PulseAugur
中
实时 08:04:19
English(EN) Thinking Machines' Inkling scores 41 on the Intelligence Index, leading U.S. open-weight releases. The model shows strong reasoning benchmarks but a 63% halluci

Thinking Machines 的 Inkling 以 41 的智商指数得分领跑美国开源模型

Thinking Machines 发布了 Inkling,这是一款开源人工智能模型,在智商指数中获得 41 分,使其成为美国开源模型中的佼佼者。虽然 Inkling 展示了强大的推理能力,但在基于知识的任务中,其幻觉率也高达 63%。该模型对 GPU 内存的巨大需求给潜在采用者带来了实际挑战。 AI

影响 为美国开源模型树立了新的基准,但高幻觉率和内存需求带来了采用挑战。

排序理由 Frontier-lab 模型发布,附带系统卡。[lever_c 从 frontier_release 降级:ic=1 ai=1.0]

在 Mastodon — fosstodon.org 阅读 →

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

Thinking Machines 的 Inkling 以 41 的智商指数得分领跑美国开源模型

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
Frontier-lab 模型发布,附带系统卡。[lever_c 从 frontier_release 降级: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
80 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]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Thinking Machines' Inkling 在智商指数中获得 41 分,领先美国开放权重模型发布。该模型在推理基准测试中表现强劲,但幻觉率为 63%

    Thinking Machines' Inkling scores 41 on the Intelligence Index, leading U.S. open-weight releases. The model shows strong reasoning benchmarks but a 63% hallucination rate on knowledge tasks. Deployment requires substantial GPU memory, raising practical questions for companies we…