Anthropic says it has trimmed more than 80% of the system prompt that steers Claude Code, its AI coding agent, and saw no measurable drop in coding performance when running on its newest Claude 5-generation models. The change, detailed in a company engineering post titled "The new rules of context engineering for Claude 5 generation models," reflects a broader shift in how the company thinks about instructing more capable models.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.