Self Query Template (
@elastic
) Often times documents come with really useful metadata! But how can you best take advantage of this metadata when doing RAG? Self-query is one way to do so. This converts a natural language query into one piece that is embedded and
LLMS
-
Self-Query Template: Leveraging Metadata in RAG Systems
By
–
-
Complete Guide to Learning Large Language Models in 2023
By
–
From zero to hero with #LLMs. Start with Large Language Models in 2023 A complete guide to start and improve your LLM skills in 2023 without an advanced background in the field and stay up-to-date with the latest news and state-of-the-art techniques https://
youtu.be/58XmJxb1x_o -
GPT-5 rumors spark expectations for breakthrough AI year ahead
By
–
I'm hearing some wild rumors about GPT-5… have a feeling next year will be nuts.
-
Best Custom GPTs Directory for the AI Gold Rush
By
–
Custom GPTs is the new AI gold rush.
— God of Prompt (@godofprompt) 17 novembre 2023
That's why I made Best Custom GPTs Directory.
You can find all publicly accessible GPTs on the internet.
Try it here: https://t.co/xWhCgqjWox#CustomGPTs #GPTs #GPTStore #ChatGPTplus #GPT4 #GPT4Vision #OpenAI #OpenAIDevDay #GodofPrompt pic.twitter.com/k42OCbiWvNCustom GPTs is the new AI gold rush. That's why I made Best Custom GPTs Directory. You can find all publicly accessible GPTs on the internet. Try it here: https://
chat.openai.com/g/g-upCgPTI4U-
20000-best-custom-gpts-directory
… #CustomGPTs #GPTs #GPTStore #ChatGPTplus #GPT4 #GPT4Vision #OpenAI #OpenAIDevDay #GodofPrompt -
GPT 4.5 and 5 launch hype cycle predictions for 2030s
By
–
Revisit this discussion in the 2030s albeit the social media hype will probably return when GPT4.5 and then 5 are launched.
-
UnRLHF Project Reveals LLM Safeguard Vulnerability Risks
By
–
There is this project called unRLHF, where they undo LLM safeguards. According to the examples, the LLM becomes quite evil, giving advice on "how to microwave a child" https://
lesswrong.com/posts/3eqHYxfW
b5x4Qfz8C/unrlhf-efficiently-undoing-llm-safeguards
… -
Regional Prompting and Attention Mechanisms in AI Models
By
–
I wonder if this is based on some variant of regional prompting 🤔
— fofr (@fofrAI) 17 novembre 2023
(The attention mechanism that underlies it) https://t.co/yDP1EfraLGI wonder if this is based on some variant of regional prompting (The attention mechanism that underlies it)
-
Attention Mechanism in AI: Technical Implementation
By
–
I mean the attention mechanism to achieve it.
-
Auto-Regressive LLMs Face Diminishing Returns, New Architecture Needed
By
–
Translation: Auto-Regressive LLMs scaling is giving diminishing returns. As I've said repeatedly, a new architecture will emerge for the next leap, perhaps along the lines of the Objective-Driven AI I've been proposing. But deep learning will still be the foundation. No wall.
-
Higher hallucination standard needed for ordinary chatbot users
By
–
Researchers can plausibly deal with hallucinations — experiment with prompt variations, responsibly verify the output, etc. It’s chatbots used by ordinary people that deserve a higher standard because those users’ priors for its correctness are highest.