AI agents
23 published articles
Multi-Agent Collaboration
The group chat just became AI's most dangerous proving ground
Alibaba Cloud's AgentTeams and Anthropic's Claude Tag are turning group chats into the proving ground for multi-agent collaboration. The shift from one-on-one to many-to-many conversations introduces complex challenges in context management, permission governance, and memory, and a new paradigm for how AI works inside organizations.
2026-07-16
Artificial Intelligence
Alibaba is betting the cloud, not the model, and it might work
Alibaba is betting the second half of 2026 on an integrated AI stack, not a single flagship model. Its strategy is to lock enterprises into its cloud via interoperable infrastructure, from agentic O&M to data warehousing, rather than to win benchmark titles.
2026-07-14
Orchestrator swap
Perplexity swapped its orchestrator model and the cost-performance chart is brutal
Perplexity swapped Grok 4.5 into Computer as its orchestrator model, claiming top accuracy on its internal benchmark at roughly half the cost of Claude Opus 4.8. The move signals a broader shift: which model you pair with an agent matters as much as the model itself.
2026-07-14
File over config
Vercel's Eve 0.22 wants your AI agents to live as files on disk, not secrets in a config
Vercel's Eve 0.22.6 brings a filesystem-based structure to AI agent development: instructions, tools, skills, and integrations all live as inspectable files, with multi-model support, human-in-the-loop prompts, and subagent orchestration.
2026-07-14
Artificial Intelligence
Meta bought Manus for its infrastructure, not its chatbot
Manus joins Meta in a strategic acquisition that prioritizes agent infrastructure over consumer AI. With over 80 million virtual computers created and 147 trillion tokens processed, Manus becomes Meta's execution layer for enterprise automation.
2026-07-13
OpenAI vs Anthropic
OpenAI just made its agent bet explicit, and Claude is stuck in single-player mode
With workspace agents, OpenAI makes its enterprise bet explicit: persistent, shared AI workers that run in the cloud and integrate with Slack. Anthropic's Claude, focused on single-session reasoning, has no answer yet.
2026-07-13
AI IDE
Point at a button, say "fix this", Cursor's design mode finally speaks visual
Cursor's updated Design Mode lets you point, draw, or speak to an agent instead of typing instructions. The result is a faster, more intuitive way to iterate on design changes directly inside the browser.
2026-07-13
Visual AI interaction
Cursor just gave developers a smarter way to tell AI what to fix: point at it
Cursor's updated Design Mode lets engineers and designers modify UI by clicking elements, drawing on the page, or speaking changes aloud, while the AI agent extracts element identity, styles, and layout context to edit code. The approach accelerates iteration by aligning the model's pace with how humans spot and act on visual issues.
2026-07-12
Synthetic Data Strategy
Nvidia's data atlas shows why synthetic data matters more than model weights
Nvidia's Nemotron Post-Training v3 Prompt Atlas provides an interactive map of billions of synthetic data samples, highlighting how open synthetic data is the missing layer for building reliable AI agents. The company argues that agent behavior must be inspectable and that synthetic data, released openly, is the only way to preserve proprietary signals without exposing trade secrets.
2026-07-12
Agent Strategy
Atlas is dead. OpenAI's agent strategy just got narrower and riskier.
OpenAI is sunsetting its experimental ChatGPT browser Atlas less than a year after launch, absorbing its learnings into new productivity features. The shutdown reflects a company-wide pivot from exploration to consolidation as it races to catch Anthropic on agentic work tools.
2026-07-11
AI Agents
OpenManus just killed the invite wall for AI agents. Here's how to run it in ten minutes.
OpenManus is an open-source AI agent framework anyone can install and run immediately: no invite code, no gimmicks, just a Python environment and an API key. Here is why you need it.
2026-07-11
AI Research
Your AI assistant forgets you every morning. This benchmark proves it.
VitaBench 2.0 tests whether AI agents can continuously extract and update user preferences from fragmented interactions over time. Results show that even state-of-the-art models struggle to build persistent user models, revealing a wide gap between chatbot competence and genuine collaborative intelligence.
2026-07-11