PulseAugur
中
实时 22:34:01
한국어(KO) 재귀적 자가개선(RSI)은 결국 무엇을 한다는 말인가? TL;DR: RSI(Recursive Self-Improvement, 재귀적 자가개선)는 모델이 스스로 문제를 만들어 풀고, 그 풀이 중에서 정답이 확실히 확인된 것만 골라 다시 학습 데이터로 삼아 자신을 개선하는 방식입니다. 핵심

AI模型通过自动化验证循环进行自我改进 · 跟踪6个来源

一种新的AI模型改进方法,称为递归自我改进(RSI),侧重于增强模型的核心能力,而不仅仅是其周围框架。该方法涉及AI生成自己的问题解决方案,在没有人为干预的情况下自动验证这些解决方案的正确性,然后对经过验证的集合进行再训练。此过程旨在改进模型。 AI

影响 这种方法可以通过减少对人工标记数据的依赖并使模型能够持续改进其核心推理能力来加速AI开发。

排序理由 该集群讨论了一种新颖的AI模型训练方法,这是一个研究课题。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

AI模型通过自动化验证循环进行自我改进 · 跟踪6个来源

本文如何被排名

Signal score
6 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群讨论了一种新颖的AI模型训练方法,这是一个研究课题。
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
model release, paper
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [6]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    TL;DR 函数调用或 MCP 代理会读取比用户消息更多内容。它还会读取它可以调用的工具的描述,以及那些工具的内容

    TL;DR A function-calling or MCP agent reads more than the user's message. It also reads the descriptions of the tools it can call, and the content those tools return . Both are text, both flow into the same context window, and a model does not natively distinguish "instruction fr…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    一位评论者发现我的代理将设计描述为正在运行代码。已验证的发布循环从未看到它。这是我构建的审计系统。# ai # python # automa

    A commenter caught my agent describing a design as running code. The verified publish loop never saw it. Here's the audit system I built. # ai # python # automation # devops # software # coding # development # engineering # inclusive # community The Loop Is Closed — So Who Checks…

  3. Mastodon — mastodon.social TIER_1 Español(ES) · [email protected] ·

    ZTC 通过读取模型内部状态来决定是否信任 AI 行为,无需第二个裁判模型。AUC 0.7289,每次决策 0.06 秒。# ai # llm # securi

    ZTC decide si confiar en una accion de IA leyendo el estado interno del modelo, sin un segundo modelo juez. AUC 0.7289 y 0.06s por decision. # ai # llm # security # spanish # software # coding # development # engineering # inclusive # community ZTC (Zero-Token Confidence): juzgar…

  4. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    TL;DR 混合专家(MoE)模型在磁盘上看起来很大,但对于任何单个 token,只有一小部分权重在工作。一个 180B 参数的 MoE 可以激活

    TL;DR Mixture-of-Experts (MoE) models look enormous on disk, but only a small slice of the weights does work on any single token. A 180B-parameter MoE can activate roughly 3B parameters per forward pass. That sparsity is exactly why 4-bit GGUF quantization behaves so differently …

  5. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    TL;DR 大多数语言模型之所以变得更好,是因为人们为它们编写了更多的训练数据。Darwin-180B-RSI 的改进方式不同。它尝试解决那些...

    TL;DR Most language models get better because people write more training data for them. Darwin-180B-RSI gets better a different way. It attempts problems whose answers can be checked automatically, keeps only the self-generated solutions that pass the check, and then retrains on …

  6. Mastodon — mastodon.social TIER_1 한국어(KO) · [email protected] ·

    什么是递归自我改进(RSI)?TL;DR:RSI(递归自我改进)是一种模型为自己创建问题来解决,然后仅使用正确验证的解决方案作为新训练数据来改进自己的方法。核心

    재귀적 자가개선(RSI)은 결국 무엇을 한다는 말인가? TL;DR: RSI(Recursive Self-Improvement, 재귀적 자가개선)는 모델이 스스로 문제를 만들어 풀고, 그 풀이 중에서 정답이 확실히 확인된 것만 골라 다시 학습 데이터로 삼아 자신을 개선하는 방식입니다. 핵심은 세 가지입니다. 첫째, 문제는 반드시 검증 가능해야 합니다. 둘째, 채점에 사람 정답표를 쓰지 않습니다. 셋째, 통과한 자기 풀이만 다음 학습에 남깁니다. 보통의 학습은 사람이 만든 정답 데이터가 있어야 합니다.…