Proposed RuleEducation Department
AI on 5 Nov 2026
Everything new on the trackers that day: official announcements, model uploads from the big labs, tool releases, papers, AI rules and outages. Each item links to its source.
On 5 Nov 2026 the Machine Notes trackers recorded 3 tool releases, 5 papers, 2 AI rules and 1 outage. The most upvoted paper was "Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems". The fastest-rising AI repo was wangzan101/Mika.
Tool releases
Releases that day| Tool | Release | Published |
|---|---|---|
| llama.cppggml-org/llama.cpp | b12122Pre-release | 06:15 UTC |
| OpenAI Python SDKopenai/openai-python | v3.46.0 | 00:55 UTC |
| LangChainlangchain-ai/langchain | langchain-core==1.7.6 | 00:22 UTC |
Papers people are reading
Research that day| Paper | Upvotes |
|---|---|
| Route Anything: A Study of Model and Policy Routing for General-Purpose AI SystemsIn this work, we present Route Anything, a unified framework for studying model and policy routing across general-purpose AI systems.Pengfei Zhou, Yixing Ma, Hexin Wang and others | 86 |
| Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in PsychotherapyWe propose Pandora, a psychotherapy client simulation framework that models how psychological experience becomes situated, individual expression.Mengxi Xiao, Jingjing Chen, Ziyan Kuang and others | 70 |
| Think Less, Locally: Local Preference Learning for Reasoning CompressionWe propose LoCo, a local preference learning method for reasoning compression. LoCo detects candidate overthinking states from the model's own traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations from the same states, and trains on the…Muyao Yuan, Liyan Xu, Weizhan Zhang and others | 65 |
| DreamX: Video Diffusion Model is a Universal Latent Action LearnerWe introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner.Jisoo Kim, Chaehyun Kim, Junsu Kim and others | 51 |
| Factorized MLLM Embeddings for Composed Image RetrievalAlthough recent approaches leveraging Multimodal Large Language Models (MLLMs) have shown significant progress, we argue that the MLLM's compositional understanding remains underutilized.WonJun Moon, Seongchan Kim, Dahun Kim and others | 44 |
AI rules
AI rulesOutages
Outage log| Service | Incident | Impact | Started | Lasted |
|---|---|---|---|---|
| Cursor | Degraded Performance - Grok BotGrok Bot | Minor | 00:34 UTC | 1 h 15 min |
Rising AI repos
Repos that day| Repository | Description | Stars gained |
|---|---|---|
| Mikawangzan101 | An on-device AI agent for Android that operates apps and the web to get things done for you. | +275 |
| sapper-v2N1nEmAn | Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow. | +255 |
| PromptReelsilverdugongenhance | Free desktop app that turns a text prompt into a short video clip on your own PC. Local AI text-to-video with Wan 2.2: type a scene, pick wide, vertical or square, get an MP4. No credits, no subscription, no queue. Windows 10/11. | +106 |
| earshotLeonxlnx | Ears for coding agents: let AI hear, review and make sound. CPU-only, open source. | +63 |
| mcpphone-harness | Connect AI agents to real iPhones and Androids | +54 |