Messages
3/5/2024
12 : 24
Edge 375: Meta's System 2 Attention is a Very Unique LLM Reasoning Method
The method has been inspired by cognitive psychology and has immediate impact in LLM reasoning. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
3/3/2024
12 : 14
Text-to-Video Games and 1-Bit Models: Two Monumental Generative AI Research Milestones in One Week
Two papers that open new possibilities for generative AI. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
3/1/2024
14 : 24
📌 You're invited to GenAI Productionize 2024
Don't miss this industry-first summit on productionizing enterprise generative AI ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/29/2024
12 : 24
Edge 374: Some Technical Details we Learned About OpenAI's Sora
The text-to-video model that astonished the world includes several clever engineering optimizations. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/27/2024
12 : 14
Edge 373: Computationally Efficient LLM Reasoning with ReWOO
In this Issue: An overview of ReWOO as an LLM reasoning method. A review of ReWOO's research paper. An introduction to LLMFlows, a framework for building LLM applications. 💡 ML Concept of the Day:
2/25/2024
12 : 14
Google Goes Small and Open Source with Gemma
Gemma is based on the core architecture powering Gemini. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/23/2024
12 : 34
📝 Guest Post: LoRA Land: 25 Fine-Tuned Mistral-7b LLMs that Rival or Outperform GPT-4
In this guest post, Predibase team discusses their recent release of LoRA Land that they built to demonstrate a real world example of how smaller, task-specific fine-tuned models can cost-effectively
2/22/2024
12 : 4
Edge 372: Learn About CALM, Google DeepMind's Method to Augment LLMs with Other LLMs
Just like RAG but with LLMs! ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/20/2024
12 : 14
Edge 371: Two-Step LLM Reasoning with Skeleton of Thoughts
Created by Microsoft Research, the technique models some of the aspects of human cognitive reasoning in LLMs. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/19/2024
12 : 44
📌 ML Engineering Event: Mastering AI and ML at Production Scale at apply()
Join the next apply() virtual conference on Wednesday, April 3, for a free event that brings together the engineering community to master AI and ML in production. Since 2021, apply() has hosted more
2/19/2024
2 : 14
Edge 370: A Deep Dive Into AlphaGeometry: Google DeepMind’s New Model that Solves Geometry Problems Like a Math Ol…
The model uses a neurosymbolic approach to reasong through complex problems. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/19/2024
1 : 42
More Super Models is All We Need
Five major foundation models released in a single week! ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
2/13/2024
12 : 4
Edge 369: LLM Reasoning with Chain-Of-Code
Can LLMs use code generation to reason through complex tasks?
2/11/2024
12 : 14
Don't Overlook China's Open Source LLMs
A version of a Chinese LLM tops the open LLM leaderboard.
2/9/2024
12 : 44
💡WEBINAR: Beyond fine-tuning. Approaches in LLM optimization
We've talked about tuning, and we've talked about prompt engineering, but those are not the only techniques at our disposal to optimize LLMs. Join us for the next webinar of our LLM series on 📅
2/8/2024
12 : 4
Edge 368: Inside MemGPT: A Framework for Building Autonomous Agents You Should Know About
Built by AI researchers from UC Berkeley and inspired by operating systems architectures, MEMGPT enables the core building blocks for agent-based applications.
2/6/2024
12 : 24
Edge 367: Understanding Multi-Chain Reasoning in LLMs
One of the most interesting techniques used for more complex reasoning in LLMs.
2/5/2024
12 : 34
🔥Building Plaid’s ML Fraud Detection Application—an apply() Fireside Chat
Want to know how Plaid, a leading fintech company, built the ML infrastructure that powers Signal, its payment fraud detection and prevention application? Then watch this virtual fireside chat on
2/4/2024
12 : 14
The Most Open Open Source Generative AI Release
AllenAI just released all the components of its OLMo LLM model.
2/1/2024
12 : 4
Edge 366: Anthropic's Sleeper Agents Explore How LLMs can be Deceptive
One of the most important recent papers in generative AI.