AI推荐理由Perplexity CEO 在 X 上一次性列出 7 项开源贡献，信息密度高且覆盖多模态决策模型、上下文嵌入、Apple Silicon 本地推理引擎、端侧 PII 分类器、研究 Agent 基准、终端检测响应与供应链扫描等方向，对 AI 模型、Agent 与开发工具有实际参考价值。但内容为推文自述，仅给出部分基准数字（如 85.7% 平均、1.23x/1.35x 加速、0.6B 参数），未提供模型卡、代码仓库或评测细节，'SoTA''beats OpenAI' 等表述缺乏可验证证据，且发布时间为 2026-10-02，需按原发证据理解。互动量仅作传播信号，不折算为质量分。
78浏览 33,223点赞 409评论 23转发 25
正文
a few open source contributions from perplexity recently:
•pplx-decider-v1-27b: SoTA multimodal decision model. 85.7% average across 11 benchmarks, ahead of Jev.
•pplx-embed-v2-context-9b-preview: SoTA contextual embeddings, best on ConTEB and turbopuffer context-bench.
•Lily: local inference engine for Apple silicon. rust plus custom metal kernels, no pytorch or mlx. 1.23x faster prefill and 1.35x faster decode than MLX-LM on an M5 Max
•PII-Tracer: 0.6B on-device PII classifier that decides when a hybrid compute task stays on your Mac. beats OpenAI’s Privacy Filter on all 5 public benchmarks. also released with the PII-TRACE benchmark: 13k conversations in 13 languages
•WANDR: benchmark for wide and deep research agents. 500 tasks needing 170k source-backed records
•Numbat: agent detection and response for laptops and workstations. 52 rules, single go binary for macOS, linux and windows
•Bumblebee: read-only supply chain scanner for dev machines. covers packages, MCP configs, and editor and browser extensions.
a lot more open source contributions coming soon!