Perplexity 通过让模型自写代码将 token 成本降低 85%
perplexity 推出了 search as code，这是一种架构，让模型编写自定义 python 搜索管道而非调用固定 api。这承诺为复杂研究代理降低 85% 的 token 使用量并提高数据精度。
perplexity detailed its new search as code architecture, which replaces standard api calls with model-generated python scripts that execute in a secure sandbox. by using an agentic search sdk, models can perform custom retrieval, filtering, and reranking to keep context windows lean and improve result accuracy. the company demonstrated this on a cybersecurity task tracking 200 vulnerabilities, where the agent used 85% fewer tokens and outperformed standard pipelines. this approach challenges the dominant fixed api paradigm, suggesting that giving models programmatic control over search logic may be more efficient than universal, black-box tools.