I tried it and it mostly worked, but at the top of the page it says "Model: Default" instead of "Model: GPT-4" which is what I used. When I continued the conversation it used GPT-4. I was hoping it would let you switch models.
ChatGPT conversations can be shared publicly
31–40 of 172 posts
Re: ChatGPT conversations can be shared publicly
#32> "One of the Maxwell equations, Faraday's law, relates changes in the magnetic field to the induction of an electric field. It states that a time-varying magnetic field induces an electric field, which is analogous to the concept of induction in electromagnetism. This induction process occurs as the changing magnetic field "propagates" through space, giving rise to an electric field that is perpendicular to both the magnetic field and the direction of propagation."
> "Mathematically, this phenomenon can be likened to the inductive step in mathematical induction. Just as mathematical induction builds upon previous steps to establish a result for the next value, the induction of an electric field in electromagnetic waves relies on the changing magnetic field at a particular point to induce the electric field at the next point in space."
> "Moreover, the wave-like nature of electromagnetic waves, including light, can be understood in terms of a progressive "domino effect." Each point in space influences the neighboring points, as changes in electric and magnetic fields induce one another. This propagation of the electromagnetic wave throughout space mirrors the idea of the sequential propagation of statements or properties in mathematical induction."
That's kind of impressive, isn't it? Cross-domain interconnections and all that?
Re: ChatGPT conversations can be shared publicly
#33Okay, here's the most mind-boggling ChatGPT response I've gotten. Someone recently posted an HN article on mathematical proof techniques which included a statement about how we shouldn't confuse the mathematical concept of induction with the electromagnetic concept of induction. After a bit of querying ChatGPT about this, here's what it came up with: > "One of the Maxwell equations, Faraday's law, relates changes in…
Re: ChatGPT conversations can be shared publicly
#34EDIT: oops this is the correct link: https://chat.openai.com/share/69839da8-317a-4e3b-b215-f9e9ff... Previous comment: GPT-4 failing with a math question: https://chat.openai.com/share/53116ac3-0c44-410a-b367-c5df0a... (I didn't discover this. I was just trying to confirm something that was reported elsewhere.)
It screws up if you ask it to use 10,000 which is what Dr. Loh gave it per his interview. I just tested it, gave me this big long proof and says Therefore, the largest fraction less than 1/2 with a numerator and denominator that are positive integers less than or equal to 10000 is 9999/10000
Re: ChatGPT conversations can be shared publicly
#35EDIT: oops this is the correct link: https://chat.openai.com/share/69839da8-317a-4e3b-b215-f9e9ff... Previous comment: GPT-4 failing with a math question: https://chat.openai.com/share/53116ac3-0c44-410a-b367-c5df0a... (I didn't discover this. I was just trying to confirm something that was reported elsewhere.)
Re: ChatGPT conversations can be shared publicly
#36Re: ChatGPT conversations can be shared publicly
#37I'm proud of the robopsychology in the middle a la Asimov's Susan Calvin:
https://chat.openai.com/share/a6c6b2be-18f8-49e5-aedc-c84c97...
Re: ChatGPT conversations can be shared publicly
#38Re: ChatGPT conversations can be shared publicly
#39For over two week, all requests in the chat UI at chat.openai.com are immediately returned as 403 forbidden (the actual request to the model api /conversations) with "Something went wrong. If this issue persists please contact us through our help center at help.openai.com.". Filing a bug report seems to not do anything. And, in true irony, OpenAI's support bot is absolutely atrocious.
Re: ChatGPT conversations can be shared publicly
#40Okay, here's the most mind-boggling ChatGPT response I've gotten. Someone recently posted an HN article on mathematical proof techniques which included a statement about how we shouldn't confuse the mathematical concept of induction with the electromagnetic concept of induction. After a bit of querying ChatGPT about this, here's what it came up with: > "One of the Maxwell equations, Faraday's law, relates changes in…
It's extremely underwhelming. The _only_ thing in common between induction of an electric field and induction in math is the spelling of the word "induction". The meaning in each context is vastly different. I stopped reading there; can't comment on the rest of it.