AGENTS - AI Dynamics

MCP Course: Build Rich-Context AI Apps with Anthropic

By

–

14 May 2025 17h13

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic @AnthropicAI and taught by Elie Schoppik @eschoppik, its Head of… pic.twitter.com/NDZZzP8QYb
— Andrew Ng (@AndrewYNg) 14 mai 2025

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic @AnthropicAI and taught by Elie Schoppik @eschoppik
, its Head of

→ View original post on X — @andrewyng

14 May 2025

Perplexity Adds PayPal and Venmo Integration to Shopping Tools

By

@perplexity_ai

–

14 May 2025 17h11

We look forward to adding @PayPal and @Venmo to Shopping and Travel on Perplexity, our voice assistants, and Comet. https://t.co/CKc59GjePJ
— Perplexity (@perplexity_ai) 14 mai 2025

We look forward to adding @PayPal and @Venmo to Shopping and Travel on Perplexity, our voice assistants, and Comet.

→ View original post on X — @perplexity_ai

14 May 2025

Perplexity’s Comet Browser Launching in 3-5 Weeks with AI Features

By

@rowancheung

–

14 May 2025 9h50

Perplexity's agentic browser, Comet, will launch in 3-5 weeks

CEO Aravind Srinivas said the browser will have native virtual meeting recording, transcription, and searches

However, it won't be a part of the first release, but a follow-up updatepic.twitter.com/Q1QE0tK2pL
— Rowan Cheung (@rowancheung) 14 mai 2025

Perplexity's agentic browser, Comet, will launch in 3-5 weeks CEO Aravind Srinivas said the browser will have native virtual meeting recording, transcription, and searches However, it won't be a part of the first release, but a follow-up update

→ View original post on X — @rowancheung

14 May 2025

LLMs for Complex Game Projects: Tractability and Resource Constraints

By

@patio11

–

14 May 2025 4h04

(I briefly considered “Beat Factorio with LLMs” as a project during my sabbatical but it looks very far from being tractable without a team and funding, which defeats the purpose of a sabbatical project.)

→ View original post on X — @patio11

14 May 2025

Ω-Coordinator: Autonomous Meta-Agentic α-AGI Business Systems

By

@montreal_ai

–

14 May 2025 3h29

Ω-Coordinator Autonomous Meta-Agentic α-AGI Businesses #AGIALPHA #MetaAgentic #ASIFirst

→ View original post on X — @montreal_ai

14 May 2025

MLE-Dojo Benchmark Evaluates Frontier LLMs on ML Engineering

By

@jiqizhixin

–

14 May 2025 2h40

MLE-Dojo: A new benchmark to evaluate LLM agents on real Machine Learning Engineering tasks. Its key innovation? An interactive environment that allows agents to experiment, debug, and refine solutions via structured feedback loops. Here’s how 8 frontier LLMs perform

→ View original post on X — @jiqizhixin

14 May 2025

Long-Term Memory for Improving Email Assistant Agent Interactions

By

@langchain

–

14 May 2025 1h54

Long-term memory is a vital part of building great agent interactions. Here's David Xu showing how to use it to make an email assistant improve over time! This ties in beautifully with the prior human in the loop steps, as the agent uses the human's edits and rejections to

→ View original post on X — @langchain

14 May 2025

Long-Term Memory for Improving Email Assistant Agents Over Time

By

@langchain

–

14 May 2025 1h52

Long-term memory is a vital part of building great agent interactions. Here's David Xu showing how to use it to make an email assistant improve over time! This ties in beautifully with the prior human in the loop steps, as the agent uses the human's edits and rejections to

→ View original post on X — @langchain

14 May 2025

OpenAI adopts Model Context Protocol for ChatGPT connectors

By

@testingcatalog

–

14 May 2025 1h23

OpenAI is finally tapping into MCPs As ChatGPT will be getting a custom connector option, which is likely similar to the recently added Remote MCP feature on Claude.

→ View original post on X — @testingcatalog

14 May 2025

Agent Inbox: Human-in-the-Loop Control and Oversight for Agents

By

@langchain

–

14 May 2025 0h40

Next up, Nick is back with a deep dive into Agent Inbox and the UI/UX around human in the loop interactions! A non-technical end user can use it to gain oversight into an agent's actions, accepting/editing/ignoring suggested actions as an agent runs! This human component

→ View original post on X — @langchain

14 May 2025