Hacker News new | past | comments | ask | show | jobs | submit | ShannonLimiter's comments login

Don’t you mean Sonja Lang?


Apparently the creator now goes by that name. I was writing out of my own memories of knowing the person under a previous name in the Esperanto and general conlang community over two decades ago.


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%."


I wish I could see the screen on my Playdate. I've found it incredibly difficult to see under normal lighting conditions.

I wish they went with a different display.


Interesting. The only concession I have to make is to take my glasses off because it's quite small. I might need varifocals.


GPT 3.5 Turbo gets the right answer for me every time.


First try on GPT 3.5 (through the chat web) I get

> Based on the information provided, Shape A is red and Shape B is the other shape. However, it is not explicitly stated what color Shape B is. Therefore, without further information, we cannot determine the color of Shape B.

I retried a second time and it answered the same

I retried a third time and it answered correctly


GPT3.5 turbo almost got it for me, sort of did but

"If Shape A is red and Shape B is a different color, one possible color for Shape B could be blue. However, it's important to note that the color of Shape B could be any color other than red. Without further information or constraints, there is no definitive answer for the color of Shape B."

Not that it matters a ton here, I'm just surprised that 3.5turbo had issues with it at all.


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


They did not. AI.com redirects to a-i.com.

This may have been a publicity stunt by the owner to get traffic.


I've just tried it and it opened openai's chatgpt


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.


Do you think that the team of engineers at Microsoft and OpenAI who worked together for months on the new Bing integration are lazy? https://twitter.com/kliu128/status/1623472922374574080


Your website is only 30 words with no examples or explanations that I can see – just a sign up. The video on your site doesn’t play on my computer.

It might be worth 1,000 votes, but it’s hard to know without actually seeing what it can do.


Thanks for explaining. What kind of computer? Yesterday I added another source to the video (mp4) in case people can't play WebM. Unless it is trying to play the WebM and doesn't like the encoding.

I definitely need to link to the Discord with the examples and/or finish the Explore/featured page which is the main plan for that.


Video doesn’t play on iPad. Think about what audience you’re trying to attract and create a landing page that would resonate with them…


Thank you for telling me it doesn't play on an iPad. Your implication that the landing page is useless does not make sense in the context that the video does not play.

I do not own any Apple products and so was not able to test on them.


I’d add Gravity and Ad Astra to that list.


I would say Ad Astra is filled to the brim with fantastic and implausible elements. The visual design is very realistic, and this contrast adds to the movie's sense of disconnect (which is great it you like it, and a movie killer if you don't).


If we are talking at implausibility, Gravity is filled to the brim with it. It does a very lousy presentation of orbital mechanic: you don't point at a general direction of space station which is 70km away, give an impulse away from it and slowly drift to it. It is not how it works!


On top of this implausibility, the criteria in the parent post was ‘there’s no “supernatural” element whatsoever,’ which given the heroic ghost of Kowalski‘s role in saving the protagonist (as a “hallucination”), should also rule it out. Never mind that the film was essentially disorienting scenes and Sandra Bullock repeatedly shouting into the cameras


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.


Book chemistry and physics (other than dust storm) looks rather plausible, what didn't you like there? Movie added some ridiculous stuff when flying with punctured space suit, that was pathetic.


Why not? What's inaccurate about it?


Objects in space in adjacent orbits around aren't floating in space, they are falling on Earth at a great speed. If you apply an impulse in the way as shown in the movie, you'll expand or shrink the orbit excentricity and you will likely start moving up or down rapidly relative to your target, instead of closing in. This way to get to your target you'll need to burn an insane amount of fuel and do orbit corrections every second. The right way is to make one impulse to change your orbit in such a way that your new orbit will intersect the orbit of your target (and that you both will be there at the same time), and the direction of such impulse might be far from obvious. More likely one impulse will result in a very long transit orbit, so a better course would be two or more orbital corrections.


Ah, that makes sense, thanks!


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.


Ad Astra is "story" wrapped around visual effects to allow Brad Pitt be used as lead actor. And there could be so much to it: The emotional controls, done by I assume AI? Great plot for a dystopian society. A rogue scientist at the edge of explored space posing a big threat? The Heart of Darkness is great, regardless of version. Various powers battling of the few rocks in what is otherwise an empty solar system? The Expense shows us how great that can be.

All of that in one film? Not so much. And then there a the logic holes bigger than a smaller galaxy. Earth is facing severe energy issues, up to the point a habdfull of dudes are fighting over three luna rovers? Could be fun, ubtil one realizes that there is apparebtly enough energy to be had to kill civilisation by energy waves created somewhere around Saturn... Then Brad is sent on a secret missions, and instead of flying on a military vessel to the lunar station, he takes acivilian flight wearing uniform. Only to land travle across the moon. The inly reason for that seems to be show some fancy lunar battle scene... I could go on...

Space Cowboys so, that would fit. As would Alien and Aliens, everything after Prometeus... If I want Eric Daenicken, I go read one of his books.


Here’s an argument for why these are holograms:

http://amasci.com/amateur/holo3.html


Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: