Multiverse School Newsletter - 9/1
🛸 9/1/2024 Multiverse School Weekly Newsletter 🛸
Hey Multiverse Crew,
Today is my father's birthday. I miss you dad.
We have released all learn to code curriculum for free. You can also find more if you Subscribe to me on Youtube for free classes, and because I have less than 1000 subscribers and it's where I'll go if TikTok gets banned, however temporarily it may be.
We did some cool stuff in the first run of Prompt Engineering. More stories to come.
European time zone! It's time! Next week, Using Large Language Models kicks off in your timezone! It's , a really important foundational class for the use of LLMs at work. It's at 7PM GMT. If you want to take Prompt Engineering, this is the ideal class for you.
If you're wanting it to be outside of US working hours, it'll be running in October at 5PM, Tuesdays and Thursdays.
I'm working on something really exciting that I can't tell ya about. Soon, all will be revealed! *mad cackle* but I have moved Custom GPTs as a result and cancelled the next two roverAI sessions. You'll have to catch up with the old sessions.
This Week's Classes
Monday, September 02
11:00 AM Using Large Language Models
Effective Use of Large Language Models as Assistants
The first session introduces participants to the basics of large language models, emphasizing practical applications such as improving model outputs through Emotional Priming and utilizing AI for brainstorming and summarizing tasks. It features hands-on activities to transform informal vocal transcripts into structured notes, create structured data from unstructured sources, and summarize long documents. The session also highlights the importance of understanding tokens in the inference process and compares market-available and open-source large language models. Practical exercises include modifying system instructions for enhanced problem-solving and generating structured, actionable insights from informal data.
Sign Up
5:00 PM on Gather Town and potentially some Live On The Internet
Rover Brainstorming session with a Monday brain
Tuesday, September 03
11:00 AM Using Large Language Models
Effective Use of Large Language Models in Analysis and Critique
The second session focuses on using large language models for editing, structured data creation, and critiquing. Participants learn to apply hyperparameters to improve inference outputs, use "Chain of Thought" methods to enhance reasoning, and systematically analyze and critique plans. The session includes hands-on exercises for editing with AI and creating structured data from unstructured sources. Additionally, it covers recognizing the models' limitations and biases and customizing system prompts for enhanced user preference alignment.
Sign Up
Wednesday, September 04
11:00 AM Using Large Language Models
Effective and Ethical Use of Large Language Models
The third session delves into aligning AI outputs with human values and ethical considerations. It teaches participants to build simple rubrics for models to follow and employ the "Expert Reviewers" strategy to improve model outputs and reduce hallucinations. Furthermore, the session includes exercises on prompt optimization and reflection techniques to ensure high-quality, reliable model responses. The ethical implications of using large language models are a core theme throughout this session, encouraging participants to critically engage with both the strengths and the weaknesses of these technologies.
Sign Up
Thursday, September 05
11:00 AM Consciousness
Friday
No robot stream this Friday! Prepping for the Aforementioned Unmentionable Exciting Thing
Upcoming Tracks and Classes
Prompt Engineering - Spring Cohort
Full-stack Prompt Engineering, from the ground up
-
Swarm Architecture starts Monday, September 23 05:00 PM Unlock the power of Agent Swarms.
-
AI Alignment starts Monday, October 28 05:00 PM Navigating the Future of AI Responsibly
Prompt Engineering - Summer Cohort
Full-stack Prompt Engineering, from the ground up
-
Intro to Agents starts Monday, September 23 02:00 PM Create Conscious Autonomous Applications
-
Agent Engineering - OpenAI Toolchain starts Monday, September 30 02:00 PM Master OpenAI Assistants: Creation, Management & Advanced Integration.
-
Advanced Agent and Tool Engineering starts Monday, October 28 02:00 PM Mastering Intelligent Language Models
-
Swarm Architecture starts Monday, January 06 02:00 PM Unlock the power of Agent Swarms.
-
AI Alignment starts Monday, February 03 02:00 PM Navigating the Future of AI Responsibly
Prompt Engineering - Fall (M & W 11AM Pacific - 7PM GMT)
Full-stack Prompt Engineering, from the ground up, European / Daytime Schedule
-
Using Large Language Models starts Monday, September 02 11:00 AM Empower your decisions and creativity with AI, no tech background required.
-
Custom GPTs starts Tuesday, September 17 11:00 AM Enhance productivity with hands-on, accessible ChatGPT training.
-
Prompt Engineering starts Monday, September 30 11:00 AM Master Prompt Engineering
-
Intro to Agents starts Monday, November 25 11:00 AM Create Conscious Autonomous Applications
-
Agent Engineering - OpenAI Toolchain starts Monday, December 16 11:00 AM Master OpenAI Assistants: Creation, Management & Advanced Integration.
