English(EN) Skip RAG entirely — SubQ loads your whole codebase in one pass

Subquadratic 发布 SubQ LLM，实现单次代码库处理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-20 16:56

Subquadratic Inc. 发布了 SubQ，这是一款新推出的长上下文语言模型，声称能够一次性处理整个代码库或文档集。该模型采用了亚二次方稀疏注意力设计，理论上允许计算量与上下文长度呈线性扩展，而非二次方。虽然供应商发布的基准测试在长上下文检索方面显示出有希望的结果，但据报道，与前沿模型相比，其编码能力一般。该模型目前处于私有测试阶段，可通过与 OpenAI 兼容的 REST API 访问，标称上限为 1200 万个 token，但迄今为止的评估仅限于 100 万个 token。 AI

影响通过消除传统的 RAG 限制，可能为代码分析和文档处理带来新的工作流程。

排序理由初创公司发布的新模型，声称拥有新颖的架构和性能指标。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; 初创公司发布的新模型，声称拥有新颖的架构和性能指标。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 105 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — LLM tag TIER_1 English(EN) · Creeta · 2026-06-20 16:56

完全跳过 RAG — SubQ 一次性加载整个代码库

<p>The pitch behind SubQ is simple enough to fit in one sentence: stop chunking and retrieving, and just load the whole codebase into a single context window. The architecture that supposedly makes that affordable, and the evidence that does and doesn't back it up, is where the i…

本文如何被排名

报道来源 [1]

完全跳过 RAG — SubQ 一次性加载整个代码库

相关实体

相关话题