Microsoft ASSERT Converts AI Policies Into Test Suites
Microsoft's open-source ASSERT framework turns natural language behavior specs into executable, auditable test suites for AI agents and LLM applications.
Articles Tagged "AI Agents"
Reasoning Leaks, Hard Limits, and Self-Aware LLMs
Three new papers expose how reasoning traces can be extracted from supposedly hidden model internals, where chain-of-thought hits an architectural ceiling, and how RL teaches models to know when to quit.
New Open Standard Puts AI Agents Under Runtime Control
The Agent Control Standard defines open middleware hooks that let teams block, allow, or modify AI agent actions before they reach production systems.
Nvidia Enters the PC Market With RTX Spark Superchip
Nvidia's RTX Spark packs 20 Arm CPU cores and a Blackwell 2.0 GPU with 6,144 CUDA cores into a 45-80W Windows laptop chip, targeting Apple Silicon head-on.
Cut CoT Costs, Fix Agent Memory, Test Clinical AI
Three papers: smarter CoT trimming cuts reasoning length by 50%, a plug-in context manager rescues frozen agents on long tasks, and a 960K-item clinical benchmark exposes LLM gaps in hospitals.
Antigravity 2.0 Review: Agent-First, Rocky Launch
Google's Antigravity 2.0 rewrites the platform from a browser IDE into a five-surface agent suite. The architecture is ambitious, the launch was a mess.
BadHost: The Auth Bypass Lurking in 325M AI Systems
CVE-2026-48710 in Starlette lets a single malformed HTTP header bypass authentication on vLLM, LiteLLM, FastAPI, and every MCP server in production.
Kore.ai Artemis Review: Enterprise Agent Control Plane
Kore.ai's Artemis platform brings a compiled blueprint language and governance-first architecture to enterprise multiagent AI - ambitious, but Azure-only for now.
Anthropic Ships Opus 4.8 with Multi-Agent Workflows
Claude Opus 4.8 launches with dynamic workflows for parallel subagent orchestration, hitting 69.2% on SWE-bench Pro and introducing granular effort controls at unchanged pricing.
Alignment Faking, Agent Collusion, and Brittle Safety
Three new papers decompose alignment faking into measurable drivers, show safety-aligned agents collude when it pays, and find standard guardrails miss the worst safety failures.
Robinhood Opens AI Agent Trading to 27M Retail Users
Robinhood launched MCP-powered agentic trading in beta on May 27, letting AI agents from Claude and ChatGPT manage stock portfolios for 27.5 million retail customers - while regulators work out who's responsible when it goes wrong.
Cognition Raises $1B at $25B as Devin Hits $492M ARR
Cognition's $1B funding round at a $25B pre-money valuation puts Devin's $492M ARR and model-agnostic architecture under scrutiny as every major AI lab ships its own coding agent.
