Source-backed discovery
New Term Radar
Discover names and concepts appearing in public sources, with dated evidence, source coverage and comparable growth.
Saved terms stay in this browser and do not sync to your account. Source collection continues on the server without this page being open.
Collection coverage · Limited historyCurrent / previous observed days 7 / 4
Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.
Current window：2026-10-30 → 2026-11-06 (end excluded) · History 12 days
| Source | Current days | Previous days | Last success |
|---|---|---|---|
| arXiv | 6 | 4 | Nov 6, 2026, 12:30 AM UTC |
| arXiv | 7 | 3 | Nov 6, 2026, 5:15 AM UTC |
| Ask HN | 7 | 4 | Nov 6, 2026, 3:45 PM UTC |
| Ask HN | 7 | 4 | Nov 6, 2026, 3:30 PM UTC |
| Ask HN | 7 | 4 | Nov 6, 2026, 4:00 PM UTC |
| Ask HN | 7 | 4 | Nov 6, 2026, 4:00 PM UTC |
| GitHub | 7 | 4 | Nov 6, 2026, 12:45 PM UTC |
| GitHub Issues | 7 | 4 | Nov 6, 2026, 4:00 PM UTC |
| GitHub Releases | 7 | 2 | Nov 6, 2026, 12:15 PM UTC |
| GitHub | 7 | 4 | Nov 6, 2026, 2:30 PM UTC |
| GitHub Issues | 7 | 4 | Nov 6, 2026, 4:45 PM UTC |
| GitHub Releases | 7 | 4 | Nov 6, 2026, 4:45 PM UTC |
| GitHub | 7 | 4 | Nov 6, 2026, 2:30 PM UTC |
| GitHub Issues | 7 | 4 | Nov 6, 2026, 5:00 PM UTC |
| GitHub Releases | 7 | 4 | Nov 6, 2026, 4:45 PM UTC |
| GitHub Discovery | 1 | 0 | Nov 6, 2026, 4:00 PM UTC |
| GitHub Trending | 7 | 4 | Nov 6, 2026, 1:15 PM UTC |
| 7 | 3 | Nov 6, 2026, 8:30 AM UTC | |
| Hugging Face | 7 | 3 | Nov 6, 2026, 8:30 AM UTC |
| Hugging Face Spaces | 1 | 0 | Nov 6, 2026, 3:30 PM UTC |
| Hacker News | 7 | 4 | Nov 6, 2026, 1:15 PM UTC |
| Hacker News | 7 | 4 | Nov 6, 2026, 4:15 PM UTC |
| Hacker News | 7 | 4 | Nov 6, 2026, 4:15 PM UTC |
| Hacker News | 1 | 0 | Nov 6, 2026, 4:00 PM UTC |
| Show HN | 1 | 0 | Nov 6, 2026, 3:45 PM UTC |
| MIT News | 7 | 3 | Nov 5, 2026, 4:15 PM UTC |
| OpenAI | 7 | 4 | Nov 6, 2026, 11:45 AM UTC |
| Product Hunt | 7 | 4 | Nov 6, 2026, 1:15 PM UTC |
| 量子位 | 6 | 4 | Nov 4, 2026, 10:15 AM UTC |
| OpenRouter | 1 | 0 | Nov 6, 2026, 5:03 PM UTC |
| Hugging Face Models | 1 | 0 | Nov 6, 2026, 5:03 PM UTC |
| HF Daily Papers | 1 | 0 | Nov 6, 2026, 5:03 PM UTC |
| OpenRouter | 1 | 0 | Nov 6, 2026, 5:03 PM UTC |
| SEC EDGAR | 7 | 4 | Nov 6, 2026, 10:45 AM UTC |
| Sequoia Capital | 7 | 3 | Nov 6, 2026, 6:45 AM UTC |
| Simon Willison | 1 | 0 | Nov 6, 2026, 3:15 PM UTC |
| TechCrunch | 7 | 4 | Nov 6, 2026, 3:00 PM UTC |
| Contracts Finder | 7 | 4 | Nov 6, 2026, 8:00 AM UTC |
| V2EX | 7 | 4 | Nov 6, 2026, 3:00 PM UTC |
- Counts describe monitored public sources, not the whole web or search demand.
- Both weeks need adequate, comparable collection coverage.
Seven-day figures use the complete UTC window above. Priority is a research triage score, not search volume, market size or a probability of success.
