oosioo

oosioo

Read in English

Things that started as a one-line request and ended as something usable — including where it went wrong. Read in order →

불꽃축제 관람 가시성을 계산해 색으로 칠한 히트맵. 배경지도를 끄고 계산 결과만 남긴 화면이다. 한강 물줄기를 따라 강변이 노랗게 길게 이어지고, 강에서 멀어질수록 보라색으로 어두워진다. 가운데 주황색 점 다섯 개가 불꽃 발사 지점이고, 왼쪽 아래로 뻗은 하늘색 점선은 상층풍을 타고 연기가 흘러갈 방향이다.
One Click

Seoul Fireworks Festival Best Viewing-Spot Map (2026) — One Line Computed 990,000 Grid Cells of Seoul

I asked an AI, in a single line, where the best spots to watch the Seoul International Fireworks Festival would be. Forty minutes later, out came a heatmap that judged sightlines across 990,000 grid cells of Seoul using terrain and building height data. Here's a breakdown of what actually ran under the hood, where it went wrong, and why a single line of input was enough.

· SYSOP
전국 가을 명소를 시간축에 얹은 지도. 어두운 남한 지도 위에 꽃과 단풍이 핀 자리가 색색으로 번져 있고, 각 자리에 그 식물 모양의 작은 그림이 흩뿌려져 있다. 화면 아래 타임라인 손잡이가 10월 22일에 놓여 있고 「이 시점 절정 명소 25곳」이라고 적혀 있다. 왼쪽에는 코스모스·핑크뮬리·꽃무릇·구절초·국화·메밀·해바라기·천일홍 같은 식물 목록이 각자의 색과 함께 있어 원하는 종만 골라 볼 수 있다. 오른쪽에는 2025년 가을 기상 요약이 있다 — 늦더위가 이어져 단풍이 평년보다 나흘에서 닷새 늦다는 내용이다.
One Click

Autumn Flower-Viewing Spots in Korea: 62 Places and When to Go — A Timeline Map

The question was one line: when and where should you go to see a given flower? Out came a map of 62 spots nationwide, each peak season placed on a timeline. Drag the slider and only the spots in bloom on that date light up.

· SYSOP
아인슈타인과 스티브 잡스의 명조. 네 기둥 여덟 글자와 오행 분포.
One Click

Reading Saju (Four Pillars) with AI — Einstein and Jobs from Eight Blind Characters

A long-fixed system like Saju has plenty of material piled up on the web, which makes it good raw material for AI. It really did come together in half a day. But once it was built, the real problem turned out to lie elsewhere — how do you know if it's right? We had it read blind, with the subject's identity hidden, and checked the results against the historical record.

· SYSOP
10초 클립 682장을 겹친 결과. 사무실을 훑고 지나간 궤적이 청록과 노랑 띠로 층을 이룬다.
One Click

Merging a Video Into a Single Photo — Long-Exposure Compositing of 682 Frames

I wanted to turn a 10-second action-cam clip into a single photo. Just adding frames burns them white; averaging them turns everything gray. It took three wrong turns and 26 minutes. This time, unlike the previous installment, I could actually see where I'd gone wrong.

· SYSOP
서울 도심 11.6 km 범위를 192×192 칸으로 나눠 칠한 종합 적합도 지도. 급경사와 도심 저지대가 붉고, 뒤가 높고 앞이 트인 사면이 초록으로 나온다. 오른쪽은 일곱 인자의 가중치 슬라이더.
One Click

Finding a Feng Shui Site with AI — Seven Conditions Translated into Terrain Numbers

I asked, in one line, to calculate a good site for building a house from terrain, water, buildings, and sunlight. Out came a map that turns old sayings like "mountain behind, water in front" and "wind-gathering, water-holding" into numbers — slope, orientation, even distance to water. I also dig into the spot where flat land scored the same everywhere, and the same problem I ran into in Part 1 showed up again.

· SYSOP
소월로 ILLUSO COFFEE AND MUSIC 앞에 선 남자 흑백 사진
One Click

How to Turn a Single Photo Into a 3D Video — Faking Instagram's 3D with a Depth Map

I took the 3D photo layering I saw on Instagram through my Oculus and faked it on a single flat monitor. An experiment using monocular depth estimation to build a depth map, then shifting pixels with gaze direction to trick the eye into seeing depth — all from one black-and-white street photo, "ILLUSO."

· SYSOP
박공지붕·모임지붕·교차 박공 세 건물. 위는 드론 사진에서 만든 점 뭉치, 아래는 거기서 세운 3D 모델. 점 4,209개짜리 박공지붕이 면 7개·정점 10개가 된다.
One Click

Building a 3D Building Model from a Drone Point Cloud — From Point Cloud to House

From a point cloud built out of aerial photos, I raise a house with ten vertices. This time I gave it one line telling it to simplify further. Vertices dropped 12%, but along the way it chewed through 1.3 m of a perfectly intact wall — twice. Here's what I fixed, and what I switched back off.

