One catch though. The bright future goes to people who can direct an agent and check its work. Direction on its own just builds a faster mess.
AGENTS
-
AI Agents Beyond LLMs: Orchestration and Architecture
By
–
AI agents are more than LLMs • Skills → expertise
• MCP → external connections
• Subagents → delegated tasks
• Hooks → automation
• Memory → persistent context Real AI systems are orchestration layers. Via Giuliano Liguori (
@ingliguori
) #AI #AIAgents #MCP -
Gary Marcus says Claude Code works in neurosymbolic system but fails alone
By
–
it’s fine as a component in a larger (neurosymbolic) system, which is at last what Anthropic figured out, with Claude Code. but did in fact get stuck when used on its own, as i had predicted.
-
Types of LLMs in AI Agents from @ingliguori
By
–
Types of #LLMs in #AIAgents by @ingliguori #GenerativeAI #ArtificialIntelligence #MachineLearning #ML
-
Coding changed forever: AI agents rewrote rules – video
By
–
Coding Changed Forever
AI agents rewrote the rules I just made a video covering everything since the AI boom Watch it here: https://
youtu.be/ShFn3MG0h8s -
Red/green TDD for agents with regression tests
By
–
I am firmly in the red/green TDD team for agent code, I like having a test suite that protects against breaking old features when they make new changes – https://simonwillison.net/guides/agentic-engineering-patterns/red-green-tdd/ …
-
Automated Tests for Coding Agent Code
By
–
Do you include automated tests for the code that your coding agents write?
-
World models as mental simulators for robot learning survey
By
–
What if robots could predict the world before acting? A consortium of researchers from NTU, UC Berkeley, Stanford, and other top institutions surveyed the rapid rise of world models in robot learning. These models act like mental simulators: they predict how the environment
-
Japanese Developer Discovers Claude Code Skills MCP Trick
By
–
Un développeur japonais a découvert un trick de Claude Code dont personne ne parle.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 25 mai 2026
Il a créé un skill appelé “find skills”.
C’est comme un mini package MCP branché directement dans Claude Code.
Il décrit une tâche une seule fois.
Ensuite, Claude explore automatiquement des… https://t.co/2WWlFeEf1p pic.twitter.com/dY3fQjwklYUn développeur japonais a découvert un trick de Claude Code dont personne ne parle. Il a créé un skill appelé “find skills”. C’est comme un mini package MCP branché directement dans Claude Code.
Il décrit une tâche une seule fois.
Ensuite, Claude explore automatiquement des -
Google’s Code Review Standard for AI Agent Implementation
By
–
Google has just published the Code Review standard that its internal engineers use. You can literally give this documentation to an AI agent and turn it into a code reviewer with Google standards. Most AIs only generate code. Now they can also: → detect bad practices
→