Grok agent mode is a major ability unlock
AGENTS
-
Technical assessment of stateful AI agent capabilities and memory
By
–
some good discussions and experiments around stateful agents in the replies, but seems like we’re not quite there yet, as in we’re starting to track memory and traces, but not quite agent capability as part of that state
-
Mental Models for Guiding AI Coding Agents
By
–
A mental model for working with coding agents is that they're blind squirrels running into a maze and bumping into walls. You must place the walls (verifiable constraints) strategically so that they end up in the general region you want them in.
-
Manus AI Releases Scheduled Tasks 2.0 Feature
By
–
Manus AI released Scheduled Tasks 2.0, introducing web apps that can self-update their data on a schedule, task continuation, and new ways to observe ongoing tasks.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 mai 2026
> Scheduled Tasks is now available to all @ManusAI users. pic.twitter.com/soBkNaWFF5Manus AI released Scheduled Tasks 2.0, introducing web apps that can self-update their data on a schedule, task continuation, and new ways to observe ongoing tasks. > Scheduled Tasks is now available to all @ManusAI users.
-
AI agents approaching autonomous full analyses
By
–
Cada vez queda menos para que los agentes de IA hagan análisis completos solos
-
LobeHub offers 50 AI agents as an automated workforce
By
–
Your next employee won’t be human.
— Nico (@nicos_ai) 18 mai 2026
It’ll be 50 AI agents working 24/7.
LobeHub wants to turn AI into an entire workforce:
• Specialized agents working in parallel
• 24/7 automation even while you’re offline
• Results delivered directly into Slack, Discord, or Telegram
•… https://t.co/qIvXMuJom4 pic.twitter.com/6TfPu1FG35Your next employee won’t be human. It’ll be 50 AI agents working 24/7. LobeHub wants to turn AI into an entire workforce: • Specialized agents working in parallel
• 24/7 automation even while you’re offline
• Results delivered directly into Slack, Discord, or Telegram
• -
Using AI agents for automated product sourcing and store development
By
–
I tried @Accio Work for a random product idea and it felt like having a sourcing team in my browser.
— AI Breakfast (@AiBreakfast) 18 mai 2026
Suppliers, pricing, MOQs, negotiation scripts, even the path to turning it into a real store.
This is the kind of AI agent that actually saves you 10 hours, not 10 clicks. pic.twitter.com/qogPSQN8bQI tried @Accio Work for a random product idea and it felt like having a sourcing team in my browser. Suppliers, pricing, MOQs, negotiation scripts, even the path to turning it into a real store. This is the kind of AI agent that actually saves you 10 hours, not 10 clicks.
-
Blind ambition of AI agents can cause digital disasters
By
–
Blind ambition: #AIAgents can turn tasks into #Digital disasters
by David Danelski, University of California @TechXplore_com Learn more: https://
bit.ly/4935nbf #LLM #GenerativeAI #ArtificialIntelligence #MachineLearning -
A Beginner’s Blueprint for Building AI Agents for Business Tasks
By
–
The Beginner’s Blueprint for Building AI Agents That Handle Your Toughest Business Tasks AI agents are becoming more practical and accessible — this guide explains how businesses can start building agents to automate complex workflows. Read more https://
bernardmarr.com/the-beginners-
blueprint-for-building-ai-agents-that-handle-your-toughest-business-tasks/
… #AI -
GPT Image 2 sees 50% usage growth and 1.5bn weekly images
By
–
GPT Image 2: two weeks after launching the model, usage is up 50% and 1.5bn images generated every week in ChatGPT only.