So Essentially Substack

Home
Archive
About
New
Top
Discussion
LLMLingua: Prompt Compression makes LLM Inference Supercharged 🚀
So essentially, "LLMLingua by Microsoft allows for compressed prompts which are 20x more token efficient! " Paper: LLMLingua: Compressing Prompts for…
 • 
Dhruv Diddi
AutoGen: Next Gen LLMs with Multi-Agent Conversation
And how does this affect the current LLM applications?
 • 
Dhruv Diddi
How can compression help with Retrieval Augmented LMs?
So essentially, "Using compressed summaries to provide extended context provides better RAG!" Paper: RECOMP: Improving Retrieval-Augmented LMs with…
 • 
Dhruv Diddi
September 2023
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
And can we scale human feedback with AI?
 • 
Dhruv Diddi
August 2023
What going on with the Platypus on HuggingFace?
And is it related to Perry?
 • 
Dhruv Diddi
Jurassic World Remake through Image-to-Image Translation!
Is this a more accurate imagination of fossils now?
 • 
Dhruv Diddi
Solving and Verifying Math Word Problems with GPT-4
How can GPT-4 get at solving math word problems?
 • 
Dhruv Diddi
Bot or Not? 🤖🤖🤖
How can you interrogate and break chatGPT?
 • 
Dhruv Diddi
June 2023
AudioPaLM: A Large Language Model That Can Speak and Listen
Is this model going to replace Siri and Alexa?
 • 
Dhruv Diddi
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
How good are code LLMs?
 • 
Dhruv Diddi
April 2023
Disco with AI
The next level of music visual generation 🚀🎶🎨
 • 
Dhruv Diddi
Your favorite TV characters now as AI ghosts!
Starting with Sheldon Cooper from the Big Bang Theory!
 • 
Dhruv Diddi
© 2023 So Essentially
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing