Anthropic says it cut 80 percent of Claude Code's system prompt because Fable 5 models "want a smaller system prompt"
Quick Answer
Anthropic has reduced the system prompt for Claude Code by 80%, as the new Fable 5 models require fewer instructions.
Quick Take
This shift allows the models to be more imaginative and effective, as they are now guided by context rather than strict rules.
Key Points
- Claude Code's system prompt was cut by 80% to enhance model performance.
- Fable 5 models are designed to operate with fewer instructions and examples.
- Anthropic emphasizes context over strict guidelines for improved creativity.
- Staffer Tariq Shihipar highlights the imaginative capabilities of the new models.
📖 Reader Mode
~1 min read
Jul 2, 2026
Anthropic says it has cut 80 percent of the system prompt for Claude Code. Tariq Shihipar, a member of technical staff at Anthropic, describes a fundamental shift in how AI models are steered, tied to the new Fable 5 models, also known as the Mythos class. More instructions and more examples no longer automatically lead to better results. "Most recently we found this new class of models want a smaller system prompt," Shihipar says, and examples "tend to constrain it because it's actually more imaginative than the examples we give it." Instead of hard rules like "do not do this," Anthropic now tries to steer Fable models through context, he adds.
According to Shihipar, this change happened in stages. Early models needed short prompts with lots of examples and restrictive instructions. Prompts then grew longer as models got better at understanding them. Now they're getting shorter again.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
