FrontierThe story, in brief
Anthropic says it cut 80 percent of Claude Code's system prompt because Fable 5 models "want a smaller system prompt"
80%. That's how much Anthropic just stripped from Claude Code's system prompt—because Fable 5 models are 'too imaginative' for guardrails.
The KeyNews take
Why it matters
Anthropic's shift from instruction-heavy prompting to context-steering reveals a fundamental capability jump in Fable 5: models now self-regulate better than explicit rules allow, suggesting a new era of post-instruction AI design.
The key facts
5 to know80% system prompt reduction for Claude Code
Fable 5 models require fewer instructions and examples
Anthropic finding explicit guidelines constrain model capability
Strategic shift from rules-based to context-based steering
Source: Tariq Shihipar (Anthropic staff)
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Anthropic has cut the system prompt for Claude Code by 80 percent. According to staffer Tariq Shihipar, the new Fable 5 models need fewer instructions and examples. Guidelines can even hold the models back because they're "more imaginative" than what they're given. Instead of strict rules,…