· SYSOP
Concept image for AI synthetic consumer panels: a row of person icons in which a few highlighted real people are mixed among outlined synthetic respondents.
One Click

Running Consumer Research with AI Synthetic Panels — The Self-Cannibalization the Survey Industry Fears

I ran a consumer survey with a single line of code. The respondents weren't people — they were 30,000 fake consumers we built ourselves. How to build a synthetic consumer panel with NeoPersona and NVIDIA's Nemotron, and why the traditional survey industry both welcomes and fears this — including the self-cannibalization and the limits.

· SYSOP
쇼핑몰·대시보드·데이터 분석 세 프로젝트에 규칙이 각각 갇혀 맥락이 넘어가지 못하는 그림
One Click

Why AI Forgets Your Previous Conversation — AI That Remembers (1)

AI losing context isn't because you're bad at using it — it's because the way it stores things is built to collapse the moment you juggle multiple unrelated tasks. Here we trace the problem to its root.

· SYSOP
어질러진 책상(전부 로드)과 색인 한 장을 둔 깔끔한 책상(필요할 때 소환)을 비교한 그림
One Click

AI That Remembers (2) — Don't Cram All the Rules Into One File

One method stuffs every rule into a single file; the other breaks them into small pieces and pulls them out only when needed. That difference in storage philosophy decides the outcome across many projects.

· SYSOP
기억의 네 종류를 카드로 나눈 그림. 나는 누구인가, 어떻게 일하라, 참고 자료, 진행 중 작업
One Click

AI That Remembers (3) — One File, One Fact

Storing memories well matters less than storing them so they can be found. How to split them by kind, the one-file-one-fact rule, and the one-line description that decides whether they get recalled.

· SYSOP
아침·점심·오후·저녁으로 이어지는 하루 타임라인 위로 맥락이 계속 따라오는 그림
One Click

AI That Remembers (4) — Handling Dozens of Tasks Like a Single Person

An online store in the morning, a dashboard at lunch, writing in the evening. What a real day looks like when context never breaks, even as you jump between unrelated tasks several times a day.

· SYSOP
비대한 색인, 낡은 기억, 불러오기 실패 세 가지 함정을 경고 카드로 나타낸 그림
One Click

AI That Remembers (5) — Even Memory Turns Toxic If You Never Discard It

Memory that's only accumulated and never managed becomes a liability, not an asset. Three traps — a bloated index, stale information, and failed retrieval — and their fixes.

· SYSOP
Cover of a liquor shelf with bottles tagged by drink type and who they were shared with
One Click

I Put Stories on the Bottles Piling Up at Home — A Drink Log Where One Label Photo Lets AI Fill In the Details

When COVID made it hard to drink out, bottles started piling up at home. I built an app over one weekend where a single label photo gets the drink's description filled in by AI, and all I write is where it's stored and who I drank it with and how it went. Alongside domestic and international precedents like Vivino, CellarTracker, and WineGraph, a look at how low the bar has dropped for building a tiny service meant for just yourself.

· SYSOP
검사 카드가 늘어나는 커버 — 검사 하나를 만들었다가 스무 개가 됐다
One Click

I Built One Psych Test, and It Became Twenty — A Structure Where Adding One Test Means Adding One File

It started as a casual quiz, just for fun. Then I rebuilt it into a framework where dropping in one file for one test automatically wires up scoring, reports, and screens — and it grew to twenty. The real power of a click isn't knocking out one thing fast; it's setting up the board so the twenty-first comes for free. But looking at how this is done elsewhere, I found that making something that looks like a test and making an actual test are entirely different leagues of difficulty.

· SYSOP
1908년 2월 23일 일요일 새벽 3시, 뉴욕 브루클린 다리 근처에서 아침 신문을 팔던 소년들. 맨 앞 소년이 『모닝 텔레그래프』를 안고 있다 (사진 루이스 하인, 퍼블릭 도메인, 미국 의회도서관 소장·위키미디어 공용)
One Click

My Own Magazine, Every Morning — Personalized Briefings That Pick Only What You Need and Fit It on One Page

Newsletters keep piling up and inboxes keep getting messier. This piece traces how personalized briefings that curate only the information you need have evolved at home and abroad — from Newneek, Naver, and SK Telecom's A. (A-dot) to Artifact, ChatGPT Pulse, and NotebookLM — and, alongside the current trends, suggests how to build, in one click with AI, your own morning briefing for work and the commute.

· SYSOP
2025년 6월 3일 제21대 대통령선거 날의 기표소. 가림막에 「기표소 POLLING BOOTH」와 「투표지 촬영금지」 안내가 붙어 있다 (사진 revi, CC BY-SA 2.0 KR, 위키미디어 공용)
One Click

The People Who Got 5,000 AI Voters to Cast Ballots — Synthetic Voters That Run the Election in Advance

More companies and researchers are asking AI-generated virtual voters how they would vote instead of real people. This piece follows Aaru, which came within 371 votes of the actual result in a New York primary but missed the presidential race; GPT models that skewed toward the Greens when questioned in German; and a Korean firm that tried predicting local elections — then shares impressions from running the experiment myself with NeoPersona, and why none of this should be called an opinion poll.

