I'm not sure if ChatGPT can solve super conductivity, but the current version of ChatGPT can handle the bears in space question and the Monty Hall problem from the linked article.
GPT-4 was released a month after that article published and its problem solving capabilities are much more sophisticated than GPT-3.5 (which ChatGPT first used.)
It would be interesting to find some new examples to test it with since some people will claim the model didn't getter smarter – it only learned the answers to those questions.
In my anecdotal experience, GPT-4 is much better at problem solving.
---
how many bears russia has launched into space:
"As of my knowledge cut-off date in September 2021, there is no publicly available information to indicate that Russia has ever launched bears into space. The idea of sending bears into space might sound intriguing or humorous, but it's important to note that space missions are highly complex and expensive endeavors that typically focus on scientific research and exploration.
Animals like dogs, monkeys, and mice have been sent into space by various countries to study the effects of space travel on living organisms, but bears are not among the animals known to have been included in space missions."
###
The table didn't fit in the car because it was too small. What was too small?:
"The sentence is somewhat ambiguous, but the way it is constructed suggests that the car was too small to fit the table. The phrase "it was too small" refers to the car, and this is why the table didn't fit inside."
###
There are three doors with a $10,000 hidden behind one door and a bag of goldfish hidden behind each of the other two doors. You choose Door 3. No matter which door you choose, the host will show you a bag of goldfish behind one of the doors you did not choose (say, Door 1) and then ask if you wish to switch your choice to the remaining door. What is the probability of winning the $10,000 prize if you do switch?:
"The situation you're describing is known as the Monty Hall problem. It's a probability puzzle named after the host of the American television game show "Let's Make a Deal." The problem can be analyzed using conditional probability.
Here's how you can think about the situation:
1. *Initially*: When you first choose a door (e.g., Door 3), there is a 1/3 chance that the $10,000 prize is behind that door, and a 2/3 chance that the prize is behind one of the other two doors (Door 1 or Door 2).
2. *Host's Reveal*: The host, who knows what's behind each door, then opens one of the other two doors to reveal a bag of goldfish. This does not change the initial probabilities.
3. *Switching Doors*: If you switch your choice, you'll win the $10,000 prize if and only if your initial choice was incorrect (i.e., you initially picked a door with a goldfish behind it). Since there was a 2/3 chance of that happening, there is a 2/3 chance that switching doors will lead you to the prize.
So the probability of winning the $10,000 prize if you do switch is 2/3, or approximately 66.67%."
Just ask it to figure it out step-by-step and to remove accents:
GPT-4:
Figure this out step by step and check your work:
Remove the accents and tell me if this a palindrome: Élu par cette crapule
GPT-3.5 (Needs to know that removing spaces and lowercasing is okay):
Figure this out step by step and check your work:
Lowercase it and remove the accents and spaces and tell me if this a palindrome: Élu par cette crapule
Only if prompt engineers and devs continue to be lazy. The most popular exposures could have been prevented if the devs talked to people who understand prompting and how to mitigate this.
Hallucinations aren’t supernatural. Kowalski wasn’t a ghost. This was evident in the movie.
The Martian’s bad physics and chemistry should also rule it out from the list based on your criteria. Which would be sad, because despite that, it’s a great movie and book.
So is The Martian. The physics in the movie and book are absolutely magical: windstorms powerful enough to impale people but not enough air pressure to require a top to the spacecraft. Toxic, perchlorate soil growing potatoes… Both the book and movie are wonderful, but have huge gaps of implausibility.