Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
A Tie Is a Loss Asking a model to try again is not a competition.
-
Survived Is Not Endorsed Twice this year I pointed a swarm of agents at a pile of free government data and asked it to find something worth building.
-
Read the JavaScript Bundle In September I pointed a swarm of research agents at the free data the US government publishes about healthcare and asked one question: what is sitting there that almost nobody uses?
-
Everything Looks Like Everything The demo everybody builds is retrieval over a diverse corpus.
-
The Probe Was the Bug I am building a navigation app that knows every road you have driven and routes you down the ones you have not.
-
Verify the Artifact, Not the Process I open-sourced a tool this summer that reads your entire Claude Code history off disk and turns it into a dashboard.
-
Read It Cold Before I open-sourced a diagnostic tool in August, I had five readers take the tree a slice at a time and check claims, not wording.
-
I Removed Authentication and Shipped It as a Feature The commit is a breaking-change feature commit.
-
Five Hours Unattended On a Friday evening in late August I gave an agent a five-hour budget, a repo, and a sentence: focus on code quality, UI, UX, and helping people understand their usage.
-
Prove the Advisory Is Unreachable Two HIGH advisories on a direct production dependency.
-
One Password for the Whole Family Supply-chain bugs are supposed to happen to other people.
-
Everything That Concluded Was Deleted In late August I spent four days investigating a database estate I am not going to describe.
-
One Line Held the Lock A Go server I built this summer stopped scaling at two cores.
-
The Simulated User Is the Confound I built a diagnostic tool for heavy equipment.
-
The Shape Leaks In April I wrote a working paper with a thesis I still think is beautiful, and in August I ran the experiment that killed it.
-
The Decision Log Ate the Project Every guide to working with a coding agent says the same thing about memory.
-
Twelve Days of Green Tests In August I rebuilt a proprietary database wire protocol I am not allowed to name, for a platform I cannot license, using nothing but the real client drivers that already speak it.
-
Spider-Man Is Not a Person This summer I put a redaction gateway in front of a small app my family uses.
-
What the Meter Did Not Count For two weeks in August I ran two agentic coding tools side by side.
-
Words That Mattered In June I wrote that the session log is the first place my judgment ever got recorded.
-
A Backup of a Lie Every SQLite database I run is in write-ahead-log mode.
-
Showing Includes Saying This summer I built a small communication tool for a child in my family who does not talk the way the world expects.
-
The Winner Was Array Order I ran a seven-model bake-off for the language pipeline in a small app I built.
-
Three Bugs in the Instrument There is a retrieval system I built this summer over a thousand near-identical insurance contracts, and an evaluation harness to go with it.
-
The Rules Are Downstream of the Work The original was written on day 40.
-
Your Rate Limiter Is Counting the Wrong IP I have now found the same bug in two of my own services, on two platforms, in two frameworks, and both times the limiter looked correct in the code and did nothing in production.
-
The Presses Never Stopped I asked the agent to audit every file it had ever printed on my machine that was not source code.
-
It Counts.
-
My Portfolio Read Like a Compliance Audit In July I had agents write the showcase cards for my own projects.
-
An Agent With Eight Minutes On one afternoon in July I had an agent firing every ten minutes on a schedule, from half past one until a quarter to six.
-
Three in Five Opus Runs Did Not Need Opus I run almost everything on the biggest model.
-
The Work Looks Like Nothing The top of the IC ladder is well traveled and still unmapped.
-
The Tree I Never Planned to Move I once asked a chat assistant whether a sentimental tree in my yard could be transplanted.
-
Git Could Not Tell Me Who Wrote It Over one weekend in May I shipped a macOS window manager.
-
The Principal IC Moat The Goal This started as a simple job search.
-
The Corpus Contains Itself In one day in May, from a little after midnight to a little after ten in the morning, an agent built a multi-tenant data-request platform from a spec it had not written and I had not written either.
-
Comprehension Confidence Is Useless I built an app whose whole job is to interview a person about what they want built until it has a specification an agent could execute.
-
The Judge Never Overrides the Regex In May I built a tool that scores Claude Code sessions.
-
A Book Every Four Days At some point this spring I got asked, more or less, whether my vocabulary was mine.
-
A Receipt Nobody Issues Yet Almost every conversation about deploying AI inside a regulated company ends at the same wall, and it is not a capability wall.
-
An Autonomous Prompt Is a Permissions Document In April I wrote a long prompt for an agent whose job was to make my ugly web apps less ugly.