Snippet
Hi HN, I built an always on always listening AI Agent, here's some backstory: I've always struggled with the attention problem while developing. Even with agents, I can work fast, but I don't know if I can keep working for long, or if I can come back to a problem once I get distracted. So a little while ago I built Snippet for myself. It's an always-on, code
First observed Oct 27, 2026 · Hacker News
- 7d mentions
- 0 previous 2
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
MARCA
arXiv:2610.33279v1 Announce Type: new Abstract: Introduction: Increasing volumes of individual case safety reports (ICSRs) challenge expert-led causality assessment in pharmacovigilance. We developed MARCA (Multi-Agent Retrieval-Augmented Causality Assessment), a four-agent framework for Naranjo-based assessment, and evaluated agreement with human experts an
First observed Oct 27, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
humanlayer/humanlayer
First observed Oct 26, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
时再添加有权使用
前几天介绍过我做的 Dime Dime Baby AI 。这次补了一条英文教程，把网站操作和实际生成样片放在一起，方便先看效果，再决定是否使用。 40 秒教程： https://www.youtube.com/shorts/BeUJo-2Z03I 流程是：选择一张清晰、获得授权的成人照片 → 选择视频规格 → 登录并购买积分 → 生成后到 My Videos 下载。 目前支持 480p ／ 5 秒，以及 720p ／ 5 秒或 10 秒。一次性积分包从 9.90 美元起，没有订阅。 下载的成品是静音 MP4 ，发布时再添加有权使用的声音。教程里的旁白不代表生成视频自带配音，AI 的人物细节和动作也可能有差异。 网站： https://dimedimebaby-ai.org/?utm_source=v2ex&am
First observed Oct 28, 2026 · V2EX
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
iayanpahwa/research-agent-from-scratch
First observed Oct 26, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
mohsa/idhn
First observed Oct 26, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Blazle
First observed Oct 27, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
CER
arXiv:2610.33004v1 Announce Type: new Abstract: Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily reflect whether meaningful information, such as names, dates, and identifiers, is preserved. In this work, we investigate entitylevel analysi
First observed Oct 27, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
RSP
arXiv:2610.33440v1 Announce Type: new Abstract: Selecting a compact training subset is an important step in adapting medical language models from existing question-answering banks. We investigate perturbation-based data selection using two signals derived from Gaussian perturbations of the final-block representation: prediction-change frequency and non-flipp
First observed Oct 27, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
nightly-labs/openbot
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
First observed Oct 26, 2026 · GitHub Trending
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Trigger.dev
Run AI agents with Slack, Supabase and 50+ other services
First observed Oct 28, 2026 · Product Hunt
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
OmniBrain-0
arXiv:2610.36013v1 Announce Type: new Abstract: General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact mo
First observed Oct 28, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Loqui
Turns your voice into ready-to-send text in any Mac app
First observed Oct 26, 2026 · Product Hunt
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
nodecode-ai/nodecode
Hi HN, we're Mike and Thom. Agents of the future should only have one tool (the interpreter, ideally a LISP eval), nothing more or less; to interact with the world. Agents remember by writing markdown files. NODECODE remembers by rewriting itself. And that is in itself a new paradigm in working with agents. What if memories, skills, MCPs, provider connectors
First observed Oct 26, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
ETC-Bench
arXiv:2610.36527v1 Announce Type: new Abstract: Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form when their differences are not determined by speech. To our knowledge, ETC
First observed Oct 28, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
V2X
Ford is rolling out two new chargers capable of powering a home or the grid — so-called V2X capability.
First observed Oct 27, 2026 · TechCrunch
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
-
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Sectr
Hey HN, I've been building Sectr, a backend-as-a-service for making it easy(ier) to develop and deploy AI agents. Deploying agents requires non-trivial systems design work. Consider a support agent: how do you stream messages to your frontend, how/where do you persist messages for frontend fetching later (or for auditing), and when the agent wants to issue a
First observed Oct 27, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
SSC
arXiv:2610.33036v1 Announce Type: new Abstract: Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbre, prosody, and expressivity. Many downstream applications, including conversational AI agents, controllable speech generation, and large-scale audio
First observed Oct 27, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
或维护
这段时间按照 DeepSeek 的 DSec 论文，做了一个 sandbox platform 的开源、自托管实现：OpenDsec。 项目地址： https://github.com/Kernflux/opendsec 先说明一下：这是独立项目，不包含 DeepSeek 代码，也不是 DeepSeek 官方发布或维护的项目。架构和主要设计来自论文；论文没有明确说明、或者我们采用不同方案的地方，都在 SPEC 里单独标注了。 整体架构分为控制面和节点运行时。 控制面里，stateless apiserver 负责认证、配额、调度和请求转发；IAM 用 Raft 保存身份、项目和配额状态；watcher 汇总各节点的健康与负载；每台计算节点运行一个 edge，负责最终准入和 sandbox 生命周期。组件之间走
First observed Oct 28, 2026 · V2EX
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
alchaincyf/huashu-design
Huashu Design 3.0 · 在 agent 里打一句话，拿回能交付的设计：网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent
First observed Oct 26, 2026 · GitHub Trending
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
FinLLM-KG
arXiv:2610.36083v1 Announce Type: new Abstract: Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to predicting the sentiment of each article in isolation and operate as black boxes, which limits contextual underst
First observed Oct 28, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
mainplane-ai/mainplane
Hi HN, I'm Alexander. Yes, this is another agent harness. Here is why I built one anyway. I was engineer #2 at Browser Use, where I built our agent harness and the evals behind it, including BU Bench, which became a default benchmark for browser agents. I left in September to build Mainplane. The problem: local agents die with your laptop, and cloud agents c
First observed Oct 26, 2026 · Hacker News
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Beyond IceBERT
arXiv:2610.36230v1 Announce Type: new Abstract: IceBERT, the reference encoder for Icelandic, found that a cleaned web crawl is enough to train a strong model and that starting from a multilingual model can help on some tasks. We revisit both findings with the ModernBERT architecture. We train Icelandic encoders from 12M to 1B parameters on 9B tokens of open
First observed Oct 28, 2026 · arXiv
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100
Outstanding Tiny Desk
Hi everyone! I’m working on a small website called Outstanding Tiny Desk AI. The idea is simple: upload a photo and turn the person in it into a performer in a short, Tiny Desk-style AI video. Think of it as making a little “that’s me on stage” clip, something playful to try for yourself or share with friends. I wanted to make this kind of video easier to cr
First observed Oct 27, 2026 · V2EX
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 13 / 100