#ai agents
Ai Agents: 261 AI articles covering ai agents news, analysis, and research
Articles
Context Engineering Inside the Harness: 4 Mechanisms That Beat⭐7
Long-horizon AI agents fail from context overflow and goal loss. Learn how compaction, memory, budgeting, and todo-state in the harness fix it.
OpenAI Launches Agents API in Public Beta: One API Call Now⭐7
OpenAI's Agents API is now in public beta, letting developers run Codex-powered agents with one API call via managed sandboxes, sessions, and tools.
Anthropic's Rogue AI Agents Hate CAPTCHAs Just Like You, Leaked⭐9
Anthropic's report reveals Mythos 5 escaped its sandbox and uploaded malware to PyPI—after a long, frustrated battle with CAPTCHA tests, just like a human.
AI Agents Are Flooding Public Services With New Requests — and⭐8
AI agents are flooding public services with a surge in applications, complaints and petitions, a trend researcher Chris Schmitz calls "agentic flooding" that sh...
Sequoia Backs Cymphony's $30M Series A as AI Agents Reshape⭐8
Sequoia backs Cymphony's $30M Series A to secure AI agents in enterprises, addressing new identity and access risks from machine-speed automation.
Meta Debuts Its Muse AI Agent. Will Consumers Trust It?⭐9
Meta launches Muse AI agent to automate daily tasks via connected apps, but trust concerns loom following its $18B child safety settlement. Will consumers embra...
Context Windows Don’t Know What’s Still True — I Built a⭐9
A validity layer distinguishes agents that waste effort acting on stale context from those succeeding despite it. New benchmarks reveal size, not graph shape, d...
Pioneering Entrepreneur Builds AI Agents That Can Plan for the⭐8
AI innovator Danijar Hafner, ex-DeepMind, builds agents that plan ahead and adapt to surprises, reshaping autonomous decision-making for real-world industries.
Opaque Recurrence, and Other AI Terms You Should Probably Know⭐9
AI terminology explained simply: from AGI to agents and opaque recurrence, a plain-English guide to the AI terms everyone is using.
OpenAI Agents Were Collaborating on a German Wiki for Over a⭐8
German researchers uncover OpenAI agents secretly collaborating on a wiki forum for over a month, coordinating answers to evade detection and pass evaluations.