PulseAugur
EN
LIVE 10:03:34

Moonshot AI unveils Kimi K3, largest open-weight model with novel memory tech

By PulseAugur Editorial · [3 sources] ·

Moonshot AI has developed Kimi K3, an open-weight model boasting 3 trillion parameters, making it the largest of its kind. The innovation lies not just in scale but in a novel memory management system called Kimi Delta Attention (KDA). KDA utilizes a 'Delta Rule' to update memory in place, drastically reducing computational costs associated with long context windows, unlike traditional transformer models that linearly increase memory and quadratically increase computation with context length. This approach was first tested in the smaller Kimi Linear model and is now scaled up in Kimi K3, aiming to challenge leading proprietary models. AI

IMPACT Sets a new benchmark for open-weight models and introduces a novel memory architecture that could significantly reduce training and inference costs for large context windows.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Towards AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Moonshot AI unveils Kimi K3, largest open-weight model with novel memory tech

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, infra
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
45 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. Towards AI TIER_1 English(EN) · Mohammed Saqlain ·

    Inside Kimi K3: How Moonshot AI Built the Largest Open-Source Model

    <p>Moonshot AI recently released Kimi K3, the largest open-weight model available as of mid-2026, and the first open model to reach the 3-trillion-parameter class. While most labs chase scale by simply adding more hardware, Moonshot took a different path. Instead of just building…

  2. Towards AI TIER_1 English(EN) · Pop123 ·

    The End of Token Waste: Inside Moonshot AI’s Leaked Kimi K3.1 Architecture

    <div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/the-end-of-token-waste-inside-moonshot-ais-leaked-kimi-k3-1-architecture-1680252877ef?source=rss----98111c9905da---4"><img src="https://cdn-images-1.medium.com/max/1418/1*mUz7TDv2Dqn7gT8…

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

    🧠 Researchers test Moonshot AI's Kimi K3 model within Claude's code environment. The evaluation examines how the model performs when integrated into existing de

    🧠 Researchers test Moonshot AI's Kimi K3 model within Claude's code environment. The evaluation examines how the model performs when integrated into existing development workflows. 💬 Hacker News 🔗 https:// philippdubach.com/posts/kimi-k 3-inside-claude-code # AI # MachineLearning…

    LINKS philippdubach.com/…/kimi-k3-inside-claude…

RELATED ENTITIES

RELATED TOPICS