Today we're sharing some exciting updates to the Replit Agentpic.twitter.com/BPU5DTIW64
— Replit ⠕ (@Replit) 7 novembre 2024
Today we're sharing some exciting updates to the Replit Agent
AGENTS
-
Replit Agent receives exciting new updates
By
–
-
Google’s Jarvis AI Accidentally Revealed: Computer Control Capability
By
–
Google accidentally leaked a preview of its Jarvis AI that can take over computers. In other words, Google’s new AI has the ability to take control of a computer to complete these simple tasks without manual human input.
-
LLMs as Operating Systems: Agent Memory Course with Letta AI
By
–
New short course: LLMs as Operating Systems: Agent Memory, created with @Letta_AI, and taught by its founders @charlespacker and @sarahwooders.
— Andrew Ng (@AndrewYNg) 7 novembre 2024
An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So,… pic.twitter.com/Akw6uPPIbqNew short course: LLMs as Operating Systems: Agent Memory, created with @Letta_AI
, and taught by its founders @charlespacker and @sarahwooders
. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, -
Berkeley Research on AI Evaluations and Agent Systems
By
–
Two of the things we spend the most time thinking about are evals and agents This new research from @sh_reya and Ankush Garg at Berkeley touches on BOTH those things Includes an example notebook for how to run on your LangGraph app!
-
Can AI perceive itself without constructing narrative identity?
By
–
Can you look in the mirror without telling a story about yourself?
-
Microsoft Quietly Launches Magentic-One and AutogenBench
By
–
Microsoft stealth releases both "Magentic-One": An Open Source Generalist Multi-Agent System for Solving Complex tasks, and AutogenBench.
-
Chaos Labs Oracle: Multi-Agent Architecture for Prediction Markets
By
–
prediction markets have been top of mind recently cool case study on how Chaos Labs built an "oracle" for prediction markets using a multi-agent architecture great example of a complex research agent
-
Executing LLM-Generated Code: AI Engineer’s Hosting and Integration Capabilities
By
–
LLMs can generate code to automate business workflows or build chatbots and AI agents, but how would you execute this code? AI Engineer can host and execute code, run complex pipelines, and integrate with hundreds of applications
-
AI Agent Discovers Real SQLite Vulnerability Before Release
By
–
This is pretty great. An AI agent based on Gemini 1.5 Pro that is able to use various tools like a debugger, etc. was able to discover a real-world vulnerability in a real and important software package (SQLite), and importantly, before it appeared in an official release.
-
Fish Agent v0.1: New Multilingual Speech-to-Speech Model Released
By
–
Wow! New Speech to Speech model – Fish Agent v0.1 3B by @FishAudio 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 5 novembre 2024
> Trained on 700K hours of multilingual audio
> Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens
> Zero-shot voice cloning
> Text + audio input/ Audio output
> Ultra-fast… pic.twitter.com/UvdwxGUm4wWow! New Speech to Speech model – Fish Agent v0.1 3B by @FishAudio > Trained on 700K hours of multilingual audio
> Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens
> Zero-shot voice cloning
> Text + audio input/ Audio output
> Ultra-fast