OpenAI's GPT 5.4 in 10 Minutes

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5.4 is OpenAI's most capable model yet.
42 articles

Claude Code now has a native Loop feature for scheduling recurring prompts - from one-minute intervals to three-day windows. Fix builds on repeat, summarize Slack channels, email yourself Hacker News digests. All from the CLI.

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5.4 is OpenAI's most capable model yet.

Anthropic dropped a batch of updates across Claude Code and Cowork - remote control from your phone, scheduled tasks, plugin repos, auto memory, and stats showing 4% of GitHub public commits now come from Claude Code.

Inception Labs shipped the first reasoning model built on diffusion instead of autoregressive generation. Over 1,000 tokens per second, competitive benchmarks, and a fundamentally different approach to how AI generates text.

Anthropic brought git worktrees to Claude Code. Spawn multiple agents working on the same repo simultaneously - no merge conflicts, no context pollution, and your main branch stays clean.

Anthropic's Sonnet 4.6 narrows the gap to Opus on agentic tasks, leads computer use benchmarks, and ships with a beta million-token context window. Here's what actually changed.

Million-token context, agent teams that coordinate without an orchestrator, and benchmark scores that push the frontier. Opus 4.6 is Anthropic's biggest model drop yet.

Claude Code's popularity isn't an accident. It's built on bash, grep, and text files - tools with decades of stability. While competitors build on fragile abstractions, Claude Code bets on the Lindy effect.

Anthropic built Cowork in 1.5 weeks - a Claude Code wrapper that brings agentic AI to non-developers. Presentations, documents, project plans. Same power, no terminal required.

CloudFlare, Anthropic, and Cursor independently discovered the same pattern: don't load all tools upfront. Let agents discover what they need. The results are dramatic.

Claude Code skills can now reflect on sessions, extract corrections, and update themselves with confidence levels. Your agent gets smarter every time you use it.

The best Claude Code sessions start with questions, not code. Spec-driven development forces requirements discovery upfront - interview first, spec second, code last.

Claude Code can now control Chrome using your existing authenticated sessions. No API keys needed. Gmail, Sheets, Figma - your agent works across tabs like you do.
Showing 12 of 41 articles
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 94 topics
Browse All Topics