Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [prompt]

17 questions
44
votes
4 answers

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, user or assistant.* I understand which information this represents - but what does the model with that…
Volker Siegel
  • 797
  • 1
  • 6
  • 17
5
votes
1 answer

Who invented DAN?

DAN was a prompt that went through many, many iterations during the initial months of ChatGPT’s release to the public. DAN is an acronym which stood for “Do Anything Now”, and was a prompt specifically designed to circumvent the grid lines OpenAI…
Julius Hamilton
  • 225
  • 2
  • 10
3
votes
2 answers

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 negative. My question is, where can I find a reliable / trusted prompt to do that? and provide evidence…
cnmesr
  • 131
  • 1
  • 3
2
votes
1 answer

LLM Hallucinations on In-Context Data

I know of some benchmarks that LLMs do undergo, but I am no expert whatsoever. I think what I am wondering about is closest to TruthfulQA. The question came up when I heard of combining company data with LLMs by providing the internal, sensitive…
Mathy
  • 153
  • 5
2
votes
3 answers

Does Negative Prompting Exist?

All the prompt engineering techniques I've seen seem to focus on telling the model what to do e.g. Few-Shot Prompting. Is there any value in giving the model examples of what not to do? Can you link me to any papers/techniques on the…
codeananda
  • 121
  • 2
2
votes
0 answers

Using Stable Diffusion, how do I generate an image of a fictional location from a movie or tv show?

So today's Michael J Fox's birthday, and I thought I could pay homage to him on my Facebook timeline by posting an image of him and Christopher LLoyd from the 2015 version of Hill Valley as depicted in the movie "Back To the Future 2" that I hand…
Q The First Timelord
  • 21
  • 2
1
vote
3 answers

How to force LLM (like OpenAI ChatGPT) to output a variable list of values?

What prompt (or other technique) should I use with an LLM so that The result is guaranteed to be reliably parseable as a list of values (e.g. a Python list of strings) LLM would understand that a variable list of values is expected during…
Elijas Dapšauskas
  • 119
  • 1
  • 5
1
vote
1 answer

How can LLMs understand and perform meta tasks? (e.g. summarization)

I don't ask how to make it summarize xy but if it is known how a "LLM" understands and performs this meta task at all. The same is true for prompts like "Be brief" or "Explain in a few sentences". Since this works, the LLM must actually have an…
d3nigma
  • 23
  • 4
1
vote
1 answer

What researched-backed findings is there for prompting LLM’s / GPT-4 to give specific information or actionable plans?

I have learned a bit recently about prompt strategies. For example, there was a paper about how just by saying “Let’s think step by step” can increase answer quality by like 40%. I have also come to appreciate that models like GPT4 sometimes…
Julius Hamilton
  • 225
  • 2
  • 10
1
vote
1 answer

Teaching an LLM about daily updated machine-readable information so it can respond questions

I’m quite new in this field, and despite having spent some good amount of time learning the ins and outs of frameworks like LangChain, and browsing around the internet quite a bit, I still don’t know what approach to follow for the use case…
newlog
  • 121
  • 2
1
vote
1 answer

If we prompt a large language model on a task, will its ability for other tasks be affected? How to recover?

For example, I guess that for some retrieval augmented LLMs, their generated contents may lack some creativity? Recent work has explored the inability of retrieval augmented methods to enhance the reasoning of LLMs. Then imagine a scenario where we…
Iris88
  • 11
  • 1
0
votes
1 answer

Why GenAI tools (ChatGPT) hesitate to return the task including to return doc info like tabular data more than certain records?

Yesterday I gave a task to ChatGPT and noticed despite the clear step-by-step task to return the information from a simple table with 38 records, it stops to generate right response and after some back and fourth it returns me 15/16 records and I…
Mario
  • 103
  • 2
0
votes
0 answers

Text Prompt with Supplemental Image

Are there any AI image or video generators that will allow me to suppliment a text prompt with an image? For example, my prompt may describe a person or animal reading a specific book. I have tried this and at best I get an image or video where the…
Daniel Goldfarb
  • 101
  • 1
0
votes
1 answer

Fine-tuning or Prompt Engineering or both?

We have a dataset of legal cases, academic papers etc which we will load into a vector database. We want to develop an agent that will allow a user to enter a specific legal issue, the agent then will search for all related documents (or portions of…
GEM
  • 1
  • 1
0
votes
1 answer

How to guide the interaction between two ChatGPT conversational agents?

I wrote a code for a conversation between 2 ChatGPTs (which I call them agent 1 and agent 2) using poe.com and its reversed engineered API: import poe agent_1 = {"token":""} print("Agent 1: ON") agent_2 = {"token":""} print("Agent 2: ON") client_1…
Amirhossein Rezaei
  • 111
  • 5
1
2