Questions tagged [open-ai]
For questions related to the openAI, including the Gym toolkit.
130 questions
0
votes
0
answers
13
views
Extract answers from users while in conversation
I am building a chatbot that allows users to ask questions based on a 500-word paragraph. However, I also have a set of 5 predefined questions for which I want to collect answers from the users. How ...
2
votes
1
answer
82
views
Does the non-ASR OpenAI API also "use log probability to automatically increase the temperature until certain thresholds are hit" when temperature=0?
I read on https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-temperature (mirror):
temperature. number. Optional. Defaults to 0. The sampling ...
- 3,267
2
votes
1
answer
50
views
What does "use log probability to automatically increase the temperature until certain thresholds are hit" mean with OpenAI ASR with temperature=0
I read on https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-temperature (mirror):
temperature. number. Optional. Defaults to 0. The sampling ...
- 3,267
0
votes
0
answers
28
views
Fine-tuning GPT-4o-mini with JSON-schema
I’m planning to extract structured data from a collection of free-text records—nearly 50,000 entries, each averaging around 200 tokens. I’ve created a comprehensive JSON schema with about 1,300 lines, ...
0
votes
0
answers
31
views
Streaming voice from openai tts and latency issue
I have a set up that connects to openai voice. The openai voice, takes my script and convert it to voice - which is sent to front end.
There is a real latency issue in my set up which I would like to ...
- 101
0
votes
0
answers
11
views
0
votes
0
answers
20
views
Will fine-tuning a LLM on general, domain-specific knowledge improve its performance on specific tasks?
I am fine tuning ChatGPT 4o-mini using instruction finetuning to extract details of a customer's complaints about specific products (scientific instruments) that my company markets.
I provide the ...
- 121
2
votes
1
answer
366
views
Does someone know when GPT5 will be publicly available?
I am planning to write an Android and iOS app to:
Generate texts about french Intelligence Agencies with Artificial Intelligence.
Generate thousands of questions with Artificial Intelligence ...
user86598
0
votes
0
answers
13
views
Application thats compatible with android that allows you to access the wifi signals around you and constructs its own
Can we develop a application thats compatible with android that allows you to access the wifi signals around you and constructs its own?
By continuously encryption data by the wifi signal by ...
2
votes
1
answer
193
views
RAG Pdf chunking and Vector Embeding
I am new RAG Application. Currently I am working in a RAG application where I have to do Ingestion of PDF invoice document and have to fill-up some date from JSON structure and store in NOSQL DB.
My ...
- 21
1
vote
0
answers
43
views
What’s the best way to train a model to change a provided image with the provided instructions?
I have a platform where clients of mine can request changes to designs, using drawings and comments. I want to make an AI feature where clients can illustrate their modification request by providing a ...
- 11
0
votes
0
answers
23
views
Efficient Matching of Sample Requests to Sample Offers Using Large Language Models
I want to discuss an interesting matching problem. We aim to match sample requests with corresponding sample offers. Here are some examples:
Sample Requests:
Need help installing Linux on my old ...
- 101
1
vote
1
answer
63
views
Can you claim copyright over a social media post that is used to train an AI model?
Can user-generated content from social media platforms be considered copyrighted training data for AI models, despite agreements between the platforms and AI companies (note that the users themselves ...
0
votes
0
answers
19
views
How Does AI-Generated Content Differ From Human-Written Content?
How Can I Determine if a Piece of Content Has Been Generated by AI?
- 1
0
votes
0
answers
34
views
How to design a custom openai gym environment to carry out 5G resource slicing?
PROBLEM AT HAND: I have a resource (Bandwidth) of B Hz. I have to distribute the bandwidth B to users as per their requirements. For instance, voice calls would require some amount of bandwidth while ...
0
votes
0
answers
38
views
Parametric noise over Input noise
I came across this research from 2017 that talked about using "Parametric noise" instead of input based noise. I have tried to have it in my PPO based Boid flocking custom environment but ...
- 1
0
votes
0
answers
32
views
in the "reward to go" trick in policy gradient methods, I have a question about the proof?
