- #36
- 11,308
- 8,744
That's a good example. It can write a correct program for you, but it can not predict what the numerical results of the program will be.bob012345 said:It wrote a Python program. It even documents the program!
That's a good example. It can write a correct program for you, but it can not predict what the numerical results of the program will be.bob012345 said:It wrote a Python program. It even documents the program!
Copilot is based out of GPT-3. People say it's great, though I haven't used it. Note that it's not free; ≈$100 per year for personal use.anorlunda said:In particular https://github.com/features/copilot
I got in with a "free trial". But access to that may be limited by country.Wrichik Basu said:Copilot is based out of GPT-3. People say it's great, though I haven't used it. Note that it's not free; ≈$100 per year for personal use.
I believe that is accurately what they did. There is no official confirmation, obviously. Copilot is exclusively trained on code.anorlunda said:Did they feed the github code as training material for the neural net
Yet the examples linked show that it does very well on understanding natural language, so I presume that it shares that ability with ChatGPT.Wrichik Basu said:I believe that is accurately what they did. There is no official confirmation, obviously. Copilot is exclusively trained on code.
Yes, since it's based on GPT-3.anorlunda said:Yet the examples linked show that it does very well on understanding natural language, so I presume that it shares that ability with ChatGPT.
Wrichik Basu said:Copilot is exclusively trained on code.
I should have used "specially" instead of "exclusively". Definitely, it has language training. But then, Github trained it on code from a huge number of repos to make it what it is today.Jarvis323 said:Are you sure? GPT stands for Generative Pretrained Transformer. You start with something which has already been trained on a huge amount of text data, and then you fine tune it for specialized purposes. If it is based on GPT-3, I would think that would mean it retains the pretrained part, but is just fine tuned with lots of additional training on code?
Yes, this is a great way to use ChatGPT. Start by assuming your students will probably try to use it, so educate them on how to do it, and also, why they shouldn't rely on it! Then give them a homework assignment that looks like, "put the following problems to ChatGPT, and prompt it until it gets the answers correct. You will be graded on your prompts, and whether or not you succeeded in leading ChatGPT to the correct result in a way that simulates learning by the bot."bob012345 said:Alternatively, if the students know they have to coach ChatGPT to get things right they will be learning the physics by doing that. For example, in the case above of an elastic collision, ChatGPT needs to be told to use both conservation of momentum and conservation of energy at the same time.
Remember to be careful with Chat GPT or artificial intelligence. It should not be used on forums, as they are not considered a source. However, these technologies are getting advanced. Scary that software can almost pass lawyer exams nowadays. :)anorlunda said:I've been experimenting with ChatGPT. Some results are good, some very very bad. I think examples can help expose the properties of this AI. Maybe you can post some of your favorite examples and tell us what they reveal about the properties of this AI.
(I had problems with copy/paste of text and formatting, so I'm posting my examples as screen shots.
View attachment 319784
That is a promising start.
But then I provided values V=1, R1=1, R2=2, R3=3 and asked for the value of I. At first, it said 1/2A. I said, "Not correct." It said "Sorry, 0.4A." I said, "No, the right answer is 0.45." It said, "Sorry, you're right." What the heck was going on there? I did more tests:
View attachment 319785
But 34893 *39427 is actually 1,375,726,311 and 1+((2*3)/(2+3)) is actually 2.2
View attachment 319787
Google recognizes numerical expressions and it sends them to a calculator logic engine. It also recognizes geographical questions like "Pizza near Mount Dora FL" and sends them to another specialized logic engine.
ChatGPT works on the basis of predicting which words follow logically. AFAIK, that is the only knowledge base it has so far. I expected it to have found millions of references to 2+2=4 in Internet text, but few or no references to 34893+39427 yet it got that right. But then it got 34893*39427 wrong, yet the wrong answer seemed like an attempted guess. So I don't understand how it really did get the right sum but the wrong product via word prediction.
Clearly, ChatGPT needs other logical engines beyond word prediction, and syntactical analysis to figure out which engine to use. One of these days, that will probably be added as a new feature.
It also suggests that science and engineering which use equations and graphics, will do far worse with ChatGPT than fields like law which is almost all textual. Indeed, others have found that ChatGPT is already close to being able to pass the bar exam for lawyers.
fluidistic said:Is the French word cauchemar understandable in other languages?
chatGPT said:Yes, the French word "cauchemar" is understandable in other languages, especially in languages that have borrowed heavily from French or have a similar origin.
