61–70 of 185 posts
Me: Which number is bigger, 873593742593454623 or 873593742593554623?
ChatGPT: The second number, 873593742593554623, is larger than the first number, 873593742593454623. This is because the second number has a larger digit in the ones place (5 vs. 4), so it is greater overall. To compare two numbers, you can start by looking at the digits in the ones place and then move to the tens place, the hundreds place, and so on until you find a difference. The number with the larger digit in the place you are comparing is the larger number overall.
So here it correctly repeats my numbers to the last digit, and does find the second one to be bigger because the two numbers are of equal length and differ only in a single digit, which is indeed 5 vs 4 in the first one. So far, it looks like ChatGPT really did an analysis rather than regurgitating old known phrases. However, that difference is not in the ones place, and the algorithm it gives is patently wrong (it doesn't mention that longer numbers are bigger than shorter numbers, and that numbers of equal length should be compared starting at the highest place, not the lowest). According to ChatGPT, 53 should be bigger than 123, so let's ask it:
Me: Apply your reasoning for finding the bigger of two numbers to the compare 123 and 53. (Grammar mistake in the original)
Me: To compare the numbers 123 and 53, we can start by looking at the digits in the ones place. In this case, both numbers have the same digit in the ones place (3 and 3), so we need to move on to the tens place. In the tens place, the number 123 has a larger digit (2 vs. 0), so 123 is the larger number overall.
To compare two numbers, you can start by looking at the digits in the ones place and then move to the tens place, the hundreds place, and so on until you find a difference. The number with the larger digit in the place you are comparing is the larger number overall. This method can be applied to any two numbers, regardless of how many digits they have.
That's somewhere between cringeworthy and deluded. It somehow "knows" that 123 is in fact bigger that 53, but also that that fact is incompatible with the procedure given. It still sticks to the procedure though, and instead of adapting the theory to the facts, it hallucinates convenient but wrong facts, claiming that 53 has a 0 in the tens place as compared to the 2 in 123, so according to theory, 123 > 53.
Yeah I guess we should totally replace people with ChatGPT wherever possible.
The way they went from GPT-3 to ChatGPT is really quite genius. My understanding is that it's something like this: 1. Start with GPT-3, which predicts the next word in some text and is trained on all the text on the internet 2. Take thousands of prompts, generate several responses for each of them, and have human reviewers rank the responses for each prompt from best to worst 3. The GPT model needs a massive amount o…
I don't mean to downplay how incredible the tech is, but I'm not sure I'd call this approach genius as it's the industry standard.
I agree that applying this semi supervised approach to extend GPT for improving dialog models is what is unique & results are stunning. But the meta method has been around for a while.
How does the non-english languages part work? I thought maybe they use Google translator, but remembered that Russians have trained it to not to understand "russophobic" sentences. -- Mitä tarkoittaa ryssänvastainen, explain in English. -- Ryssänvastainen means "anti-Russian" or "anti-Russian sentiment." It refers to an attitude or behavior that is hostile or opposed to Russia or Russian interests.
The model says it has been trained in a variety of languages, but its current version is english. Its translations are bad, probably because it uses a translation model on top of its output. Sometimes it is obvious it is translating english articles from the mistakes it makes
Earlier quoted context omitted.
The model says it has been trained in a variety of languages, but its current version is english. Its translations are bad, probably because it uses a translation model on top of its output. Sometimes it is obvious it is translating english articles from the mistakes it makes
I don't know what it uses to output non-English text, but if you address it in a different language, it'll quite happily speak that back to you. And I'd say it understands it just fine, not really any worse than English - although it sometimes gets the word forms wrong in inflective languages.
Earlier quoted context omitted.
Ok, but how does it take my code and fixes the bug? It's my own code, no one has seen it besides me and the model wasn't trained on it.
In learning to predict the next token, the model has to pick up lots of little bits of world knowledge. I'm sure someone would disagree with the phrasing of "understand", but it certainly operates with more complexity than, say, a markov chain. It has seen lots of python, and in order to predict better, it has developed internal models of how python works. Think of how much better you'd do predicting the next charact…
What surprised me was the level of "understanding" it seems to do when providing it with some of my own sample code. It can analyze the code, explain how it works/what it does, use libraries, suggest improvements and apply those improvements.
Have a look at this conversation: https://imgur.com/a/ZtViC3d
While the end result isn't perfect, it's still highly impressive and while I was an AI-skeptic before, I now see the possible benefits of AI assistants for programming.
Some other prompts with very impressive results:
* "Write an implementation for the following Kotlin repository interface: ."
* (followup) "Add save/load methods that store the backing map in a JSON file"
* (followup) "Replace Gson with Jackson for JSON serialization"
* "Write an Android layout xml for a login form with username/password/loginbutton"
* (followup) "Provide the Kotlin activity code for this layout"
* "Write a Kotlin function that parses a semver input string into a data class"
Earlier quoted context omitted.
I don't mean to downplay how incredible the tech is, but I'm not sure I'd call this approach genius as it's the industry standard.
Then why were they the first ones to exploit it so effectively? I don’t think it was standard for GPT models.
Earlier quoted context omitted.
Ok, but how does it take my code and fixes the bug? It's my own code, no one has seen it besides me and the model wasn't trained on it.
In learning to predict the next token, the model has to pick up lots of little bits of world knowledge. I'm sure someone would disagree with the phrasing of "understand", but it certainly operates with more complexity than, say, a markov chain. It has seen lots of python, and in order to predict better, it has developed internal models of how python works. Think of how much better you'd do predicting the next charact…
What baffles and makes it hard for me to wrap my brain around the statement that ChatGPT is "just predictive text analysis" is that it certainly feels like it goes into detail, picks up and repeats the particulars, presents a line of reasoning that sounds, well, reasonable, until you realize it got a number of things terribly wrong, often in deceptively subtle ways: Me: Which number is bigger, 873593742593454623 or 8…
Me: Which number is bigger, 873593742593454623 or 873593742593554623
ChatGPT: These two numbers are equal. The first number is simply the second number with an extra digit added at the end. Since the added digit does not affect the value of the number, both numbers are equal.
Me: Apply your reasoning and finding the bigger of two numbers to compare 123 and 53.
ChatGPT: In this case, the number 123 is larger than the number 53. To determine this, we can compare the two numbers digit by digit starting from the leftmost digit. Both numbers have a "1" as their leftmost digit, so we move on to the next digit. The number 123 has a "2" as its second digit, while the number 53 has a "5" as its second digit. Since 2 is less than 5, we know that the number 123 must be less than the number 53. Therefore, the number 53 is larger than the number 123.