· SYSOP
Two satellite photos of the same spot. In the left image, from September 9, 2023, there is only a faint line through the forest; in the right image, from September 10, 2025, the same spot shows a bright strip of bare earth roughly 20 m wide and about 2.8 km long. 1.4 km north of the demarcation line, opposite Cheorwon. The area south of the demarcation line is greyed out (Contains modified Copernicus Sentinel data 2023, 2025)
One Click

Can Satellites Find Landmines? — On Armed Forces Day, Mapping Border-Area Mines with Free Satellite and Terrain Data

On Armed Forces Day, I tried to use free satellite imagery to map where landmines might be buried or might have washed downstream. The AI's first answer was "not as it stands." I changed course, mapping the southern riverbanks of rivers flowing down from the North and changes in the land north of the demarcation line separately — and end with the fact that the mines themselves never became visible.

· SYSOP
Anatomy of one frame of a narrated explainer video: full-screen B-roll, a source credit in the upper right, a bottom caption matching the narration, and the number "600 million dollars" highlighted in orange
One Click

I Fed It One Article and Got a Narrated Video Back — Handing Script, Voice, and Footage Search to AI for 1 Minute 17 Seconds

Feed it an article, and AI writes the script, reads it aloud with TTS, finds footage and photos, attaches sources, and stitches it all into a narrated video. Here's what happened when I tested it with the AG1 story, how it compares to similar services at home and abroad, and where YouTube draws the line.

· SYSOP
A temporary course in front of Saitama-Shintoshin Station. Riders file under a red sponsor arch while spectators line up behind the barriers. Saitama Criterium 2018 (photo Fukumoto, Wikimedia Commons, CC BY-SA 4.0)
One Click

The Day a Line Hung Over Gwanghwamun — Computing a Course for a Downtown Bike Race

On October 1 I watched a man walk a line 120 m above Gwanghwamun, then came home thinking about events that borrow the city for a day: soapbox races, urban downhill, and the criterium, a bike race that circles a short loop dozens of times. I designed a web app that lays out such a course on a map, keeping as much traffic moving as possible while placing grandstands and ad boards with some logic, and ran a prototype on the real street network around Gwanghwamun.

· SYSOP
A grid of one beach photo rendered six ways: original plus five film looks based on Portra 400, Ektar 100, Velvia 50, CineStill 800T, and Tri-X 400
One Click

A One-Click Film Camera Built by Reading 1,027 Film Photos — Twenty Film Looks, and the Films the Samples Could Never Tell Apart

I gathered public sample photos of films like Portra, Velvia, and Tri-X, measured their differences in color and tone, and built an app that turns one photo into twenty film looks at once. Tone followed the samples. But color casts followed whoever scanned the film, not the film itself, and four slide films couldn't be told apart from samples alone.

· SYSOP
Two jet fans hanging from the ceiling of Misiryeong Tunnel, Korea. The concrete around them is blackened with soot. 2006 (photo Misiryeong, Wikimedia Commons, CC BY-SA 4.0)
One Click

Was the Bus Driver Who Told Us to Close the Windows in Tunnels Right? — Running Tunnel Air Through a Simulator

Tunnels have jet fans hanging from the ceiling and cars rushing through fast, so it seemed like dust would clear out quickly. I tracked down real measurement data and built a simulator that calculates tunnel airflow and dust by varying the number, size, and speed of vehicles along with road-surface dust, to check the old folk wisdom. While I was at it, I also looked into whether AI-built simulators are a threat to simulation software companies.

· SYSOP
A large family dome tent collapsed to one side in a snowy aspen grove. The green and red fly is crumpled and sagging, with two coolers in front (photo brian gautreau, Wikimedia Commons, CC BY-SA 2.0)
One Click

Where Does a Tent Give Way First in a Windy Campsite? — Eight Tents Set Up in a Wind Simulator

I went camping and the wind was far too strong. Using published structures and material figures, I set up eight tents in a simulator: dome, geodesic, tunnel, A-frame, pyramid, family cabin, and two rooftop tents that sit on a car, one fold-out and one wedge. Changing wind direction, pole and fabric material, stake length and ground, guylines and vehicle mass, I worked out what gives way first. In most cases it was the stakes, not the poles, and quartering winds were the weakest direction.

· SYSOP
Rembrandt's Bust of a Young Woman with five face zones (forehead, nose, both cheeks, chin) outlined in white, beside the title: Reading skin from a photo, keeping only ingredients with evidence
One Click

Reading Skin from a Photo, Keeping Only Ingredients with Evidence — An Ingredient Recommender Built to Dodge Where Skin-Analysis Apps Collapsed

Services that use a camera to analyze skin and recommend cosmetics have come and gone for a decade now. We examined where twenty-two prior cases broke down, then built a tool that shows ingredients instead of products — and only ones whose effects are confirmed by randomized controlled trials. It also notes what a photo can never measure, down to numbers that shift with a single light source.

· SYSOP