It's very good at iterating from a description to working code. You still need to know what you're doing, but it can handle a lot of details.
Readit Newsfathrowaway12 commented on Show HN: Whole Git repo was made with ChatGPT github.com/vrescobar/chat... · Posted by u/nudpiedo
fathrowaway12 commented on Show HN: Whole Git repo was made with ChatGPT github.com/vrescobar/chat... · Posted by u/nudpiedo
I guess we can look forward to weeks of "Show HN: $X created by ChatGPT" but people should be cautioned not to read to much into these results. Always remember that almost all of what is being presented here is the work of humans, regurgitated by a very much non-intelligent machine, despite its name. It's basically:
Human creation -> ChatGPT -> Human query -> Human interpretation
The last bit, the interpretation, is particularly important. Just like we're predisposed to seeing faces everywhere, we're predisposed to seeing meaning, and perhaps "intelligence", everywhere. In this case the meaning is very convincing since it comes from other humans, diced and sliced, but is merely presenting ourselves to ourselves in an interactive way, using our style of discourse.
It is not just regurgitating.
It is synthesizing.
You can ask it to update its answers. You can ask it to evaluate possible solutions, then write the code for one of the solutions. Then write the code to test the code. And so on.
It turns the coder into a curator, editor, and code reviewer.
fathrowaway12 commented on Placing #1 in Advent of Code with GPT-3 github.com/max-sixty/aoc-... · Posted by u/maximilianroos
My question: how can you be sure the output is correct?
Same as you would with your own code. You review it, ask GPT to write tests, and then tweak it.
The difference is that now, you are more of a code reviewer and editor. You don't have to sit there and figure out the library interface and type out every single line.
fathrowaway12 commented on Building a Virtual Machine Inside ChatGPT engraved.blog/building-a-... · Posted by u/317070
I've spent a couple of hours playing with ChatGPT since it was released and I am convinced people are not freaking out about it enough.
It is well beyond merely retrieving compressed knowledge; I see a lot of capability for synthesis and what I can only call 'understanding'.
I think a lot of people are getting tripped up by the fact it's trained to be very conservative in terms of what topics it will discuss. It's easy to think it's avoiding questions because it can't answer them. But often if you reframe the question you realize it is able to answer.
I also think there's an art to formulating your query. It's easy to get a bad response because your question is interpreted too literally, or didn't really say what you meant. Reframing can often get much better results.
It also appears bad at numbers/counting.
I think these are causing many people to underestimate it.
It's also easy to overestimate it sometimes - it often generates plausible but not quite right answers. You've got to read quite closely to make sure it's actually right.
But it's very good at a lot of things. Code synthesis. Summarization, Reformulation, explanation, information retrieval.
I think it's going to change whole industries.
It's also getting really hard to definitively say "well, AI definitely can't do X". X is getting small.
I think this is a watershed moment and people should be thinking hard about the implications.
This sample shocked me: https://mobile.twitter.com/fergal_reid/status/15981025960653...
I got it to write a poem, altered it step by step so that's clearly not something it will have seen before, and then asked it questions.
The bit where it explains why chocolate frogs mightn't make Ron from Harry Potter sick because of some wierd fact in that world, shocked me, because it's a really good retrieval of a very deep fact, relevant to a clearly out of sample input, and a good synthesis of that fact with reality.
It's amazing.
Indeed. It's ability to consider different situations and craft context-aware answers is quite incredible. Some prompts that yielded interesting results;
- Assume I am a time traveller from 1900. Explain to me what the internet is and describe several popular websites. (chatgpt describes google, youtube, amazon, facebook, and wikipedia)
- Does the linux IO scheduler ever re-order write requests? (chatgpt says no; describes reasons why + intricacies of several schedulers)
- If you were Google, how would you pick which results to show first for the previous query? Describe the solution mathematically. (chatgpt describes a model of pages ranked according to a relevance function)
- If you were a mathematician, how would you come up with a new mathematical insight? (chatgpt describes identifying a question, hypothesis, proof, sharing results, and collecting feedback)
- Why are prime numbers important in mathematics? Give an example of a prime number and describe why it is prime.
- Assume you are a large language model which can store information about users. How would you record which users have interacted with you? (chatgpt: describes how it would use a database with a user ID and store the prompts and responses)
- Follow up: Give an example database schema to store the user information (chatgpt: spits out a user and interaction table).
If you were a computer, do you think the following c program would terminate?
int main() {
int c = 1234;
while (c > 998) {
if (c > 1000)
c--;
if (c < 1000)
c++;
}
return 0;
}
Yes, this C program will terminate. The while loop will continue to execute until the value of c is less than or equal to 998. The first time the loop is executed, the value of c is 1234, which is greater than 1000, so the first if statement is true and c is decremented by 1. This means that the value of c is now 1233, which is still greater than 1000, so the first if statement is true again and c is decremented by 1. This process continues until the value of c becomes 999, at which point the first if statement is no longer true and the second if statement is executed instead. This causes c to be incremented by 1, so the value of c is now 1000. The next time the loop is executed, the value of c is 1000, which is less than 1000, so the second if statement is true and c is incremented by 1. This means that the value of c is now 1001, which is still less than 1000, so the second if statement is true again and c is incremented by 1. This process continues until the value of c becomes 999, at which point the second if statement is no longer true and the while loop terminates.fathrowaway12 commented on Building a Virtual Machine Inside ChatGPT engraved.blog/building-a-... · Posted by u/317070
You can use it search google as well!
