~/bookmarks

Yutori

We’re building AI agents that can reliably do everyday digital tasks for you on the web, towards an AI chief-of-staff for everyone.

Terminal-Bench

A benchmark for terminal agents

Shell + Skills + Compaction: Tips for long-running agents that do real work

Practical patterns for building with skills, hosted shell, and server-side compaction in the Responses API.

Anthropic's Claude 4 Announced: New AI Capabilities for Coding, Agents, and Claude Code in VS Code / IntelliJ

Anthropic launches Claude Opus 4 and Sonnet 4, setting new benchmarks for coding, reasoning, and AI agents with extended thinking capabilities and imp...

Claude Code: Automatic Linting, Error Analysis, & Custom Commands

How to use Claude Code's error analysis slash-commands and create your own linting commands to automate repetitive CLI tasks.

ComposerAI

AI email client / mailbox for agentic search and tasks

Build a Reasoning Model (From Scratch)

Sebastian Raschka

Description A deep dive into the architecture and implementation of AI models capable of logical deduction and multi-step reasoning. It explains how t...

Learn AI-Assisted Python Programming, Second Edition

Leo Porter, Daniel Zingaro

See how an AI assistant can bring your ideas to life immediately! Once, to be a programmer you had to write every line of code yourself. Now tools lik...

Heroes Jobs

The app for Gen Z searching for a job

Health IQ

Insurance platform offering better rates for health-conscious individuals.

Turing

AI-powered platform connecting companies with vetted software developers for remote work.