TheSequence
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Edge 395: Task Decomposition in Autonomous Agents
The cornerstone of planning in autonomous agents.
May 14
56
Share this post
Edge 395: Task Decomposition in Autonomous Agents
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
DeepMind’s AI-First Science Quest Continues with AlphaFold 3
The new model can predict the structure of many life's molecules such as proteins, DNA, RNA and several others.
May 12
6
Share this post
DeepMind’s AI-First Science Quest Continues with AlphaFold 3
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Edge 394: Not Just Transformers: Jamba is New LLM that Brings the Best of SSMs, Transformers, and MoEs in a Single Architecture
Jamba addresses some of the limitations of transformers with a novel architecture paradigms.
May 9
12
Share this post
Edge 394: Not Just Transformers: Jamba is New LLM that Brings the Best of SSMs, Transformers, and MoEs in a Single Architecture
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Edge 393: Understanding Planning Techniques in Autonomous Agents
A taxonomy of planning in autonomous agents, the ADaPT planning method and the XLANG framework.
May 7
9
Share this post
Edge 393: Understanding Planning Techniques in Autonomous Agents
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
🔥 Announcing Galileo Protect: Real-Time Hallucination Firewall*
Unveiling Galileo Protect – the first GenAI firewall built for the enterprise!
May 6
27
Share this post
🔥 Announcing Galileo Protect: Real-Time Hallucination Firewall*
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Maybe Two Big Research Breakthroughs or Maybe Nothing
Multi-token prediction and a multi-layer perceptron alternative.
May 5
13
Share this post
Maybe Two Big Research Breakthroughs or Maybe Nothing
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
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.
May 2
14
Share this post
Edge 392: Meet RAFT: UC Berkeley's New Method to Improve RAG Patterns in LLMs
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
April 2024
Edge 391: Autonomous Agents and LLM Function Calling
LLMs that invoke external functions, UC Berkeley's LLM Compiler and the Phidata framework.
Apr 30
12
Share this post
Edge 391: Autonomous Agents and LLM Function Calling
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Nobody Likes a Know-It-All: Smaller LLMs are Gaining Momentum
Phi-3 and OpenELM, two major small model releases this week.
Apr 28
25
Share this post
Nobody Likes a Know-It-All: Smaller LLMs are Gaining Momentum
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
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.
Apr 25
12
Share this post
Edge 390: Diving Into Databricks' DBRX: One of the Most Impressive Open Source LLMs Released Recently
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Edge 389: Understanding Large Action Models
One of the most important concepts in autonomous agents.
Apr 23
13
Share this post
Edge 389: Understanding Large Action Models
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
1
Some Cool Details About Llama 3
Solid performance, new tokenizer, fairly optimal training and other details about Meta AI's new model.
Apr 21
24
Share this post
Some Cool Details About Llama 3
thesequence.substack.com
Copy link
Facebook
Email
Note
Other
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts