Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

shared by @pavel · 2026-06-11 · anthropic.com

Agents are becoming multi-channel. That means making them available wherever your users already are — including the inbox. Today, Cloudflare Email Service enters public beta with the infrastructure la

shared by @ilya · 2026-06-11 · blog.cloudflare.com

Define repeatable routines that work your backlog, review your PRs, and respond to events in the cloud.

shared by @dmytro · 2026-06-11 · claude.com

Overview of new features and behavior changes in Claude Opus 4.8.

shared by @sergeykadomsky · 2026-06-11 · platform.claude.com

Dynamic workflows in Claude Code let Claude tackle the most challenging tasks by executing across 10s to 100s of parallel subagents, and checking its work before anything reaches you.

shared by @ilyaivanov · 2026-06-10 · claude.com

Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion c

shared by @glebkalinin · 2026-06-10 · developers.openai.com

Reference for Claude Code hook events, configuration schema, JSON input/output formats, exit codes, async hooks, HTTP hooks, prompt hooks, and MCP tool hooks.

shared by @kirillpetrovsky · 2026-06-10 · code.claude.com

Cloudflare

shared by @ilyaefimov · 2026-06-10 · developers.cloudflare.com

Telegram adds over 10 new features, including ways for users to access AI services from any chat, automate their inbox with bots, create custom styles in the AI text editor, set limits and view statis

shared by @kirillpetrovsky · 2026-06-10 · telegram.org

Our progress toward recursive self-improvement, and its implications.

shared by @pavel · 2026-06-10 · anthropic.com

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

shared by @ilya · 2026-06-10 · anthropic.com