Questions tagged [chatgpt]

For questions related to the OpenAI ChatGPT model/chatbot, which was trained by Reinforcement Learning from Human Feedback (RLHF).

Filter by
Sorted by
Tagged with
54 votes
2 answers
46k views

How does ChatGPT retain the context of previous questions?

One of the innovations with OpenAI's ChatGPT is how natural it is for users to interact with it. What is the technical enabler for ChatGPT to maintain the context of previous questions in its answers? ...
milez's user avatar
  • 981
50 votes
3 answers
23k views

Was ChatGPT trained on Stack Overflow data?

Has ChatGPT used highly rated and upvoted questions/answers from Stack Overflow in its training data? For me it makes complete sense to take answers that have upwards of 100 upvotes and include them ...
Nicolas Zein's user avatar
41 votes
2 answers
30k views

How is ChatGPT aware of today's date?

I asked ChatGPT (3.5 and 4) about current date and (s)he answered correctly. In subsequent conversation (s)he was not able to explain how (s)he has this knowledge. I always thought that the model only ...
Peter Franek's user avatar
39 votes
7 answers
16k views

Is the "Chinese room" an explanation of how ChatGPT works?

Sorry if this question makes no sense. I'm a software developer but know very little about AI. Quite a while ago, I read about the Chinese room, and the person inside who has had a lot of training/...
Guntram Blohm's user avatar
36 votes
1 answer
38k views

Meaning of roles in the API of GPT-4/ChatGPT (system/user/assistant)

In the API of GPT-4 and ChatGPT, the prompt for a chat conversation is a list of messages, each marked as one of three roles: system, ...
Volker Siegel's user avatar
34 votes
6 answers
11k views

How does an AI like ChatGPT answer a question in a subject which it may not know?

After seeing StackOverflow's banning of ChatGPT, I explored it out of curiosity. It's marvellous as it can write code by itself! Later to check if it knows chess as well like Google-Deepmind's ...
iammilind's user avatar
  • 443
29 votes
4 answers
36k views

Why is ChatGPT bad at math?

As opposed to How does ChatGPT know math?, I've been seeing some things floating around the Twitterverse about how ChatGPT can actually be very bad at math. For instance, I asked it "If it takes ...
Mithical's user avatar
  • 2,905
27 votes
4 answers
15k views

Why do ChatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the ...
TylerDurden's user avatar
24 votes
5 answers
12k views

Why does ChatGPT fail in playing "20 questions"?

IBM Watson's success in playing "Jeopardy!" was a landmark in the history of artificial intelligence. In the seemingly simpler game of "Twenty questions" where player B has to ...
Hans-Peter Stricker's user avatar
24 votes
4 answers
12k views

How does ChatGPT know math?

ChatGPT is a language model. As far as I know and If I'm not wrong, it gets text as tokens and word embeddings. So, how can it do math? For example, I asked: ME: Which one is bigger 5 or 9. ChatGPT: ...
Peyman's user avatar
  • 564
18 votes
6 answers
19k views

How much energy consumption is involved in Chat GPT responses being generated?

I note this question was deemed off-topic, so I'm trying to clearly frame this question in terms of scope of response I'm interested in, namely ethics and sustainability issues associated with the ...
wide_eyed_pupil's user avatar
16 votes
2 answers
7k views

Why does ChatGPT not give the answer text all at once?

When ChatGPT is generating an answer to my question, it generates it word by word. So I actually have to wait until I get the final answer. Is this just for show? Or is it really real-time generating ...
Sander van den Oord's user avatar
15 votes
6 answers
7k views

Why do many AI bots feel the need to be know-it-alls?

Having used various AI bots often over recent months, I noticed that often it will claim to know something, even if it doesn't. It would then either explain something which is clearly nonsense, or by ...
ben svenssohn's user avatar
10 votes
2 answers
3k views

Are GPT-3.5 series models based on GPT-3?

In the official blog post about ChatGPT from OpenAI, there is this paragraph explaining how ChatGPT model was trained: We trained this model using Reinforcement Learning from Human Feedback (RLHF), ...
iMad's user avatar
  • 203
9 votes
1 answer
1k views

What causes ChatGPT to generate responses that refer to itself as a bot or LM?

ChatGPT occasionally generates responses to prompts that refer to itself as a "bot" or "language model." For instance, when given a certain input (the first paragraph of this ...
Obie 2.0's user avatar
  • 192
8 votes
4 answers
50k views

OpenAI ChatGPT gives a network error at long responds. How can I fix it? [closed]

When OpenAI's ChatGPT replies with a very long answer, it will return a network error. When you check the network console, the POST request will fail with a ...
Lars Flieger's user avatar
6 votes
5 answers
11k views

How is GPT 4 able to solve math?

How can GPT 4 solve complex calculus and other math problems. I believe these problems require analytical reasoning and ability to compute numbers. Does it still use a LLM to complete this process or ...
desert_ranger's user avatar
6 votes
1 answer
2k views

Why does ChatGPT create fake code?