In English, for example, "cauchemar" is commonly translated as "nightmare," which is a word that comes from the Old English "nyhtcmaran," meaning "evil spirit that oppresses people during sleep."
In other languages, such as Spanish ("pesadilla"), Italian ("incubo"), Portuguese ("pesadelo"), and Romanian ("coșmar"), similar words are used to refer to a bad dream or a nightmare. These words also have their origins in Latin or Romance languages like French.
So, while the spelling and pronunciation may vary slightly, the concept of a "cauchemar" or "nightmare" is generally understood across different languages.
fluidistic said:Hmm, how is "pesadilla" similar to "cauchemar"?
chatGPT said:"Pesadilla" is the Spanish word for "nightmare," and it is similar to "cauchemar" in several ways. Both words have similar meanings, as they refer to a bad dream or a terrifying experience during sleep.
Additionally, both "cauchemar" and "pesadilla" are derived from similar roots. "Cauchemar" comes from the Old French word "caucher" meaning "to press," and "mar" meaning "ghost" or "spirit," which suggests a sense of being oppressed or haunted by a malevolent spirit during sleep. "Pesadilla," on the other hand, comes from the Spanish word "pesado," meaning "heavy," and "illa," a diminutive suffix, which together conveys the sense of a heavy or burdensome experience during sleep.
Furthermore, both French and Spanish are Romance languages, meaning that they share a common origin in Latin, which makes it easier for speakers of these languages to understand and recognize similarities between their respective vocabularies.
fluidistic said:Is the French word "cauchmar" phonetically similar in other languages? If so, in which languages?
chatGPT said:The phonetic similarity between the French word "cauchemar" and the equivalent term in other languages will depend on the specific language in question and the degree to which it has been influenced by French or shares common linguistic roots with French.
For example, in Spanish, the word for "nightmare" is "pesadilla," which is not particularly phonetically similar to "cauchemar," although the two words share some common features in terms of their derivation and meaning.
In Italian, the word for "nightmare" is "incubo," which is somewhat closer to "cauchemar" phonetically, particularly in terms of the vowel sounds and the emphasis on the second syllable.
In Portuguese, the word for "nightmare" is "pesadelo," which is more similar to the Spanish term "pesadilla" than to "cauchemar," although there are some phonetic similarities between the two words.
In Romanian, the word for "nightmare" is "coșmar," which is not particularly similar to "cauchemar" in terms of its phonetics, although it shares a similar etymology and meaning.
In summary, the degree of phonetic similarity between "cauchemar" and the equivalent term in other languages will vary depending on the language in question and its relationship to French and other Romance languages.
fluidistic said:Could a Polish person understand this French word?
chatGPT said:It is possible that a Polish person may understand the French word "cauchemar" if they are familiar with the French language or have studied it. However, Polish and French are not closely related languages, and the pronunciation and spelling of "cauchemar" may be quite different from what a Polish speaker is accustomed to.
Additionally, the vocabulary of French and Polish is not particularly similar, so a Polish person who is not familiar with French may not be able to guess the meaning of "cauchemar" based on any similarities with Polish words.
In summary, while it is possible that a Polish person may understand the meaning of "cauchemar," it is not a word that would be immediately recognizable to someone who is not familiar with the French language or its vocabulary.
fluidistic said:Well, I think the words "koszmar" and "cauchemar" are phonetically pretty similar, aren't they?
Based on a single encounter with this AI, I would say it is a very "bad" AI, "bad" in terms of understanding what a human asks for, "bad" for giving contradicting answers without mentioning how wrong it in the first place. But I should retry a few million times to draw conclusions.fluidistic said:Yes, you are correct. The Polish word "koszmar" for "nightmare" and the French word "cauchemar" are phonetically similar. Both words share the same "k" sound at the beginning and have a similar number of syllables and stress pattern. Additionally, the meaning of the two words is the same, which could further help a Polish speaker understand the meaning of "cauchemar" if they were to encounter it in a French context.
While Polish and French are not closely related languages, there are some similarities between the two in terms of phonetics and vocabulary due to their shared history as Indo-European languages. As a result, some words in Polish and French may have similar sounds and meanings, even though they are not cognates.
fluidistic said:Please solve the following physics problem "How many times faster would have the Earth to spin for someone based in NYC feel weightless?"
chatGPT said:In order for someone based in NYC to feel weightless, the gravitational force between that person and the Earth must be balanced by a centrifugal force. This can be achieved if the Earth's rotation speed is increased.
