I needed to book flights for a bunch of upcoming travel. As always, I used Claude Cowork to do it. In the past, Cowork has been decent at booking flights, but with Opus 4.7, for the first time ever, it 1-shotted it!
AGENTS
-
Anthropic introduces Agent View in Claude Code CLI
By
–
Anthropic released Agent View in Claude Code CLI, from where users can observe and interact with parallel-running agents.
— 🚨 AI News | TestingCatalog (@testingcatalog) 12 mai 2026
It looks like preparation for a future in which agents will pursue broader long-term goals. Claude's mobile app is being prepared for that as well. pic.twitter.com/x5YWfHxatJAnthropic released Agent View in Claude Code CLI, from where users can observe and interact with parallel-running agents. It looks like preparation for a future in which agents will pursue broader long-term goals. Claude's mobile app is being prepared for that as well.
-
AI Council Conference Participation and Financial Agent Workshop Announcement
By
–
We’ll be at @AICouncilConf in San Francisco this week (May 12–14). Come say hi if you’re attending Join us tomorrow from 10:15–11 AM for a workshop with Charles Dickens: Towards Reliable Financial Agents: How a 4B Model Outsmarted a 235B Giant. See you there:
-
Critique of AI demos focusing on fun not valuable cases
By
–
Haven’t tried this but it seems very neat…
— Ethan Mollick (@emollick) 11 mai 2026
Yet all of the demos (except maybe one) are the model being fun and/or annoying by correcting or reminding in real time. There are obvious uses for this sort of model in meetings, education, training, etc. Why not demo valuable cases? https://t.co/COgZPUxVTmHaven’t tried this but it seems very neat… Yet all of the demos (except maybe one) are the model being fun and/or annoying by correcting or reminding in real time. There are obvious uses for this sort of model in meetings, education, training, etc. Why not demo valuable cases?
-
Scaling from Single to Multi-Agent Workflows
By
–
The best way to level up from 1 agent => many agents. No more cycling between terminal tabs https://t.co/PjQpKdi1aO
— Boris Cherny (@bcherny) 11 mai 2026The best way to level up from 1 agent => many agents. No more cycling between terminal tabs
-
Real-time model streaming with tool use
By
–
real time model streaming audio/video/text in and out with tool use https://t.co/M68lEOpFFF
— Yohei (@yoheinakajima) 11 mai 2026real time model streaming audio/video/text in and out with tool use
-
Agentic Context Engineering: Evolving AI Context Over Time
By
–
Instead of treating prompts as static, Agentic Context Engineering (ACE) explores how context can evolve over time through generation, reflection, and curation. Read the paper
-
OpenAI Unveils Daybreak: AI Agent System for Automated Cybersecurity Workflows
By
–
OpenAI acaba de presentar el futuro de la ciberseguridad automatizada.
— Nico (@nicos_ai) 11 mai 2026
Ha presentado Daybreak, un sistema de agentes de IA que:
• detectan vulnerabilidades
• validan fixes
• automatizan workflows completos de seguridad
Y esto ya no parece un simple copiloto.
→ Daybreak… https://t.co/VW8N7HxxN9 pic.twitter.com/HEuKfwbvLCOpenAI has just unveiled the future of automated cybersecurity. It has introduced Daybreak, an AI agent system that: • detects vulnerabilities
• validates fixes
• automates complete security workflows And this no longer feels like a mere copilot. → Daybreak combines -
Sigma Browser Adds Hermes Agent Support
By
–
Sigma browser now supports Hermes Agents 🤯
— Charly Wargnier (@DataChaz) 11 mai 2026
You can now run open-source models natively via their Eclipse engine for unlimited agentic workflows.
Private. Local.
Open-Source. No cloud. No subs.
Mac. Windows. iOS. Android 👀↓pic.twitter.com/tMwwPolCq9 https://t.co/XNCTCQXD1uSigma browser now supports Hermes Agents You can now run open-source models natively via their Eclipse engine for unlimited agentic workflows. Private. Local. Open-Source. No cloud. No subs. Mac. Windows. iOS. Android ↓
-
OpenAI Launches Daybreak, an Agentic Cybersecurity Tool
By
–
OpenAI just launched a new cybersecurity product called 'Daybreak' that pairs GPT-5.5 with Codex to act as an agentic security team across a codebase.
— The Rundown AI (@TheRundownAI) 11 mai 2026
The product scans repositories, identifies vulnerabilities, generates patches, and automates detection and response.
It ships… pic.twitter.com/WdZkgIPZMoOpenAI has just unveiled a new cybersecurity product named 'Daybreak,' which combines GPT-5.5 with Codex to function as an autonomous security team for a codebase. The tool scans repositories, detects vulnerabilities, generates patches, and automates threat detection and response. It is now available.