ChatGPT has been a big thing lately. It also makes a lot of mistakes. For example, it creates fake functions of a package and tells it as it works for real. I was wondering how that works. Why is it ...
Quinten's user avatar
  • 185
6 votes
2 answers
1k views

Would self-hosting ChatGPT be feasible, w.r.t. computation costs?

Suppose the pre-trained, current date (2023-02-04) ChatGPT model was released open source, would it be feasible for regular users to interact with the model on a self-hosted computer? Assumptions I ...
a.t.'s user avatar
  • 243
6 votes
3 answers
3k views

How is ChatGPT able to repeat random numbers?

From what I understand, ChatGPT is just a fancy neural network, operating like a sophisticated Markov Chain generator. As such, it should only be able to generate tokens that are in its training ...
yters's user avatar
  • 387
6 votes
1 answer
2k views

How was ChatGPT trained?

I know that large language models like GPT-3 are trained simply to continue pieces of text that have been scraped from the web. But how was ChatGPT trained, which, while also having a good ...
HelloGoodbye's user avatar
6 votes
1 answer
649 views

How much of the ChatGPT output is copied from its training set (vs. being abstractively generated)?

One of the main concerns of using ChatGPT answers on Stack Exchange is that it may copy verbatim or almost verbatim some text from its training set, which may infringe the source text's license. This ...
Franck Dernoncourt's user avatar
6 votes
1 answer
742 views

How can a language model keep track of the provenance of the main knowledge/sources used to generate a given output?

One of the main criticisms against the use of ChatGPT on Stack Exchange is that it doesn't attribute the main knowledge/sources used to generate a given output. How can a language model keep track of ...
Franck Dernoncourt's user avatar
6 votes
2 answers
550 views

How does GPT-based language model like ChatGPT determine the n-th letter of a word?

I understand that GPT models process input text by converting words into tokens and then embedding vectors and do not process them letter by letter. Given this approach, I am curious to know how a ...
Peyman's user avatar
  • 564
5 votes
3 answers
2k views

How do I get chatGPT to include custom knowledge?

While studying chatGPT's thought process, I asked it to list ten story ideas for an old and fairly niche tabletop roleplaying game (GURPS Reign of Steel). It did very well, so clearly, it can base ...
Henry Stone's user avatar
5 votes
1 answer
4k views

Does ChatGPT type slowly on purpose or is it computing? [duplicate]

When you give ChatGPT a prompt, does it A) generate the entire response instantly (at least on the server), but then "buffers" it slowly to the end user (for whatever reason) or B) it's ...
laggingreflex's user avatar
5 votes
0 answers
634 views

Are "prompt engineering" and "prompt design" used as synonymous?

Are "prompt engineering" and "prompt design" used as synonymous / equivalent terms on the day to day communications (not research papers) in Artificial Intelligence community ? Do ...
Rubén's user avatar
  • 159
4 votes
2 answers
1k views

ChatGPT claims that it doesn't get information from anywhere, so can't say why it gave a blatantly false statement. How is that possible?

I asked ChatGPT a question, and its response included this statement: In "The Ruling Class" film, which was released in 1972, Patrick McGoohan played the role of Bishop Lampton. Unlike ...
Ray Butterworth's user avatar
4 votes
4 answers
4k views

How does ChatGPT respond to novel prompts and commands?

So I understand how a language model could scan a large data set like the internet and produce text that mimicked the statistical properties of the input data, eg completing a sentence like "eggs ...
ak0000's user avatar
  • 205
4 votes
1 answer
779 views

How can Transformers handle random sequences?

I have asked ChatGPT the following: Can you concatenate jfef9230rj2mreg90r23ewfrn02eqwdk and 32ir20r3i2ofg90r32kee? And without any error the model produces: ...
killertoge's user avatar
4 votes
1 answer
328 views

How do the "built on ChatGPT" apps work in general at a high level?

I see stuff in my Twitter feed like this every day, showing "ChatGPT used to create X new customized/tailored AI feature". ColorGPT: Generate a color hex name from real-world color capture ...
Lance's user avatar
  • 153
4 votes
0 answers
3k views

How is ChatGPT maintaining context?

It has been suggested in the answer to this earlier question that it is just remembering a certain amount of recent information. The reference used is this post by OpenAI which says that ChatGPT ...
Kay999's user avatar
  • 41
3 votes
3 answers
3k views

Do AI-based code-generators guarantee correct output?

I haven't spent much time looking at AI-based code-generators. What mechanism is used to generate code and how is it different than standard NLP?
FourierFlux's user avatar
3 votes
1 answer
11k views

Does chatGPT learn or remember from (public) user input? Will it 'fess up to it? I could not get it to reveal [closed]

It started with a question inspired by this video: New Research Suggests to Put AI to Sleep https://youtu.be/0yuQlbCkTJ0 She says: "In this video I discuss a new research paper which suggest a ...
Ectosoprophilous's user avatar
3 votes
2 answers
4k views

How to Formulate a realiable ChatGPT Prompt for Sentiment Analysis of a Text, and show that it is reliable?