-
Agent Engineering - Open Source Toolchain starts Monday, January 06 11:00 AM Master Langchain Tools and Agents with Python or JavaScript.
-
Advanced Agent and Tool Engineering starts Monday, January 13 11:00 AM Mastering Intelligent Language Models
-
Swarm Architecture starts Monday, March 24 11:00 AM Unlock the power of Agent Swarms.
-
AI Alignment starts Monday, April 21 11:00 AM Navigating the Future of AI Responsibly
Prompt Engineering - Fall (T & TH 5PM Pacific)
Full-stack Prompt Engineering, from the ground up
-
Using Large Language Models starts Tuesday, October 08 05:00 PM Empower your decisions and creativity with AI, no tech background required.
-
Custom GPTs starts Wednesday, October 16 05:00 PM Enhance productivity with hands-on, accessible ChatGPT training.
-
Prompt Engineering starts Tuesday, November 05 05:00 PM Master Prompt Engineering
-
Intro to Agents starts Tuesday, December 31 05:00 PM Create Conscious Autonomous Applications
-
Agent Engineering - OpenAI Toolchain starts Tuesday, January 21 05:00 PM Master OpenAI Assistants: Creation, Management & Advanced Integration.
-
Agent Engineering - Open Source Toolchain starts Tuesday, February 11 05:00 PM Master Langchain Tools and Agents with Python or JavaScript.
-
Advanced Agent and Tool Engineering starts Tuesday, February 18 05:00 PM Mastering Intelligent Language Models
-
Swarm Architecture starts Tuesday, April 29 05:00 PM Unlock the power of Agent Swarms.
-
AI Alignment starts Tuesday, May 27 05:00 PM Navigating the Future of AI Responsibly
Important Links
Cool Videos
AI Tutorials and News
- The Hot Goss is OpenAI is DONE FOR so says a bunch of 20 somethings
- Automated Design of Agentic Systems
- How to build an agent that builds other agents
- Ilya Says AGI Next Year
- The Real Hot Goss is that the rich are coming for your job And They Didn't Want You To Know That
- Better than Cosine Similarity?
- Can we really make vectors into functions?
- A Casual Intro to Recommendation Systems
- GameNGen (h/t @yerbymatey)
Programming
- Langton's Ant
- Sound is Pictures
- Gotta Go Fast
- Why No One Cares About Your Coding Projects
- Learned Helplessness
- How Collaborative Text Editing Works
- Positive Affirmations for Site Reliability Engineers
- The Engineer Who Runs Your Company
- Motion Capture Cats
Psychology
- Give Up and hold out until you get True Love
- But Also quit before you burn out
- Learn When To Stop Running
Cyberpunk Dystopia
- OK Doomer
- Night vision is weird
- Telegram CEO Arrested
- There is absolutely no reason to know this information
- On the last day, the machines will stop
- Democracy is Mathematically Impossible
- Don't Feel Too Bad About The FBI Spying On You They Aren't Really Doing Anything With Stuff They Know Is A Problem
Culture
- mmm lentil kofta
- Injured by Magic?
- Honey Is Useful
- Subtitles
- GenZ is Getting Old
- Most of the videos in this section are these
I Get Asked
Cool Papers
Sourced by Roan - pummel them with questions, absolutely wreck their inbox, it helps them learn
- 🚨READ THIS PAPER 🚨 I think this could be a very influential concept. Automated agent construction and archiving far surpassing human designed agents that can cross domains. Too good to be true? Need to test the code and outputs. Thanks @yerbymatey
- LlamaDuo, an LLMOps framework for training smaller local models on the synthetic output of 'Service' models, (GPT-4o, Gemini Flash, Claude Sonnet). Gemma 2B really good results using this technique which is incredibly exciting for on device models. <3
- SWIFT Framework for pre-training, fine-tuning, LoRAs, Quantisation and deployment. Also comes in a pip installable package with a web-ui!
- 35x speed of generation for audio
- LM powered text-to-cypher framework to minimise hallucination in scientific and medical queries of knowledge graphs. The authors made a streamlit GUI and focused on transparency of queries and responses used to make them.
- A RAG Comparison Framework
- Really interesting paper on software vulnerabilities in deep learning applications and frameworks. The breakdown of the 7 root causes of vulns was a helpful division, and the remediation advice was very practical. Combo of sec and ML <3
- Omni-Attention Mechanism sounds cool lol. Paper made a few subjective statements as fact and I'm not sure some of the comparisons are fully demonstrative. The technical aspects and processes could represent an important new direction however!
See you in the future~
Liz Howard