Party at my place! Get ready to talk about all things: Fast Inference Open Source AI Agentic AI See you soon!
AGENTS
-
LangManus Open Source Project Replicates Manus Framework
By
–
🦜🤖LangManus
— Harrison Chase (@hwchase17) 20 mars 2025
You had to know it was coming!
This community effort attempts to replicate Manus using the LangStack (LangChain + LangGraph)
Still early innings – but check it out here!https://t.co/2APEonZTRg pic.twitter.com/5BOTHdhKn1LangManus You had to know it was coming! This community effort attempts to replicate Manus using the LangStack (LangChain + LangGraph) Still early innings – but check it out here! https://
github.com/langmanus/lang
manus
… -
AI Strategies Across Industries: From Chatbots to Autonomous Agents
By
–
Enterprises are rapidly adopting both basic AI tools like chatbots and advanced systems like autonomous AI agents. How do AI strategies vary across industries? Here’s a glimpse into how different industries are applying AI in unique ways. https://
dbricks.co/4bYPRNz -
Building Voice Agents with New Audio API Models
By
–
Building voice agents with new audio models in the API.
-
Code and Claude’s Bracket Analysis Results Shared
By
–
Here's the code and claude's bracket analysis/results if you're interested. This was done at midnight last night so there may be bugs.
-
Creating a Game Analysis Harness with Claude Code
By
–
The harness was easy to make with claude code, didn't touch the actual code once Definitely could be optimized much more but at a high level here's how it works rn For each game, we dispatch search subagents across a few queries and then bring all their analysis back to claude
-
Claude Code Creates March Madness Bracket Picker in 20 Minutes
By
–
I used Claude Code to make an agentic march madness bracket picker in <20 minutes. Here's the final four that Claude picked:
-
Control and Interpretability: Feeling Rational Yet Illusory
By
–
Actually I feel the same way btw. It feels a little bit irrational (?) but real. It's some (illusion?) or degree of control and some degree of interpretability of what is happening when I press go.
-
LLM Conversation Strategies: New Chats vs Persistent Memory
By
–
When working with LLMs I am used to starting "New Conversation" for each request. But there is also the polar opposite approach of keeping one giant conversation going forever. The standard approach can still choose to use a Memory tool to write things down in between
-
Multiple GPT Agents in Single Chat Interface
By
–
A few tabs? Have you tried calling the second/third ones in the same chat? Just @ the GPT in the chat box, like slack.