AIToday
Large Language ModelsSimon Willison's WeblogPublished: Apr 19, 2026, 10:00 JST1 min read

Claude's system prompt underwent notable modifications between versions 4.6 and 4.7, revealing shifts in how Anthropic instructs its AI assistant.

Claude's system prompt underwent notable modifications between versions 4.6 and 4.7, revealing shifts in how Anthropic instructs its AI assistant.

3 Key Points

  1. System prompt changes between Claude Opus 4.6 and 4.7 were documented and analyzed

  2. The modifications reflect Anthropic's iterative approach to refining AI behavior and capabilities

  3. Specific differences in instructions likely impact how Claude responds to user queries

  4. Such updates demonstrate ongoing efforts to improve AI assistant consistency and performance

Ask the AI about this article →

Simon Willison's WeblogRead Original Article

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Walmart settles opioid claims for $50MTop Companies AI · 1h ago
  • Tim Cook's legacy hinges on Apple's AI betTop Companies AI · 1h ago
  • CrowdStrike Falcon Guardian Targets AI SecurityTop Companies AI · 1h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleAn analyst highlights a disciplined approach to AI investment as the winning strategy among the 'Magnificent Seven' tech stocks heading into earnings season.