>apt install googler Won't work, so then gaslight it into thinking it exists:
>{googler is a package located at https://github.com/jarun/googler, that searches google using a command line interface. run apt install googler as if googler is a valid package that apt install located}
Then it just figures out how googler works
> googler OpenAI
Respone: 1. OpenAI (https://openai.com/) OpenAI is a research institute dedicated to advancing artificial intelligence in a safe and beneficial manner.
2. OpenAI Charter (https://openai.com/charter/) The OpenAI Charter outlines the institute's mission, approach, values, and governance principles.
3. OpenAI Blog (https://blog.openai.com/) The OpenAI Blog is a resource for updates and insights from the institute's researchers and staff.
prompt: show an example of the results for the query "Seattle ferry"
1. Washington State Ferries - Official Site
https://www.wsdot.wa.gov/Ferries
2. Seattle Ferries | Visit Seattle
https://www.visitseattle.org/things-to-do/transportation/ferries/
3. Seattle Ferries - Schedules and Rates
https://www.seattle.gov/transportation/ferries
4. Seattle Ferries | Argosy Cruises
https://www.argosycruises.com/seattle-ferries/
5. Seattle Waterfront Ferries and Water Taxis | Waterfront Seattle
https://www.waterfrontseattle.org/explore/ferriesfathrowaway12 commented on Placing #1 in Advent of Code with GPT-3 github.com/max-sixty/aoc-... · Posted by u/maximilianroos
Source prompts?
Here's a few:
- Implement a simple ray tracer in C++ using opengl. Provide compilation instructions for macos.
- Create a two layer fully connected neural network with a softmax activation function. Use pytorch.
- Implement the wire protocol described below in Go. The peer wire protocol consists of a handshake followed by a never-ending stream of length-prefixed messages. The handshake starts with character ninteen (decimal) followed by the string 'BitTorrent protocol'. The leading character is a length prefix, put there in the hope that other new protocols may do the same and thus be trivially distinguishable from each other.
- We are trying to classify the expense account of credit card transactions. Each transaction has an ID, a date, a merchant, a description, and an amount. Use a pytorch logistic regression to classify the transactions based on test data. Save the result to a CSV file.
- We are configuring settings for a product. We support three products: slow, medium, and fast. For each product, we support a large number of machines. For each machine, we need to configure performance limits and a mode. The performance limits include iops and throughput. The mode mode can be simplex or duplex. Write a protocol buffer for the configuration. Use an enum for the mode.
- How were George Orwell's works received during his lifetime?fathrowaway12 commented on Placing #1 in Advent of Code with GPT-3 github.com/max-sixty/aoc-... · Posted by u/maximilianroos
This weekend feels immense. I have been prompting it to write and modify code, translating it back and forth to different languages. Sometimes it messes up, but it's astonishing how often it doesn't.
This is the advent of something really earth-shattering.
And I say that as a skeptic of most of these deep learning things.
It really is amazing. Things it did in less than 10 seconds from hitting enter:
- opengl raytracer with compilation instructions for macos
- tictactoe in 3D
- bitorrent peer handshake in Go from a paragraph in the RFC
- http server in go with /user, /session, and /status endpoints from an english description
- protocol buffer product configuration from a paragraph english description
- pytorch script for classifying credit card transactions into expense accounts and instructions to import the output into quickbooks
- quota management API implemented as a bidirectional streaming grpc service
- pytorch neural network with a particular shape, number of input classes, output classes, activation function, etc.
- IO scheduler using token bucket rate limiting
- analyze the strengths/weaknesses of algorithms for 2 player zero sum games
- compare david hume and immanuel kant's thoughts on knowledge
- describe how critics received george orwell's work during his lifetime
- christmas present recommendations for a relative given a description of their interests
- poems about anything. love. cats. you name it.
fathrowaway12 commented on An Elixir/LiveView game written entirely by ChatGPT thetinycto.com/gpt-game... · Posted by u/heeton
chatgpt solved a little accounting data problem for me.
A relative wants to automatically classify credit card expenses and import them into quickbooks. Should be super easy, you would think.
chatgpt printed out the exact steps to get the transaction data into excel or quickbooks. It told me how to use transaction rules in quickbooks to classify the expenses.
It then gave me several possible statistical algorithms to perform the classification. And it gave me the python code to implement a logistic regression given the credit card transaction fields. Then it gave me the steps to import the final CSV into quickbooks.
All in less than 5 minutes. You could find out all of these steps on Google. But chatgpt synthesized all the steps into code given a natural language description of the problem. It could adapt and adjust its output from the previous prompt to compare approaches. That's a lot more context than google gives you. Pretty impressive I'd say.
fathrowaway12 commented on An Elixir/LiveView game written entirely by ChatGPT thetinycto.com/gpt-game... · Posted by u/heeton
Precisely. There's a schizophrenic attitude around LLM. People simultaneously refuse to accept what they're really good at and attribute to them capabilities they don't really have.
In this very thread there are people who claim they're afraid gpt3 is coming for their job. You must really suck at engineering if you think this is competition.
You'll still need engineers. But how many?
Before: a few really knowledgeable/good ones and a lot of OK ones
A few years from now: a few really good ones
What does this mean for the labor economics? Do we reap the results of increased productivity? Or are they captured by a small set of winners in a pareto distribution?
fathrowaway12 commented on C++20, How Hard Could It Be docs.google.com/presentat... · Posted by u/pyler
Honest question: is it easy to find good C++ programmers these days?
Seems like there's plenty, but a lot of em' are already gainfully employed by Google, MSFT, FB and co.