№ 02 / SUMMARIES

#claude

Every summary, chronological. Filter by category, tag, or source from the rail.

Tag · #claude
DAY 01April 20, 2026 APR 20 · 20261 SUMMARIES
Simon Willison's Weblog

Claude Opus 4.7 System Prompt: Act First, Stay Safe, Cut Verbose

Opus 4.7 prioritizes acting on ambiguous requests with tools over asking users, expands child safety to taint entire conversations, reduces verbosity, adds PowerPoint tool, and drops legacy fixes like Trump presidency note.

Simon Willison's Weblog
DAY 02April 19, 2026 APR 19 · 20262 SUMMARIES
Simon Willison's WeblogAI & LLMs

Claude Opus 4.7 System Prompt Boosts Autonomy and Safety

Opus 4.7 refines Claude to act first with tools on ambiguous tasks, expands child safety refusals across conversations, cuts verbosity, and adds guards against one-word answers on controversies.

Simon Willison's Weblog
Nate Herk | AI AutomationAI Automation

Claude AI Generates Motion Graphics Videos in Minutes

Use Claude Design for no-code conversational video creation or Claude Code + Hyperframes for customizable motion graphics, turning hours of editing into minutes without manual work.

DAY 03April 18, 2026 APR 18 · 20262 SUMMARIES
Nate Herk | AI AutomationAI Automation

Claude Code Routines for 24/7 Cloud AI Agents

Claude Code's Routines run scheduled prompts in Anthropic's cloud, enabling always-on agents without local hardware—setup covers API gotchas, limits, and security for reliable automation.

Nate Herk | AI Automation
Nick Saraev

Claude Routines: Schedule AI Agents via API and Webhooks

Claude's Routines feature enables scheduling, webhooks, and API-triggered cloud AI agents, demonstrated with email drafting from inbox and converting transcripts to proposals—replacing complex n8n setups.

Showing 8 of 8