This article by Cankun Wang maps 50+ years of cybernetics theory directly onto modern AI agent system design, arguing that multi-agent architectures are unknowingly reinventing principles established decades ago. Starting with Wiener's feedback loops and Ashby's Law of Requisite Variety, the piece shows how foundational cybernetic concepts explain why single orchestrators fail at complex tasks and why multi-agent systems with proper variety engineering succeed. Stafford Beer's Viable System Model (VSM) is presented as a near-exact blueprint for current orchestrator-worker architectures, with its five subsystems (operations, coordination, internal management, intelligence, identity) mapping cleanly onto components like worker agents, conflict resolution layers, and quality audits.
The article moves through Perceptual Control Theory (defining what agents should perceive rather than output), second-order cybernetics (recognizing designers are part of the system they build), autopoiesis (systems that maintain their own operating conditions), and Pask's Conversation Theory (multi-level dialogue between agents operating at execution, description, and explanation layers). Donella Meadows' leverage points framework provides a practical hierarchy for system intervention, showing that tweaking parameters like temperature is far weaker than changing system goals or paradigms.
The most forward-looking section covers Karl Friston's Free Energy Principle and Active Inference, positioning it as the 21st-century continuation of cybernetics. The fusion of Active Inference with LLMs — where Active Inference serves as a cognitive control layer deciding what the LLM should attend to while LLMs provide the language interface — is highlighted as the key frontier for 2024–2026. The piece also introduces stigmergy as the critical scaling mechanism for moving from small agent teams to thousands, using shared environments instead of centralized communication. A comprehensive mapping table and prioritized reading list make this a practical reference for agent system designers.
Andi Peng announces the mission of Humans&, a company focused on building AI that centers human interaction, collaboration, and coordination. She emphasizes the need to move beyond traditional task-centric training approaches and scale toward more advanced capabilities.
The post highlights three key areas of innovation the team is pursuing: long-horizon memory, multi-agent systems, and user understanding. The tweet is truncated, suggesting additional details about their approach or vision were shared in the full thread.
Kimi Agent Swarm, built by Moonshot AI, represents a significant shift in how AI handles complex tasks — instead of relying on a single agent, it spawns up to 300 parallel sub-agents that self-organize like a temporary company. Shipped with Kimi K2.6 in April 2026, the system can coordinate 4,000 steps per run, outperforming GPT-5.4 on key benchmarks like BrowseComp Swarm (86.3% vs 78.4%) and DeepSearchQA (92.5 vs 78.6 f1-score). The author highlights a viral example: one prompt generating a 104-page, fully cited literature review exported directly to Word — no follow-up prompts required.
The guide identifies five core use cases where the swarm excels: discovery at scale (parallel research across hundreds of items), output at scale (book-length document synthesis), perspective at scale (simulated expert panels), batch processing (thousands of repetitive tasks), and long-horizon execution (multi-hour autonomous workflows). The author provides five reusable prompt patterns and a practical 60-minute onboarding roadmap, from account setup through first swarm run to export.
Critically, the piece is honest about limitations: orchestration degrades past ~100 agents on complex tasks, the swarm struggles with strictly sequential work, outputs from many sub-agents can lack coherence, and credit costs are substantial. The author positions Kimi Agent Swarm not as a replacement for ChatGPT (quick single-agent tasks) or Claude Cowork (local file-based knowledge work), but as a complement for wide, parallel-intensive jobs. The broader thesis is that horizontal scaling — coordinating many agents rather than building one bigger model — is the next frontier of AI capability, and Kimi shipped it first in a consumer-accessible product.
ROBIN is introduced as a pioneering multi-agent AI system designed to automate the full cycle of scientific discovery. It is described as the first AI system capable of autonomously performing all key steps of the scientific method, including hypothesis generation, experiment proposal, data analysis, and hypothesis refinement, all within an iterative loop.
This represents a significant development in the intersection of biology and AI, suggesting that autonomous research agents could accelerate the pace of scientific breakthroughs by handling the end-to-end research workflow without constant human intervention. The post highlights ROBIN's potential to reshape how discoveries are made by closing the loop between generating ideas and refining them based on experimental outcomes.