I have a dataset which consists of like.. 400000 sentences and I want give each sentence to ChatGPT so it classifies each sentence as positive or ...
cnmesr's user avatar
  • 131
3 votes
1 answer
1k views

Does ChatGPT use different transformers for different downstream tasks?

What I find hard to figure out is whether ChatGPT guesses from the prompt the downstream NLP task to be performed - text summary, text generation, question-answering, doing logic or arithmetic, ...
Hans-Peter Stricker's user avatar
3 votes
1 answer
7k views

OpenAI: What is the difference between model "gpt-3.5-turbo" and "gpt-3.5-turbo-0301"?

I have performed an API call to OpenAI's endpoint https://api.openai.com/v1/models . The endpoint lists the currently available engines, and provides basic information about each one such as the owner ...
knb's user avatar
  • 165
3 votes
1 answer
841 views

Why do we need RL in RLHF? [closed]

In RLHF, the reward function is a neural network. This means we can compute its gradients cheaply and accurately through backpropagation. Now, we want to find a policy that maximizes reward (see https:...
DeltaIV's user avatar
  • 194
3 votes
1 answer
632 views

Process 2TB worth of conversational data hoarded over 40 years. How can I pass this into GPT to ask questions about it?

I'm still very new to this stuff. I have close to 2TB worth of data hoarded from IRC chats to everyday chats with friends and family. But is there a way to pass in this much data into GPT to ask ...
Patoshi パトシ's user avatar
3 votes
1 answer
644 views

What exactly is the future of mathematical analysis that can be dealt with AI (especially in the automated theorem proving)?

As a student of numerical analysis, I can see how mathematical analysis involved in making a language program specifically in the convergence analysis of an approximation method. But, while chatting ...
Messi Lio's user avatar
  • 133
3 votes
0 answers
255 views

What strategy does ChatGPT use to manage its context in very lengthy conversations?

I'm asking specifically about ChatGPT4, but the question could apply to either that or 3.5. When you use the ChatGPT API, it's of course up to you to manage conversation history and include that in ...
Ascendant's user avatar
  • 131
3 votes
0 answers
348 views

How is ChatGPT able to perform part-of-speech tagging?

ChatGPT seems to be able of part-of-speech tagging: How can its – possibly emergent – ability to perform part-of-speech tagging be understood?
Hans-Peter Stricker's user avatar
2 votes
2 answers
2k views

What makes ChatGPT a generative model?

I'm working my way through how ChatGPT works. So I read that ChatGPT is a generative model. When searching for generative models, I found two defintions: A generative model includes the distribution ...
Ai4l2s's user avatar
  • 121
2 votes
2 answers
292 views

Are LLM hallucination necessarily a bad thing?

I've been pondering over this for a while now: is the so-called hallucinating necessarily a problem in LLM or in AI in general? What it stands for anyway, maybe the model is trying to crunch so much ...
harism's user avatar
  • 125
2 votes
1 answer
61 views

What are these special "AI chips" actually used for?

To make an AI / LLM, like ChatGPT, you need two things: To create the LLM. This includes training it, etc. Very expensive from computation perspective. Run the LLM to answer user queries. For ...
ineedahero's user avatar
2 votes
1 answer
87 views

Can models like chatGPT learn functions with infinite domain or range

Lets assume two types of prompt: A fixed prompt for which reasonable responses can be infinite. For example: > output a random number > output a palindrome ...
Sayam Qazi's user avatar
2 votes
2 answers
4k views

What temperature would you recommend for the chatgpt api?

I believe that it is recommended to have a tiny bit of temperature with GPT 3 even for noncreative tasks like 0.2 or something (I am not entirely sure why). Last I checked, and if I remember correctly,...
userrandrand's user avatar
2 votes
2 answers
2k views

Does ChatGPT imply that the direction of knowledge graph is unpromising?

In this question I asked about the role of knowledge graphs in the future, and in this answer I found that If curation and annotation are not sufficient, the knowledge base maybe cannot apply in AI. ...
Lerner Zhang's user avatar
2 votes
1 answer
149 views

Would a transformer trained on highly specific material be as usable as a commercial product like ChatGPT?

Soft question here. I was recently learning a bit about how it is feasible to train a transformer on a personal computer like an M1 Mac. I have been told that the model could have 1-3 million ...
Julius Hamilton's user avatar
2 votes
1 answer
108 views

Could hallucinations be the demise of the AI hype? [closed]

For quite some time now, I have been evaluating ChatGPT's capability to deliver accurate and helpful responses. While its performance is undeniably impressive, the issue of hallucinations poses a ...
machine_1's user avatar
  • 133