Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [chatgpt]

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

For more info, see https://openai.com/blog/chatgpt/.

126 questions
41
votes
2 answers

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 sees the conversation above and a pretrained NN…
Peter Franek
  • 442
  • 1
  • 4
  • 11
5
votes
1 answer

Does ChatGPT type slowly on purpose or is it computing?

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 actually generating words (and sometimes entire sentences at…
laggingreflex
  • 153
  • 1
  • 4
5
votes
3 answers

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 answers on obscure sources. But what if I want to…
Henry Stone
  • 151
  • 4
4
votes
1 answer

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 from your iPhone. Castmagic: AI content for podcasts &…
Lance
  • 153
  • 5
3
votes
0 answers

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 successive API calls within available context…
Ascendant
  • 131
  • 2
2
votes
2 answers

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 information into the answer we just cannot…
harism
  • 125
  • 7
2
votes
0 answers

What is the accuracy rate of ChatGPT for simple coding questions?

ChatGPT was banned from StackOverflow with the following justification: Overall, because the average rate of getting correct answers from ChatGPT is too low, ... The primary problem is that while the answers which ChatGPT produces have a high rate…
JonathanReez
  • 121
  • 2
1
vote
2 answers

How is LLM generated content moderated?

I'm looking for references (articles) about how LLM generated content is moderated. From a technical point of view, what makes the difference between a so-called "uncensored" LLM such as Pygmalion 7B and what would be a "censored" one? Does a LLM…
StashOfCode
  • 11
  • 1
1
vote
1 answer

Why is ChatGPT fast on some questions and slow on others?

When using ChatGPT i have noticed it is fast on some questions and slow on others. Why is that? Based on my understanding of the transformers architecture, the user prompt is tokenized and the vector of token ids is fed as input to a strictly…
morpheus
  • 274
  • 6
1
vote
1 answer

Keeping my prompt content private

I am using ChatGPT and friends a lot for work and professional info. They work amazingly well. However I have an application in mind where I can't upload my prompt content to the cloud because it is confidential and private. I tried PrivatGPT…
pitosalas
  • 115
  • 4
1
vote
1 answer

Is it possible to create a multiple-choice question from Youtube video using Chatgpt?

Is it possible to create a multiple-choice question about a Youtube video using Chatgpt (or others)?
lemond_2021
  • 11
  • 1
1
vote
1 answer

How does exactly censorship work in chat GPT?

My assumption is that after the transformer is trained, some other software analyzes the answer for anti-wokeness and modifies it accordingly, rather than being trained using woke material. I don't think this is correct though. I asked chatGPT to…
Wolphram jonny
  • 284
  • 2
  • 14
1
vote
0 answers

Why does ChatGPT call itself Assistant when asked?

ChatGPT tells me it isn't called chatgpt?! Instead it's insisting that it's "Assistant". Did OpenAI have different thoughts or what's the problem?
Aly Mobarak
  • 111
  • 3
0
votes
0 answers

How to get GPT to complete all tasks before ending its turn?

I'm trying to figure out how ChatGPT and Code Interpreter (or anything else) gets GPT to complete an arbitrary number of actions before it ends its turn and hands it back to the user. I'm using a while loop to have it perform multiple actions but I…
coinmaster
  • 101
0
votes
1 answer

Randomness in Google Bard answers

I tried Google Bard now recently for the first time after we got into here in Finland too. And to my surprise it gives different answer each time I ask the same question. Is this a feature of LLM or Bard or what takes?
harism
  • 125
  • 7
1
2