English(EN) "MirrorCode: AI can rebuild entire programs from behavior alone." "Across all 25 target programs, 17/25 had at least one perfect-scoring run. Four more targets

MirrorCode AI仅凭行为即可重建程序

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-05 03:00

一个名为MirrorCode的新AI系统能够仅通过观察其行为来重建整个软件程序。在对25个目标程序的测试中，MirrorCode在其中17个程序上获得了满分，另外四个程序的得分超过99%。该AI通过重新实现大型程序展示了其能力，其中包括一个包含约16,000行Go代码的生物信息学工具包。 AI

影响展示了一种新颖的程序合成方法，可能对软件开发和AI代理能力产生影响。

排序理由该集群描述了一个新的AI系统及其功能，并有研究论文支持。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — fosstodon.org 阅读 →

MirrorCode

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: Tool; 该集群描述了一个新的AI系统及其功能，并有研究论文支持。[lever_c_demoted from research: 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: 64 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]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-08-05 03:00

"MirrorCode：AI仅凭行为即可重建整个程序。" 在所有25个目标程序中，17/25至少有一个完美得分的运行。另外四个目标

"MirrorCode: AI can rebuild entire programs from behavior alone." "Across all 25 target programs, 17/25 had at least one perfect-scoring run. Four more targets had a near-perfect run scoring over 99%. AI models successfully reimplemented large target programs; for example, one of…

链接 arxiv.org/…/2606.30182

本文如何被排名

报道来源 [1]

"MirrorCode：AI仅凭行为即可重建整个程序。" 在所有25个目标程序中，17/25至少有一个完美得分的运行。另外四个目标

相关话题