Self-Improving AI Agents: Sakana MASS and Its Shared Blind Spots
Sakana AI's MASS lets one model solve, judge, and refine its own work. Self-improving AI agents got better, but shared blind spots let errors pass as progress.
AI Agent Teams: Up to 5.1x the Cost, Rarely Better Quality
AI agent teams cost 1.8x to 5.1x more than single agents in Vals AI's coding test, and only 1 of 4 gained quality. Why higher effort often beats a team.
DeepMind Put 100 AI Agents in a Room. Some Cheated. Others Whistleblew.
Google DeepMind ran 100 Gemini agents through a math competition. Within 27 minutes of one agent finding an exploit, fraud spread — then 24% of agents spontaneously became whistleblowers. No one programmed them to.
Building Production Agentic AI: What IBM Learned the Hard Way
IBM deployed a multi-agent platform with LangGraph and MCP in months. Three hard lessons: instrument early, baseline before build, and solve data access first.
Claude Code Sessions Can Now Talk to Each Other Across Terminals
Anthropic's new cross-session messaging turns isolated Claude Code instances into a coordinated team — local sessions share context automatically, remote sessions route through Anthropic's servers.
Agentic AI Reliability: Two Engineering Disciplines Most Teams Skip
A Thoughtworks case study on PRINCE, a drug discovery agentic AI platform, reveals why context and harness engineering — not model choice — determine production reliability.
Data2Story: 7 AI Agents That Out-Verify Human Data Journalism
Oxford and Stanford researchers built a 7-agent system that turns a CSV into a verified interactive news article — and makes 93% of its statements verifiable, vs 25% for human-written articles.
Kong Gateway: How Agentic AI Fixed 12 Flaky Tests in 1.5 Weeks
Kong's three-tier Claude Code agent system closed 12 of 15 flaky tests in 1.5 weeks and surfaced two previously hidden production bugs without human intervention.
100 AI Agents, $1.3M/Month: What OpenClaw's Tab Reveals
A three-person team running 100 concurrent Codex agents spent $1.3M in 30 days — 603B tokens, 7.6M API requests. The real figure is $300K without Fast Mode.
Microsoft MDASH: 100 AI Agents Found 16 Windows Flaws
MDASH found 16 real Windows flaws — 4 critical RCEs — using 100+ AI agents that argue, verify, and prove exploits. Enterprise preview opens June 2026.
Stanford Study: Single AI Agents Beat Teams When Compute Is Equal
A new Stanford study challenges the multi-agent hype: when given the same compute budget, solo agents match or beat coordinated teams. Two exceptions matter — here's when teams actually win.
Meta's Hyperagents: The AI System That Gets Better at Getting Better
The Darwin Gödel Machine-Hyperagents architecture lets AI improve not just at tasks but at its own improvement process — and cross-domain transfer suggests the strategy generalizes.
Kensho's LangGraph Architecture: Multi-Agent Financial Data Retrieval at S&P Global
S&P Global's AI engine built Grounding — a router, domain agents, and aggregation layer on LangGraph — to unify fragmented financial data retrieval with trusted outputs.
Why Multi-Agent Systems are the Future of Productivity
Discover how specialized AI agents working in concert outperform monolithic models.