TheSequence

Home
Archive
About
Edge 393: Understanding Planning Techniques in Autonomous Agents
A taxonomy of planning in autonomous agents, the ADaPT planning method and the XLANG framework.
🔥 Announcing Galileo Protect: Real-Time Hallucination Firewall*
Unveiling Galileo Protect – the first GenAI firewall built for the enterprise!
Maybe Two Big Research Breakthroughs or Maybe Nothing
Multi-token prediction and a multi-layer perceptron alternative.
Edge 392: Meet RAFT: UC Berkeley's New Method to Improve RAG Patterns in LLMs
The method brings the best of RAG and supervised fine tuning.

April 2024

Edge 391: Autonomous Agents and LLM Function Calling
LLMs that invoke external functions, UC Berkeley's LLM Compiler and the Phidata framework.
Nobody Likes a Know-It-All: Smaller LLMs are Gaining Momentum
Phi-3 and OpenELM, two major small model releases this week.
Edge 390: Diving Into Databricks' DBRX: One of the Most Impressive Open Source LLMs Released Recently
The model uses an MoE architecture which exhibits remarkable perfromance on a relatively small budget.
Edge 389: Understanding Large Action Models
One of the most important concepts in autonomous agents.
1
Some Cool Details About Llama 3
Solid performance, new tokenizer, fairly optimal training and other details about Meta AI's new model.
Edge 388: Google DeepMind's SIMA can Follow Language Instructions in 3D Games Just Like Humans
The AI agent represents a major improvement relative to expensive reinforcement learning methods.
Edge 387: Tool Learning in Autonomous Agents
Agents that master tools and APIs, UC Berkeley's Gorilla and Microsoft's TaskWeaver
Neuro-Symbolic Models are Making a Comeback
A new startup called Symbolica comes out of stealth with a very different value proposition.
© 2024 Jesus Rodriguez
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture