Community Digest |
Top new questions this week: |
||||||||
How to understand DeepSeek's offline token usage estimator?DeepSeek has a simple python code to calculate token usage offline but I don't really understand what it is showing. For example: result = tokenizer.encode("This is a test") print(result) &...
|
||||||||
Feasible to implement AI interacting with webpages?I'm in the process of doing a personal project and I think it might be a good idea to create an app that can help people retrieve information from the Web, based on their needs. However, after several ...
|
||||||||
Greatest hits from previous weeks: |
||||||||
Is Google Translate, the web application, a Generative Artificial Intelligence (GenAI) tool?I have seen sources claiming that Google Translate uses artificial intelligence, like blog articles published by Google, Wikipedia articles and questions from Artificial Intelligence Stack Exchange ...
|
||||||||
Stable Diffusion XL is two separate models - how do I use it to generate images?SDXL 1.0 just released and, unlike previous Stable Diffusion releases, appears to be made up of two separate models - a "base" and a "refiner": https://huggingface.co/stabilityai/...
|
||||||||
Does saying "please" and "thank you" to LLMs change anything?I've been using language models for various tasks, and I often find myself saying "please" and "thank you" in my requests (like many others). I'm not sure if this politeness ...
|
||||||||
How does ChatGPT render math in Markdown output?ChatGPT renders inline math output like this: Markdown: is \( 2^4 = 16 \). Rendered: It doesn't use the typical $ ... $ or $$ ... $$ to wrap around math expressions (like in LaTex / MathJax), so what ...
|
||||||||
Do LLMs suffer from a kind of Dunning-Kruger effect, giving an inflated self-assessment in domains they lack expertise in?The Dunning–Kruger effect is a cognitive bias whereby people with low ability, expertise, or experience regarding a type of task or area of knowledge tend to overestimate their ability or knowledge. (...
|
||||||||
How can I encourage ChatGPT to give me more concise information?When working with ChatGPT 4 on specific questions (such as programming, electrical engineering, writing, etc), I often ask specific questions and know that ChatGPT will provide an example. However, by ...
|
||||||||
What prompt is required to have a subject fully in frame using Stable Diffusion based AI image generation?When using an AI image generation package based on Stable Diffusion (For example, Automatic1111 Stable Diffusion web UI, or Stable Diffusion Infinity), what prompt (+ or -) is required to have your ...
|
||||||||
Can you answer this question? |
||||||||
How does model choice impact the results of "Optimize this Code" with Continue and VS CodeAccording to the Continue documentation at https://docs.continue.dev/setup/select-model, with Ollama as a provider, I can specify a main model for chat, an autocomplete model and a model for ...
|