The formula for centrifugal force is:
F = m * r * w^2
where F is the centrifugal force, m is the mass of the object, r is the distance from the axis of rotation, and w is the angular velocity (in radians per second).
For a person standing on the surface of the Earth, r is equal to the radius of the Earth, which is approximately 6,371 km.
The formula for gravitational force is:
F = G * m1 * m2 / r^2
where F is the gravitational force, G is the gravitational constant, m1 is the mass of the Earth, m2 is the mass of the person, and r is the distance between the person and the center of the Earth.
For a person standing on the surface of the Earth, r is approximately equal to the radius of the Earth plus the person's height, which we'll assume to be 1.8 meters.
In order for the person to feel weightless, the centrifugal force must be equal in magnitude to the gravitational force. Therefore:
m * r * w^2 = G * m1 * m2 / r^2
Simplifying this equation, we get:
w^2 = G * m1 / r^3
Substituting in the values for G, m1, and r, we get:
w^2 = 3.986 * 10^14 m^3/s^2 / (6,371,000 + 1.8)^3 m^3
Solving for w, we get:
w = 7.905 * 10^-5 radians per second
The current angular velocity of the Earth is approximately 7.292 * 10^-5 radians per second, so the Earth would need to spin approximately 1.08 times faster for someone based in NYC to feel weightless.
. It then corrected itself correctly.fluidistic said:You are still saying "it is characterized by a flow of heat due to the interaction between the temperature gradient and the electric field.". Why do you say it is a flow of heat?
According to Cambridge english dictionary it should be two words. "Firetruck" may be commonly used but it is not the proper spelling.jack action said:
I think it's getting better. It seemed to always agree with me even when I gave it bad information as a test. Recently it stood its ground and told me I was wrong.jack action said:I like how ChatGPT seems to always give the answer you want to hear.
Edward Tian, 22, a Princeton University student studying computer science and journalism, developed an app called GPTZero to deter the misuse of the viral chatbot ChatGPT in classrooms. The app hase racked up 1.2 million (1.2 E6) registered users since January.
He is now launching a new program called Origin aimed at "saving journalism," by distinguishing AI misinformation from fact in online media.
...
GPTZero analyzes the randomness of text, known as perplexity, and the uniformity of this randomness -- called burstiness --- to identify when AI is being used. The tool has an accuracy rate of 99% for human text and 85% for AI text...
I certainly hope that we are not that ?*&?%% ... uh, something or another.Stephen Tashi said:Perhaps people who intend to answer questions will start double checking their proposed answers by consulting ChatGPT instead of Googling.
The ChatGPT issue is more dangerous in that the responses tend to be authoritative while often being wrong leaving the prompter satisfied and accepting the explanation as fact. The prudent prompter should attempt to verify the response from another source.Stephen Tashi said:The self contradictions and errors of ChatGPT responses are no more confusing that the contradictions that happen when several people respond to a post and debate technical and tangential issues. ChatGPT responses are fast compared to responses on forums.
Sorry, no.russ_watters said:Thief?
The trick, although few people are able to do it, is to free your mind and think laterally about what a "policeman" could be, and a "leading" policeman, in particular. Think really laterally: it's nothing to do with crime detection!russ_watters said:[edit] That wasn't a joke, @Tom.G , but I'm not a crossword puzzle/riddle guy.
I'm not a crossword expert either, but I wanted to try with a search engine instead of ChatGPT. The second link DuckDuckGo gave me was to a "crossword solver" site with "police leader?" as the clue (https://www.wordplays.com/crossword-solver/police-leader?), which offered the answer "STING". (I couldn't understand the answer without doing a little bit more research on it; I really don't have a crossword-like mind )PeroK said:I tried giving ChatGPT a cryptic crossword clues and it struggled. This is one of mine, which I made up recently
Leading policeman? (5 letters)
ChatGPT suggested "chief", which is too literal. I pointed out the question mark in the clue, which it then recognised as indicating a tricky aspect, and tried "copse". But, that makes little sense.
I wonder whether any of the intelligent humans on PF can solve it?
That's too literal. That would be a simple crossword, where the answer is just a synonym for the clue. Cryptic means that the answer is hidden in some way. In this case "Leading policeman?" alludes to the lead singer of the band The Police, which is Sting.gleem said:CHIEF