2026-11-15 AI 日报
统计日时区:America/Los_Angeles · 尚未结算
NVIDIA/SkillEvaluator · Tencent/LoopForge · elementalsouls/Claude-BugHunter
开源项目
- NVIDIA/SkillEvaluator
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent…
- Tencent/LoopForge
Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows…
- elementalsouls/Claude-BugHunter
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core…
- google-labs-code/stitch-skills
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents…
- ag-ui-protocol/ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
- tradermonty/claude-trading-skills
Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.
- dream-num/univer
Build your own AI office with Univer Office SDK. Bring editing, calculation, collaboration, and file processing into your product for people and AI agents.…
- alibaba/open-code-review
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level…
- ChromeDevTools/chrome-devtools-mcp
Chrome DevTools for coding agents
- huytieu/COG-second-brain
Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades…
论文
本统计日暂无条目。
行业新闻
- Understanding Positional Embeddings in Modern LLMs
- Show HN: db-branch – database branches in seconds for AI agents and CI, via ZFS
- A Human Reads the Anthropic IPO Filing
- Show HN: Nano-Edge-TTS – 70x realtime, Lightweight Kokoro-based TTS model
A 1.75M-parameter decoder for Kokoro-82M that runs no neural network at audio rate. Kokoro's text side (pronunciation, timing, pitch and all voices) is…
社区动态
- AGI requires understanding.
AGI requires understanding. Cadence brains learn sounds as symbols for memorized concepts and objects in space. Equilibrium propagation gives binding for…
- [Meta FAIR + NYU] Unbundling Multimodal Vision Encoding: training 200+ MLLMs to find encoder pretraining is optional but vision-only parameters are not [R]
X threads (with videos!): https://x.com/choang333/status/2121335484236386574 https://x.com/_ellisbrown/status/2121335477244428419 Paper:…
- I don't think double-blind review systems work [D]
Reviewers can see the authors’ names and affiliations in many cases, making this system closer to single-blind review than double-blind review. I have…
- Basalt 0.4.0: More models, still as fast - Qwen 27B up to 770 tok/s on a 5090
Hi everyone! I wanted to post a quick update on Basalt . Since last I posted, multi model and router support was implemented, starting with DeepSeek V4.1…
- From Activity to Intent: Generating User Journeys with LLMs
Pinterest has moved its user-journey inference system from a multi-stage clustering pipeline to a fine-tuned 4-billion-parameter language model, reporting a…
- EUROPA, the EU's open AI model, is aiming for nearly 1 trillion parameters
One can hope
- Latest version of strata made my Qwen3.8-Flash-Next dumb and useless
I updated the strata to the latest version from v0.1.42.0, so I can try the latest unsloths models and see how they fare against the iq3_s variant I have been…
- Should unused Codex usage roll over to the next week?
I’m a Pro subscriber, but my coding workload varies. Some weeks I leave usage unused; other weeks I need more. Why not allow unused usage to roll over, with a…
- Probable GLM model
https://preview.redd.it/k7ife2j2ms1i1.png?width=591&format=png&auto=webp&s=e8dd29b327ac46e7634a5faf48454ec1beb7aa0b Because of Theo gg tweet of all people, I…
- DeepSeek is AMAZING.
Seriously. Over the last month I've been using Claude Code's $20 plan to reverse engineer a closed source .so binary that's part of a larger open source…
官方发布
- Gemini 4 Carbon is now available
Today, we’re making Gemini 4 Carbon available to developers, enterprises, scientists, and consumers.
- Our new blog for science
The OpenAI science blog shares new findings, practical methods, and firsthand accounts from researchers using AI to advance scientific discovery.
- A step toward defining the Standard Model on a lattice
Explore a candidate nonperturbative lattice definition of the Standard Model and how GPT-6 Astra helped turn the idea into a detailed proof.
- Introducing Businesses in ChatGPT
Manage your business information, get insights about how your business shows up, and turn interest into action in ChatGPT.
- We’ve launched fast mode for Claude Fable 5.2 in Messages API requests on the Claude API.
We’ve launched fast mode for Claude Fable 5.2 in Messages API requests on the Claude API. Fast mode delivers up to 2.5x higher output tokens per second, at…
- Gemini Decisions API: Fast, calibrated multimodal decisions
Meet the Gemini Decisions API, powered by our state-of-the-art model Gemini Decision for fast, calibrated multimodal decisions.
- Anthropic launches roadshow for proposed initial public offering
- Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.
- The full DeepSeek App experience, now via API
- Releasing the full suite of application APIs
In the DeepSeek App (including the web version), web search, file input, URL reading, voice interaction and safety work together with model inference to form…