Systems that plan, call tools, and act over many steps. Protocols like MCP, memory that writes rather than retrieves, tool-use reliability, and what separates an agent demo from an agent running in production.
An agent skill scanner is an eval, and its leaderboard score is pass@1 against an adversary who rewrites the input. Why the eight-scanner bypass was inevitable.
Eval harness security after the July 2026 OpenAI/Hugging Face sandbox escape: egress as the failed control, answer keys as secrets, and a threat model you can run.
Agent memory is not RAG: it needs a write path, not just retrieval. Memory types, temporal knowledge graphs, forgetting by design, and why chat logs fall short.
Agent evaluation for tool use: why pass@1 hides unreliability, the pass^k metric, BFCL and tau-bench, state-based vs LLM-judge scoring, and building a harness.
World models explained: latent dynamics models, generative simulators like Genie 3, and language world models inside LLMs, plus concrete tests for coherence.
Explore how AI agents, open protocols like MCP and A2A, and computer-use models are transforming the internet from a document-retrieval system into an agentic web where software reasons, acts, and collaborates autonomously.
Learn the architecture, frameworks, and reliability patterns needed to deploy AI agents in production. Covers LangGraph, CrewAI, multi-agent systems, and more.
Learn how Model Context Protocol (MCP) became the universal standard for connecting AI models to tools and data, reshaping the entire AI ecosystem.
Explore vibe coding: the AI development paradigm coined by Karpathy. Compare Cursor, Claude Code, Google Antigravity & Copilot — with honest takes on which tools actually deliver.