Welcome to the staging ground for new communities! Each proposal has a description in the "Descriptions" category and a body of questions and answers in "Incubator Q&A". You can ask questions (and get answers, we hope!) right away, and start new proposals.
Posts tagged ai-tech
There is a lot of debate about the "cognitive" capabilities of LLMs and LLM-based chatbots, like ChatGPT. It's common to see statements like "these models just apply statistical pattern matching" a...
I created the AI tech proposal primarily because I thought it would be good to have a place to discuss doing stuff with AI models rather than the details of how they are trained and how they work. ...
I want to give an AI the ability to read, write and manipulate files on my computer, such as with the OpenAI function calling feature. The goal of this is to use the AI to work on a project compris...
I want to use ChatGPT to edit individual source code files. When I give it the file and state what changes I want, it tends to do those quite well, but it's also very chatty and includes a lot of e...
Site Name AI Tech Description Technical AI discussion. Questions, answers and articles about creating and using sophisticated cutting-edge AI models. Topics Topics covered would include: La...
What free alternatives are available to the GPT-3 and GPT-4 large language models (LLM)? Are there competing models with similar capabilities that I can download and run on my own computer?
Prompt engineering has emerged as a critical concept in the use of LLMs. Are there any good resources for learning prompt engineering techniques?
GPT-NeoX is provided as open source software which you can train yourself: https://github.com/EleutherAI/gpt-neox What are the hardware requirements like for training this model within a reasonabl...
The Python library for OpenAI has a method openai.ChatCompletion.create which takes various parameters like messages, functions, and so on. I could not find documentation for these in the context o...
Sometimes responses from the OpenAI API are large and it takes a long time to receive them. During this time the program appears to hang since there is no output. Is there a way to incrementally r...
The context window of various GPT-3 models is given as 4-16k tokens. One token corresponds to about 0.75 words of English text. However, if an average book is 64k words, the GPT-3's context is far ...
