← Library

2026-02-10

8 saved articles

  3. Aigarth - The AI Garden on Qubic Network | Qubic Docs

    docs.qubic.org

    Aigarth is a pioneering project that is being developed on top of the Qubic network. It combines the fields of artificial intelligence and distributed computing to create a collective system for solving complex AI tasks. The name "Aigarth" is a fusion of "AI" for artificial intelligence, and "garth," an old term for garden or yard.

  6. Fast-weight Product Key Memory

    [Submitted on 2 Jan 2026 (v1), last revised 22 Feb 2026 (this version, v2)] · arXiv.org

    Sequence modeling layers in modern language models typically face a trade-off between storage capacity and computational efficiency. While softmax attention offers unbounded storage at prohibitive quadratic cost, linear variants are more efficient but suffer from limited, fixed-size storage. We introduce Fast-weight Product Key Memory (FwPKM), a sparse fast-weight memory layer that resolves this tension. FwPKM updates sparsely activated parameters at both training and inference time using chunk-

  7. Agent Trace: Capturing the Context Graph of Code | Cognition

    cognition.ai

    We’re excited to join in Cursor, Cloudflare, Vercel, git-ai, OpenCode and others in support of [Agent Trace](https://agent-trace.dev/). As described in the spec, Agent Trace is an open, vendor-neutral spec for recording AI contributions alongside human authorship in version-controlled codebases.

  8. Incident Analysis for AI Agents

    [Submitted on 19 Aug 2025] · arXiv.org

    As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private information or make unauthorized purchases. Structured information about such incidents (e.g., user prompts) can help us understand their causes and prevent future occurrences. However, existing incident reporting processes are not sufficient for understanding agen