aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分34

ByteAsk 推出 C/C++ 编程代理,称可减少修复任务的 token 用量

AI 导读

ByteAsk 推出面向 C/C++ 的编程代理:在模型读取代码前,先按构建视角定位修改位置,并标记可能需要同步修改的代码。发布材料称,它在修复同样数量漏洞的测试中减少了 78% 的 token 用量,成本降低 68.1%;材料未说明测试项目和评估方法。

原帖引用 · 原文

@rohanpaul_ai

Another great launch to reduce token cost.

Most of what you pay an AI agent to fix C++ goes to finding the code, before any fixing.

@ByteAsk removed 78% of the tokens and fixed exactly as many bugs and at 68.1% lower cost.

ByteAsk is a C and C++ coding agent that finds where a fix belongs before the AI model starts reading. Before the model starts, ByteAsk’s context engine reads the code as the build sees it and marks where the change belongs.

It also flags sibling sites needing the same edit, and the agent checks its patch against only the tests covering them.

That upfront map cut pooled tokens from 1,795K to 395K per run, with about 80% savings on little-known projects and hard issues.

引用Anirudha (YC F26)@4n1rudh4
Introducing @ByteAsk Your AI C++ engineer, and a swarm of them > SOTA on multi SWE bench (C/C++) > 60% fewer tokens wrt cc/codex > auto debug/perf/optimize/test with native C/C++ tools Free plan. Open Source. https://t.co/FhvdqMcdtp https://t.co/pGNxndCYEK
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

产品
发现内容有误?提交纠错