Show HN: Tjaz – create a quiz about anything
Article URL: https://tjaz.com/ Comments URL: https://news.ycombinator.com/item?id=50371403 Points: 1 # Comments: 0
翻译服务暂未运行，当前显示原文。
Hacker News Show HN
FOXAI SEARCH
全站搜索
新闻报道 302
Show HN: ZeBridge – PostgreSQL replicas on devices, synchronized over NATS
Article URL: https://github.com/ndrean/ZeBridge Comments URL: https://news.ycombinator.com/item?id=50376801 Points: 1 # Comments: 0
翻译服务暂未运行，当前显示原文。
Hacker News Show HN
Smart Approvals in Amazon Quick: Human oversight where it matters
Smart Approvals in Amazon Quick reviews eligible agent actions within your existing controls, reducing unnecessary approval prompts while keeping consequential decisions with a person. See how policy sets the boundary, how a classifier reviews actions, and how AWS CloudTrail and Amazon CloudWatch Logs support audit.
翻译服务暂未运行，当前显示原文。
AWS Machine Learning Blog
Use decision models with Amazon Bedrock AgentCore Evaluations
Some agent-evaluation questions are narrow and repeatable, and decision models answer exactly that kind of question. This post shows how to connect two decision models, Jev and Strands Decider, to Amazon Bedrock AgentCore Evaluations through code-based evaluators, and how to validate a decision-model check before you gate a release on it.
翻译服务暂未运行，当前显示原文。
AWS Machine Learning Blog
Workflow SDK adds idempotent starts
The Workflow SDK's start() function now allows initiating a workflow run and claiming a hook atomically, eliminating the race condition present in the previous getHookByToken()-then-start() pattern. This change ensures idempotency using a token derived from domain-specific identifiers like order or invoice IDs. Duplicate starts fail safely with a HookConflictError, which includes the conflicting run's ID. The claimed hook is available immediately, enabling early payload buffering and ordered delivery even before execution begins. Inside workflows, createHook with the same token binds to the existing hook without conflict or additional steps. Experimental settings like minRetention prevent late duplicates by keeping tokens reserved after run completion.
翻译服务暂未运行，当前显示原文。
Vercel
A thousand fewer paths to root
OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.
翻译服务暂未运行，当前显示原文。
OpenAI 官方新闻
b12102
The ggml library now checks view bounds based on the actual bytes reached by strides, improving accuracy for strided views. Views are required to start from contiguous elements along dimension 0, ensuring correct data access. Convolution windows in delta_net are created with all rows at once to prevent stride-related issues.
翻译服务暂未运行，当前显示原文。
llama.cpp releases
CaRe-KT: Continuity-Aware Retrieval-Augmented Reasoning for Knowledge Tracing
arXiv:2611.03744v1 Announce Type: new Abstract: Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning. Retrieval-augmented KT improves these estimates using cross-learner behavioral evidence, but existing approaches typically separate evidence retrieval from downstream prediction. This creates a retrieval-inference alignment gap because evidence relevance varies with the learner's evolving state and prediction context. We propose CaRe-KT, a query-adaptive framework that maintains relevance continuity between evidence acquisition and inference without equating retrieval relevance with predictive utility. CaRe-KT introduces an Evidence-Graph Cache (EGC) that combines persistent question-level relational compatibility with interaction-level temporal validity to construct query-specific evidence subgraphs. Historical learning trajectories retrieved through these subgraphs are encoded alongside the target learner's history in a shared representation space using outcome-supervised contrastive learning. An attention mechanism combines acquisition relevance with learned query-evidence compatibility, allowing relevance to inform, rather than determine, each trajectory's predictive influence. Experiments across five benchmarks show that CaRe-KT outperforms strong KT baselines and remains robust under sparse-history and cold-start conditions. These findings support relevance continuity as a design principle for retrieval-augmented knowledge tracing.
翻译服务暂未运行，当前显示原文。
arXiv cs.LG
Introducing Images 2.6
Images 2.6 brings faster image generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.
翻译服务暂未运行，当前显示原文。
OpenAI 官方新闻
Introducing Vercel Schedules
Vercel Schedules enables applications and agents to create, modify, or cancel one-time and recurring tasks dynamically through code without redeployment. It supports both static schedules defined in configuration files and dynamic schedules managed via SDK, CLI, or API during runtime. The service integrates with Vercel Queues to trigger tasks at specified times, allowing apps to handle work like data cleanup or AI-driven summaries securely and efficiently. Users can test schedules in preview environments before production, and the feature is now available in Public Beta.
翻译服务暂未运行，当前显示原文。
Vercel