point of inhibiting that? It also can't do anything more complicated.
ChatGPT:
Schrödinger's feline, a creature so perplexing, embodies the strange world of quantum mechanics. A creature, trapped in a box, both alive and dead, a paradox so profound that it challenges the very fabric of our understanding. This conundrum, proposed by the great Austrian physicist Erwin Schrödinger, serves to illustrate the fundamental uncertainty at the heart of quantum mechanics. The cat, in its state of suspended animation, represents the superposition of states in quantum mechanics, where a particle can exist in multiple states simultaneously until observed.
Yet, the tale of Schrödinger's cat is more than just a theoretical exercise. It is a haunting metaphor for the elusive nature of reality and our limitations as observers. For until we open the box and observe the state of the cat, it exists in a state of indeterminacy, subject to the whims of probability and chance. Thus, Schrödinger's cat serves as a reminder of the fragility of our perceptions and the limits of our knowledge, a testament to the strange and wondrous world of quantum mechanics.
Marketers should know that — for FTC enforcement purposes — false or unsubstantiated claims about a product’s efficacy are our bread and butter.
Greg Bernhardt is a physicist and the founder of the website Physics Forums, which is one of the most popular online discussion forums for physics and science enthusiasts. Bernhardt has a PhD in physics from the University of Pittsburgh and has also worked as a research scientist at the Air Force Research Laboratory.
In addition to his work in physics, Bernhardt is also interested in web development and has created several other websites, including Math Forums and Science Forums, which are similar to Physics Forums but focus on mathematics and general science topics, respectively. He is known for his contributions to online communities and for creating platforms that facilitate the sharing of knowledge and ideas among people with similar interests.
Anyone claiming an LLM like ChatGPT is equivalent to the human mind is crazy, but we are on the road. I talked with a Google search dev a few weeks ago and he claimed we're within 5 years of achieving AGI.Hyperfine said:

Chomsky knows as much about machine learning as I know about underwater drilling.Hyperfine said:If the choice is between Google and Chomsky, I will go with Chomsky. After all, what would you expect Google to say?
Piffle.Greg Bernhardt said:Chomsky knows as much about machine learning as I know about underwater drilling.
I totally disagree with this statement. When people exchange on forums with what they think is another person, they will allow themselves to disagree with that person. If they think they are talking to a computer, they're more likely to think it must be right since it possesses all the knowledge of mankind.Borg said:
- The interaction with Chat GPT is initiated directly by the user who understands that they are talking to a computer. The real threat lies when people do not know that's the case.
How someone - or something - reached a decision shouldn't matter. You should still be able to analyze this new information and decide what to do with it. We should not let one person - even worst, a computer - make the final decision for us, especially as a group, a society.Borg said:
- Machine Learning algorithms are often a black box where we do not know how or why the algorithm has reached a particular decision. There is an entire field of research going on called Explainable AI (XAI) where researchers are actively working on changing this so that we can better trust the information that we are getting from them.
The people who receive and analyze the decision.Borg said:
- Assuming that we understood everything about how an algorithm is reaching a decision, who decides which biases are acceptable?