I am specifically talking about this proof Why does the "reward to go" trick in policy gradient methods work?
where Dennis says 'on ith iteration the outer sum of random variable and ...
0
votes
1
answer
420
views
Train my own LLM on a smaller corpus of text?
Would it be possible to train my own LLM on a smaller corpus of text, lets say some coding documentation that I then want to ask questions about using the model?
If so, are there any recommended ways ...
- 101
0
votes
0
answers
21
views
Unable to Save Generated Data to JSONL File - Always Resulting in "Wrote 0 examples to finetuning_events.jsonl" Message
Issue Description
When attempting to generate JSONL data using Llama Index, the process works well until the final step where the results are saved to a JSONL file. However, every time I try to save ...
- 101
0
votes
0
answers
287
views
Where do you keep track of Chat History for an LLM Chat Application?
I am creating a LLM chat app with LangChain. I am keeping track of the chat history with a simple array that gets sent to the LLM with every prompt. I noticed LangChain also has classes that ...
- 167
0
votes
0
answers
39
views
Do Poe AI, Open AI and Claude AI have the ability to retain information from previous queries or remember previous responses?
Do Poe AI, Open AI,and Claude AI have the ability to retain information from previous queries or remember previous responses?
- 1
0
votes
0
answers
42
views
Do Poe AI, Open AI, and Claude AI generate all answers from training data, including factual and logical answers or from personal information?
Do Poe AI, Open AI, and Claude AI generate all answers from training data, including factual and logical answers or from firsthand personal information?
- 1
0
votes
0
answers
44
views
DDPG input incompatible in OpenAI Gym custom environment
I have a custom OpenAI Gym Boid flocking environment using StableBAselines3 for DDPG. This error I encounter occurred previously due to wrong input size of actions. But my reset function is correct, ...
- 1
0
votes
1
answer
169
views
How does chatgpt interpret prompts? [closed]
First of all, my English isn't very good, please bear with me.
I've heard that chatgpt is a decoder-only model, which doesn't use any encoder model.
How does it interpret our prompts if it doesn't use ...
- 11
1
vote
1
answer
1k
views
What is accelerated years in describing the amount of the training time?
As described in this article, it was written that GPT-3 took 405 V100 years to train in 2020.
I'm a bit confused about this definition, does that mean the process was accelerated like using a V100 GPU ...
1
vote
1
answer
2k
views
How LLM keeps the context of a chat/thread
How an LLM keeps the context (what has already been entered by the user) of a chat/thread?
For reference, in chat.openai.com, for each chat we create (or a Thread according to their API), the LLM ...
- 111
2
votes
0
answers
482
views
What is 'system card'?
What is 'system card' in these context:
https://ai.meta.com/blog/system-cards-a-new-resource-for-understanding-how-ai-systems-work/
Additionally, individual model developers may provide ...
- 119
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 ...
- 389
0
votes
1
answer
106
views
Does retriever-augmented generation enable the LLM to violate my data privacy?
I understand in RAG, documents are sent (perhaps in embedded form?) to an LLM.
Supposing one uses openAI as in this popular demo, would it send my data to them, thus with a potential data privacy risk?...
- 101
1
vote
0
answers
190
views
LLM for Postgres
I have a postgres database with 200+ Tables. Each table contains information about my supply inventory. It also contains columns which are JSON and there are nested JSON as well. There are ...
1
vote
1
answer
95
views
Help for my custom ENV with GYM, trying with DQN
I created a custom env to simulate a sort of blocks using gym enviroments.
My environment consists of an 8 x 8 observation space, which would be the stacks of blocks and the height of each stack.
<...
- 11
2
votes
0
answers
166
views
What type of fine-tuning does the OpenAI API use?
They have instructions on how to fine-tune. But I'm not clear on the type of fine-tuning that is done. Maybe this is mentioned somewhere. I would imagine it's some type of PEFT to avoid catastrophic ...
- 121
1
vote
1
answer
96
views
How to disapprove some who says that AI is capable of irrational thought and emotions
A teacher of mine said something of about AI being self sufficient and operating on experience. They backed this statement by this example-a car programmed to avoid ramming into apple, mango and banna ...
