뉴스 및 전체 검색
뉴스, 도구, 모델, 가이드, 주제, 워크플로, 프롬프트를 함께 검색합니다.
뉴스 기사 142
“AI Code Guide”
Ling 3.1 Flash 1019 now available on AI Gateway for free
The Ling 3.1 Flash 1019 model from InclusionAI is now available on Vercel's AI Gateway at no cost until November 3, 2026. Designed for coding, multi-step reasoning, and tool-using agents, it features a 1M-token context window. It can be used via the model name 'inclusionai/ling-3.1-flash-1019' in applications like Claude Code, Codex, and Cursor after setting up the Vercel CLI. Free usage appears in the spend dashboard with full request tracing. After the free period, charges will apply at the published rate. AI Gateway offers unified API access, usage tracking, cost management, routing rules, and Zero Data Retention support, reflecting provider pricing without markup or platform fees.
Simplifying runtime caching on Vercel
Vercel is merging its Data Cache service into Runtime Cache, unifying data caching across frameworks like Next.js, SvelteKit, and Nuxt. Developers using fetch caching or unstable_cache in Next.js won’t need to change their code. Pro and Enterprise projects receive increased storage allocations, with Pro getting 8x more space and Enterprise 10x. Runtime Cache now handles regional storage, authentication, and tag-based invalidation across Vercel’s global infrastructure. Improvements include faster reads during traffic bursts via circuit breakers, higher storage budgets reducing evictions, and enhanced observability with deployment markers, revalidation causes, and write utilization metrics. The migration simplifies billing and usage tools, with existing teams receiving advance notice and pricing details.
How to build evidence-grounded agent memory with OpenWiki and Graphs
LangChain used OpenWiki, its open-source wiki compiler, and an evidence graph to build a persistent memory layer that preserves knowledge for agents to reuse across tasks. Learn how.
b11946
server : add realtime conversation and transcription on /v1/realtime (#31269) * server : add realtime conversation and transcription on /v1/realtime Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * examples : default the realtime client to the server port 9931 Assisted-by: Claude Opus 5.5 * server : sample realtime responses right after their own decode Slots respond in turns on one context: sampling at the start of the next step read the logits of whichever slot decoded last, so concurrent sessions mixed their outputs. Assisted-by: Claude Opus 5.5 * move more stuff to server-realtime, making it self-contained * examples : fix the type check of the realtime client Assisted-by: Claude Opus 5.5 * examples : use the model card prompts in the realtime client Assisted-by: Claude O
해석하기 전에 감지하기: LLM에서의 페르투베이션 기반 입력 모호성 감지
arXiv:2610.36353v1 발표 유형: 신규 초록: 대규모 언어 모델(LLM)은 종종 모호한 입력에 대해 하나의 의도된 의미만 있는 것처럼 답변합니다. 이는 문제가 되는데, 입력의 모호성은 불확실성의 상류 원천이기 때문입니다. 즉, 프롬프트가 여러 가지 타당한 해석을 허용할 때, 핵심 질문은 모델이 과연 직접 답변을 해야 하는지 여부입니다. 기존의 입력 불확실성 처리 방법들은 종종 LLM이 생성한 문장이나 명확화에 의존하지만, 이러한 변환 과정 자체가 모호성을 측정하기 전에 이미 입력을 해석해 버릴 수 있습니다. 우리는 입력 모호성 감지를 위한 라벨 보존형 페르투베이션 프레임워크를 제안하며, 이 프레임워크에서는 페르투베이션이 원래 입력에 가까운 상태로 유지되면서 동시에 해당 입력의 라벨을 보존합니다. 우리는 이 원칙을 두 가지 감지기로 구현했습니다: 블랙박스 기반 규칙 기반 페르투베이션 라이브러리와
b11951
chat : stop qwen3-coder reasoning and content before template separators (#30557) * chat : strip trailing whitespace from parsed reasoning and content Assisted-by: Claude Fable 5.1 * chat : stop qwen3-coder reasoning and content before template separators Assisted-by: Claude * tests : remove the Qwen parser case from the chat session tests Assisted-by: Claude * common : handle partial prefix until match at end of generation --------- Co-authored-by: Zeshawn Zahid Co-authored-by: Alde Rojas **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11951/llama-b11951-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel
How LangChain grew self-serve analytics questions 40x by giving its AI agent layered context
LangChain gave its Hex agent layered context, turning self-serve analytics questions from occasional to routine.
b11953
cuda : add top-k MoE fusion for 384 experts (#31288) Assisted-by: Codex **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11953/llama-b11953-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11953/llama-b11953-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11953/llama-b11953-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11953/llama-b11953-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/dow
b11938
model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252) * model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B Co-authored-by: Sigbjørn Skjæret Co-authored-by: Xuan-Son Nguyen Assisted-by: Claude Opus 5.5 * tests : set the SWA rope base of the LFM3 test model Assisted-by: Claude Opus 5.5 * llama : enable recurrent state rollback for LFM3 Assisted-by: Claude Opus 5.5 * Apply batched suggestions from code review Co-authored-by: Sigbjørn Skjæret Co-authored-by: Tarek Dakhran * gguf-py : align the lfm3vl mapping comments Assisted-by: Claude Opus 5.5 * llama : fix CRLF line endings from the review suggestions Assisted-by: Claude Opus 5.5 * tests : add the LFM3 Metal fusion baseline Assisted-by: Claude Opus 5.5 * llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing As
GitHub intelligence puts your code, context, and history to work
Agents should understand more than your codebase—they should understand how your team works. Your preferences, repository conventions, skills, and custom instructions guide how changes should be made, while code in… The post GitHub intelligence puts your code, context, and history to work appeared first on The GitHub Blog.