RAG From Scratch: Feedback + self-reflection Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the final part in our series, focusing on self-reflection + feedback to improve RAG systems. Problem: RAG systems
PROMPT ENGINEERING
-
Claude-Author: AI System Generates Complete Novels Automatically
By
–
Introducing `Claude-Author` 📕✍️
— Matt Shumer (@mattshumer_) 3 avril 2024
One prompt -> an entire novel!
Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes.
– complete w/ cover art
– packages your book as a real e-book
And it's open-source! pic.twitter.com/56jJzCusEfIntroducing `Claude-Author` One prompt -> an entire novel! Just describe the high-level details, and a chain of AI systems will write an entire book for you in minutes. – complete w/ cover art
– packages your book as a real e-book And it's open-source! -
Claude-Author: Constrained Agent for Coherent Novel Writing
By
–
Claude-Author is a constrained agent — meaning its behavior is highly-controlled, leading to better results than open-ended agents. It's a chain of many Claude 3 Haiku/Opus and Stable Diffusion API calls that work together to write a coherent novel.
-
Technical Knowledge Matters for LLM Understanding and Limitations
By
–
I am not sure the technical explanations are needed to use LLMs well (in fact I am pretty sure they aren’t) but they are useful for understanding their power and limitations.
-
ROBOSHOT: Optimizing Foundation Models Without Fine-Tuning
By
–
Coming up this Friday! PhD student Dyah Adila will explain how data scientists can get better performance out of foundation models without any additional fine-tuning. The technique, called ROBOSHOT, applies a kind of lens to model outputs Register now!
-
AI breakthroughs: Developer agents, Vision Pro, voice AI, jailbreaking risks
By
–
Top stories in AI today: -Open-sourced AI software developer agent
-Apple Vision Pro’s spatial Personas
-Get text-to-speech audio trained on your voice
-Anthropic uncovers 'many-shot jailbreaking'
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/open-sourced
-software-developer-agent
… -
RAG Remains Essential for Large Language Models
By
–
I can't imagine RAG becoming irrelevant. Even long context LLMs still need to have documents selectively added to that context to increase the chance of a correct answer, and I don't see any other way of answering questions using content that's only a few minutes/hours old
-
OpenAI Stock Investing GPTs Fail Basic Investment Question
By
–
OpenAI's stock investing GPTs fail this basic question about stock investing They fail not by claiming falsehoods but by reiterating ignorance. https://
zdnet.com/article/openai
s-stock-investing-gpts-fail-this-basic-question-about-stock-investing/
… @OpenAI @OpenAIDevs -
Matt Shumer Launches Personal AI Clone Using Delphi
By
–
Excited to announce that you can now chat with AI Matt. I created an AI clone of myself using @withdelphi
. AI Matt knows quite a bit about training models, writing prompts, and building AI systems. Chat now: https://
delphi.ai/matt-shumer -
Anthropic Research: Many-Shot Jailbreaking Techniques Analysis
By
–
Research: https://
anthropic.com/research/many-
shot-jailbreaking
…