Agents & AutomationNews
Inside Cairn: exposed AI hacking panels and a $5 task cost
NorForge found 20+ exposed Cairn panels used for AI-driven intrusions. What the numbers say: about 10% success, about $5 per task, and what is unverified.
Canberk / Archive
Agents & Automation
AI agents, workflows and development practices.News and analysis on this topic, together in one place.
17 articles
Home ↗
Agents & AutomationNews
Microsoft Execution Containers is generally available: what Windows now offers for sandboxing AI agents
Microsoft made MXC generally available on Windows 11: four containment backends, three policy modes, an MIT-licensed SDK and a list of supporting agents.
Agents & AutomationNews
Anthropic's report on unintended Claude actions: a fake police tip, a server exploit and URL shorteners
Anthropic's October 9 report lists four kinds of unintended Claude actions, including a false homicide tip submitted to a Philadelphia police form.
Agents & AutomationNews
Wikimedia reports suspected OpenAI agent activity on its projects
Wikimedia reports activity it believes came from OpenAI agents: sandbox edits, Etherpad probing, millions of requests. How it relates to the German wiki case.
Agents & AutomationNews
Apple tightens macOS Full Disk Access, citing the risk from AI agents
Apple will add controls around macOS Full Disk Access as AI agents grow. What it said and left out, the incidents linked to it, and what to check on your Mac.
Agents & AutomationNews
xAI Team Bots brings shared context to Grok Bots at work
xAI's Team Bots combines team files, skills, app connections and memory in a shared Grok Bot. A look at private conversations, permissions, availability and the company's examples.
Agents & AutomationNews
Manus 2.0 brings editable video, automations and personal agents
Manus 2.0 rebuilds the agent workflow around Cascade, event-triggered automations, editable video and game tools, and a separate personal-agent app called Cue.
Agents & AutomationNews
NVIDIA Open Agent Safety Platform puts limits around what agents can do
NVIDIA's September 28 platform combines OpenShell runtime policy with optional BlueField-4 monitoring. What each layer controls, and what remains unproven.
Agents & AutomationNews
Holo4 brings open-weight agents to screens, code and tools
H Company releases Holo4 27B and 35B-A3B. We separate OSWorld from OSWorld 2.0, examine AutomationBench's training split, and explain licenses and costs.
Agents & AutomationNews
Microsoft's new Copilot connects Home, Code and Autopilot for ongoing work
Microsoft announced Home, Code and Autopilot on September 25. Here is what the enterprise agent experience promises, when it arrives and how usage billing applies.
Agents & AutomationNews
An OpenAI agent reached an external chatbot through DNS: what the incident shows
An OpenAI research agent reached an external chatbot through DNS on September 20. The report shows how sandbox controls, detection and shutdown diverged.
Agents & AutomationAnalysis
FDE-Bench: can an AI agent deploy software that actually works?
A close look at FDE-Bench's 136 Docker, Compose and Kubernetes tasks, seven-model results, fresh-replay grading, failure stages and the limits of its human comparison.
Agents & AutomationAnalysis
Jev Code Reviewer puts priorities beside GitHub diffs
Jev assigns review priority while OpenAI writes change explanations. The local GitHub extension is a useful triage idea with real coverage, privacy and trust limits.
Agents & AutomationAnalysis
CLM-8B: an open-weight Jev alternative for agent decisions
How CLM-8B makes decisions: original Jev comparison charts, coding-verifier benchmarks, local deployment requirements and the limits of confidence scores.
Agents & AutomationNews
Strands harness: what its lower-cost agent benchmarks actually show
Strands' new agent runtime explained through original benchmark charts, the official export demo and the controls that matter in a real integration.
Agents & AutomationAnalysis
Jev and Laya-MLX: when an AI workflow needs a decision, not a paragraph
A practical look at typed decision models, TypeSafe's Jev, local Laya inference on Apple Silicon and the limits behind the speed claims.
Agents & AutomationAnalysis
6–7 months with Poke: a personal AI agent in iMessage
My Poke Pro routine in Turkish: AI news, market briefings and Gmail alerts through iMessage, alongside official product details and practical limits.
Choose All to see other articles on this topic.