Let your AI agents paint big arrows, boxes and text on your screen
Comments
TUMN 인사이트 · AI와 IT를 이해하는 실용 정보
AI와 IT의 변화를 이해하고, 실제 서비스에 적용하는 데 필요한 정보를 모읍니다.
I think I found a planet nobody knew existed. I used Claude Code to find it
Comments
Production-grade LLMs and agents: a field guide
A maturity model for taking agents from an impressive demo to a system people can depend on — with a self-assessment and the map to a deep-dive on each layer.
Microsoft 365 Family subscribers will finally be able to share AI benefits
Microsoft bundled its AI-powered Office features into Microsoft 365 Personal and Family subscriptions last year, but it only allowed the primary account holder to access the AI benefits. Now, Microsoft is about to let Microsoft 365 Family and Premium subscribers share Copilot and
ttok 1.0
<p><strong>Release:</strong> <a href="https://github.com/simonw/ttok/releases/tag/1.0">ttok 1.0</a></p> <p>I released <a href="https://simonwillison.net/2026/Oct/8/ttok/">ttok 0.4</a>, ran <code>uv tool upgrade ttok</code>, piped a file into the new version... and realized that i
Part 6: An operating system for coding agents: the disciplined build
Coding agents are great for an afternoon and mediocre for a quarter. Here’s the small set of files and rules — with the actual configs — that keeps quality from decaying across months and thousands of edits, whether you run one agent or a fleet of them on the same repo.
The model that didn't exist, so you made it yourself
The model that didn't exist, so you made it yourself
Part 4: Safety and governance for LLM systems: guardrails, PII, audit, and memory
Part 4: Safety and governance for LLM systems: guardrails, PII, audit, and memory
Scale Bitwise-Deterministic Pretraining with NVIDIA Megatron Core
Bitwise determinism makes large-scale pretraining easier to debug, validate, and resume reproducibly. These benefits become especially valuable when training...
LegalOn halves Codex costs while maintaining development speed
LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.
Show HN: Rgpu – a PyTorch device whose tensors live on a remote GPU
Comments
Opus 5.5에 프롬프트 하나와 6시간을 주고 『보이지 않는 도시들』을 시각화하게 해봤다
Claude Opus 5.5 와 GPT-6 Astra 에 같은 프롬프트를 주고, Italo Calvino의 『보이지 않는 도시들』에 등장하는 모든 도시를 추가 질문 없이 인터랙티브 시각화하도록 실험함 과제는 three.js와 pnpm 을 사용하고, 걸작이 될 때까지 주어진
인터넷을 떠받치는 사람들
휴대전화·브라우저·서버가 의존하는 오픈소스 프로젝트 23개 중 11개는 최근 1년간 정기적으로 코드를 변경한 사람이 한두 명뿐 이었음 40억 대 휴대전화의 시간대를 관리하는 Paul Eggert , core-js의 Denis Pushkarev, sudo의 Todd Miller처럼 일상의 디지털 기능이...
Fired OpenAI safety researchers dispute misconduct claims, warn of chilling effect
Three fired OpenAI safety researchers dispute allegations of mishandling sensitive information, warning in an open letter that their dismissals are creating a chilling effect on the company’s AI safety culture.
ICE detainees in Georgia used the facility’s video calling software to expose the conditions inside
Four men detained at an ICE detention center in rural Georgia used the facility's video conferencing software to expose both the conditions inside and President Donald Trump's hostile takeover of the immigration courts. In the five-minute video, the men describe an intentionally
Show GN: Porch - 클로드코드·코덱스로 한 일을 프로젝트별로 정리하는 맥 메뉴바 앱
클로드코드와 코덱스로 한 일을 프로젝트별로 하루·한 주·한 달 단위로 정리해 주는 맥 메뉴바 앱을 직접 만들었습니다. 오픈소스 이고 가입 없이 쓸 수 있습니다. 여러 터미널에서 세션을 돌리다 보니 하루동안 어떤 작업에 시간을 썼는지, 스스로 에이전트 활용이나 세션들을 어떻게 얼마나
Show HN: Pocketty – iPhone SSH terminal that pings you when an agent is blocked
Comments
Show HN: Jevman – AI decision models play Pac-Man
Comments
Show GN: 반도체부터 전세·보험까지, 시뮬레이터를 만지며 배우는 무료 웹 교과서 시리즈
2022년 Bartosz Ciechanowski의 Mechanical Watch 를 보고 신선한 충격을 받았습니다. 그 뒤로 제가 관심 있는 분야도 저렇게 직접 만져 보며 이해하는 웹 페이지로 만들고 싶다는 생각이 늘 있었는데, AI가 발전한 덕분에 이제는 혼자서도 만들 수 있게 되었습...
AMD will bring FSR 4 to handhelds by the end of 2026
It's already possible to get AMD's framerate-enhancing FSR 4 boost on handhelds as old as the Steam Deck - but in June, AMD reserved the right to disappoint handheld gamers by not officially bringing FSR 4 to older handhelds. Now, AMD consumer chip boss Jack Huynh says he will br
California is trying to shut down robot vs. human cage matches
The California State Athletic Commission sent a cease-and-desist letter to a startup that hosted a match between a human and a robot last month, as reported by The New York Times. The fight, which took place on September 18th, pitted a human, Frankie LaPenna, against a humanoid r
RIP Margaret Hamilton, whose code saved the Apollo 11 Moon landing
Hamilton also coined the term "software engineering" and founded two successful software companies.
SynthID Detector - AI 생성 미디어 워터마크 탐지 도구
Google의 SynthID Detector 는 이미지, 영상, 오디오를 업로드해 AI 생성 또는 편집 과정에서 삽입된 SynthID 워터마크를 확인하는 도구임 이미지에서는 워터마크 존재 여부를, 영상과 오디오에서는 워터마크가 있는 구간 을 탐지함 Google DeepMind가 개발...
Trump Mobile hack and apparent lack of FCC authorization raise security alarms
After hack and data breach, senator asks why Trump Mobile lacks some FCC filings.
AI-ready biological data: $1.8B global commitment
Comments
5 Steps to Create SimReady Assets for Robotics with Frontier AI Models
Preparing CAD assets for robotics simulation requires more than converting geometry to OpenUSD: developers must configure and validate materials, collision...
Part 5: Operating an LLM system: observability, cost, routing, and the platform underneath
Your service can be 100% up and still quietly approving the wrong things, burning its budget, or failing over into untested quality. Level 5 is the infrastructure that lets you see your decisions, bound your spend, route and fail over between models, kill bad behavior in seconds
내 웹사이트가 Google 검색 색인에서 삭제됐다
AI와 끊임없는 스크래핑을 이유로 개인 블로그의 검색 엔진 색인 제외 를 추진했고, 마지막 설정 변경 후 최소 3개월이 지나 확인했을 때 Google 색인에서 삭제된 상태였음 처음에는 robots.txt 에서 모든 봇의 접근을 차단했지만, 몇 주 동안 기다리며 확인해도 색인...
Show HN: Edi Life OS – self-hosted life dashboard with an MCP server for AI
Comments
Anthropic launches free AI security scans for open-source projects
Anthropic's offering to help open-source projects track down security vulnerabilities with a new service called OSS Scanner. It says open-source projects that opt-in will get "thorough, periodic security scans by our strongest models at no cost." That could mean open-source proje