- 11
-2
votes
1
answer
36
views
Dynamic text completion [closed]
I am using the get_completion function to generate response to a question. Since generating response takes a long time (~5 seconds) I would like to display the response text as it's generated (...
- 97
0
votes
1
answer
300
views
How to prompt an LLM for a real variable list length? [closed]
I struggle to get a variable list out of an LLM. Even with a prompt like
...
- 109
3
votes
2
answers
581
views
How do you deal with movement inertia in an environment after a step?
I was wondering how can we deal with movement inertia in an environment that is constantly changing?
Imagine that you make a step on an environment that moves a ball. When you make the step, you make ...
- 145
0
votes
1
answer
110
views
Noob crafting a simple "Zero-Shot Classifier" Using an API . How can I avoid passing the categories every single request? [closed]
I have a collection of 700 categories, all potential classifications for articles. My current need is to create a system that can dynamically categorize short texts or articles according to these 700 ...
- 109
3
votes
1
answer
514
views
Match two paragraphs of text
I'm building a friend finder app and I need to match people based on a paragraph of text. Here is an example of what I mean:
Person A:
I love walking and going to the beach, I also love reading and ...
- 31
0
votes
1
answer
2k
views
Why does LLM inference cost scale in both input tokens and output tokens?
EDIT
This question was flawed. See my answer with help from commenters.
Original question
This question has been asked in other forums [1] [2] but I'm not sure I understand the claims, which are (...
- 208
5
votes
3
answers
4k
views
How do open source LLMs compare to GPT-4?
I have heard some back and forth regarding open source LLMs like Llama.
I have heard that on certain benchmarks they perform close, the same or better than GPT-4, but caveats that they tend to lack ...
- 225
2
votes
0
answers
356
views
How is OpenAI embeddings obtained
There is OpenAI embedding API https://platform.openai.com/docs/guides/embeddings. How is this embedding related to the GPT3.5 transformer model architecture? Is it the vectors learned from the input ...
- 121
0
votes
1
answer
232
views
Machine Learning Math Requirements [duplicate]
What area of math do i need for AI and ML? and some recommendations for YouTube math's playlist
I've just started to learn to code in python and i want to go to the path of AI/ML
- 11
0
votes
1
answer
226
views
How do you define an action space for a card game with an unlimited and variable hand size?
I'm new to the world of AI and have been primarily reading through the documentation for OpenAI's Gym/Gymnasium in hopes of training an AI to play a board game. One piece of information I haven't been ...
- 1
0
votes
1
answer
265
views
Can transformer models be used to convert code from one programming language to another?
There was a question like this in 2019. I hope things have changed since then.
Concretely, I am looking for a way to train a transformer model to convert code from SAS to Python. I guess the method ...
- 51
0
votes
1
answer
6k
views
can GPU crypto mining rigs be converted to train or run AI? [closed]
SHORT VERSION:
"I've got a bunch of GPU mining rigs, surely I can do something useful with them like train my own AI or provide hashing power to astronomy or genome folding operations?"
TLDR:...
3
votes
1
answer
8k
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 ...
- 165
4
votes
1
answer
2k
views
What's the difference between GPT3.5 and InstructGPT?
I read about the different model series in GPT3.5 here - https://platform.openai.com/docs/models/gpt-3-5
At the beginning of the page, it mentions to look at https://platform.openai.com/docs/model-...
- 41
1
vote
1
answer
307
views
Summarizing articles with ChatGPT [closed]
You cannot upload files such as articles on ChatGPT. As an alternative I provided links to ChatGPT of the corresponding webpages but it is clear from its summaries that it is not able to open the link ...
- 119
-1
votes
1
answer
173
views
Could it be probable to quantify or measure the IQ of a super-intelligent machine like GPT? [closed]
In the age of artificial intelligence, super-intelligent machines like GPT have become a reality, leading to the question of how to quantify or measure their intelligence. While IQ tests are widely ...
- 137
8
votes
2
answers
1k
views
Is GPT-4 based on GPT-3 or was it trained from the scratch?
To me it looks like GPT-4 is based on GPT-3.
On the other hand, there were rumors that training of GPT-3 was done with errors, but re-train was impossible due to the costs.
- 351