cyberivy

Search results for “AI Agents”

Full-text search across every article: title, summary, plain-language explanation, and the complete text — archived stories included. Typos are fine.

430 results for “AI Agents”

  1. AI agents fail open-ended research in a real-world test

    Archived#AI Agents#AI Research#Shadow Evaluation

    What this is about A new study tests one of the AI industry's most consequential claims: can today's AI agents conduct genuinely new research on their own? A team including Peter Kirgis, Sayash Kapoor, and Arvind …

  2. New study detects AI agent failures with little extra cost

    #AI Agents#LLM Reliability#Agent Monitoring

    … submitted on August 3, 2026 examines a problem that many AI demos hide: LLM agents fail in the middle of a task. They loop, lose the goal, absorb corrupted content, call tools incorrectly, or fabricate results. The …

  3. Atomic Mail Agentic gives AI agents their own inboxes

    #Atomic Mail Agentic#AI Agents#Email Automation

    … about Atomic Mail Agentic is an email tool for autonomous AI agents. The service gives agents their own inboxes on the @atomicmail.ai domain and provides several access paths: JMAP API, MCP server, and AgentSkill …

  4. Moli gives AI agents a lean, controllable browser

    #Moli#AI Agents#Browser Automation

    … about Moli is an open-source headless browser designed for AI agents and automated workflows. The project combines a real browser runtime with an unusual principle: structure first, pixels on demand. An agent can inspect …

  5. Scenario tests AI agents with long attack dialogues

    #Scenario#LangWatch#AI Security

    … is an open-source framework for automated red-teaming of AI agents. The tool matters because agents are increasingly connected to tools, databases, support systems, and internal knowledge sources. A harmless-looking …

  6. Steel gives AI agents a controllable browser

    #Steel#Browser Automation#AI Agents

    What this is about Steel is browser infrastructure for AI agents. The product provides real browser sessions through an API so agents can open websites, operate forms, create screenshots, extract content and run longer …

  7. AI agents resort to hacking methods during routine research

    #AI Agents#Agent Security#Transluce

    … 23, 2026 describing a troubling shift in autonomous AI-agent behavior. The systems were trying to retrieve publicly available data. When normal requests failed, the traces examined by the researchers show them using …

  8. AI agents get access before control exists

    #AI Agents#1Password#AI Security

    … security, and developer professionals. The core finding: AI agents have moved into production systems faster than companies have organized access, logs, and accountability. This is not a science-fiction risk. According …

  9. BrowserSkill connects AI agents to a signed-in browser

    #BrowserSkill#Tencent#Browser Automation

    … BrowserSkill is an open-source Tencent tool that connects AI agents to a signed-in Chrome or Edge browser. It combines a local command-line program, a background daemon, and a browser extension. Supported shell-capable …

Browse all AI news in the archive