New research introduces Tri-System Theory to explain how we think with AI. It builds on the idea that we have two main thinking styles: System 1 for fast, intuitive thinking. and System 2 for slow, deliberate thinking.
This new theory adds a System 3: thinking with AI. The study found people often "surrender" to AI, meaning they accept AI's answers without much questioning – even if those answers are wrong. This can sometimes improve performance, but often leads to mistakes.
People who trust AI more, and who don't enjoy deep thinking, are more likely to rely on it. In short, we're increasingly letting AI do some of our thinking, and this has both benefits and risks.
This new theory adds a System 3: thinking with AI. The study found people often "surrender" to AI, meaning they accept AI's answers without much questioning – even if those answers are wrong. This can sometimes improve performance, but often leads to mistakes.
People who trust AI more, and who don't enjoy deep thinking, are more likely to rely on it. In short, we're increasingly letting AI do some of our thinking, and this has both benefits and risks.
Anthropic has released a guide detailing “Skills,” a new method for customizing Claude by teaching it specific tasks through dedicated folders containing structured metadata in a single SKILL.md file. Skills enable consistent automation of workflows, enhancement of existing tools via accumulated expertise, and standardized document creation, functioning alongside MCP (which grants Claude tool access). The guide highlights five effective patterns – sequential orchestration, multi-tool coordination, iterative refinement, context-aware tool selection, and domain-specific intelligence – while cautioning against vague descriptions, overly complex skills, and lack of error handling. Ultimately, Skills aim to transform Claude from a general chatbot into a focused, integral part of daily work processes.
FastCode is a token-efficient framework for comprehensive code understanding and analysis, delivering superior speed, exceptional accuracy, and cost-effectiveness for large-scale codebases and software architectures. It features a three-phase framework for semantic-structural code representation, lightning-fast codebase navigation, and cost-efficient context management.
This document provides 68 samples of some of the intelligent textbooks that have been created with our workflows. This list is changing every day, so please check back frequently.
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries
A collection of prompts designed to be used with AI coding assistants to build various use cases, ranging from personal CRM and knowledge bases to content pipelines and social media research.
A review of Google's Auto Browse agent, testing its ability to perform various online tasks, from playing web games to managing playlists and scanning emails. The agent shows promise but requires significant supervision and struggles with certain tasks, particularly those involving prolonged monitoring or complex interfaces.
T-Mobile is launching Live Translation, a real-time call translation feature for over 50 languages, built directly into its network. It requires no apps or downloads and will be available through a spring beta program.
This article details how Google SREs are leveraging Gemini 3 and Gemini CLI to accelerate incident response, root cause analysis, and postmortem creation, ultimately reducing Mean Time To Mitigation (MTTM) and improving system reliability.
Structured, temporal memory for AI agents. memv extracts knowledge from conversations using a predict-calibrate approach: importance emerges from prediction error, not upfront LLM scoring.
