ainewsblitz.com

Breaking

Anthropic's Claude Code Chief Boris Cherny Champions 'Routines Over Prompts' as Model Advances Slash System Prompt by 80%

Anthropic's Claude Code Chief Boris Cherny Champions 'Routines Over Prompts' as Model Advances Slash System Prompt by 80%
  • AI Agents
  • Software Dev & Coding
  • Foundation Models

Boris Cherny, the head of Anthropic's Claude Code, is reframing how developers should work with agentic coding tools, arguing that the real skill is no longer writing individual prompts but building routines that generate and run the prompting automatically. His now widely circulated framing—that he is not the one doing the prompting but rather the one creating a routine that does the prompting—captures a broader shift in how AI-assisted software development is being practiced at the frontier.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,874 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year