Pinned Tweet
What a week! A 5 day Design Sprint at Oxford University's Future of Humanity Institute, with AI Safety researchers from @FHIOxford and @CSERCambridge, designing a strategic role-playing game for decision makers about the effects of AI. With @anderssandberg @rossgritz
Your coding agent isn't running out of intelligence. It's running out of room.
One Playwright snapshot = 56 KB of context. 30 minutes in, 40% of the window is gone. Then /compact wipes what the agent was doing.
Context Mode fixes that:
â 315 KB of tool output becomes 5.4 KB (98% less)â Sessions go from ~30 min to ~3 hoursâ Agent writes a script & reads only the answer: 47 file reads (700 KB) become 3.6 KBâ Edits, tasks & decisions survive /compact via local SQLite + BM25â 17 platforms: Claude Code, Cursor, Codex, Copilot, Gemini CLI
31K+ stars. Free & source-available.
Think in code NOT in context.
On GitHub: mksglu/context-mode
First answer in a customer interview is pablum (Bob Moesta's word). Shallow, not wrong.
Keep asking why. Once the real friction surfaces, people enjoy talking about it.
Most interviews stop one question too early.
Your coding agent ships a feature in 20 minutes. Then you spend an hour clicking through it.
e2e is an open source testing framework built for that gap:
â Write the goal in plain English: agent.act('upgrade the workspace to Pro')â Assert in plain English, or with normal locators, in the same testâ Verified agent steps get recorded and replayed with zero model calls until the UI changesâ Web (Chromium, Firefox, WebKit) + iOS & Androidâ Bring your own subscription, API key, or local modelâ Docs ship in node_modules so your coding agent can read them
Apache 2.0. 9K+ stars.
Goals NOT selectors.
npx e2e initOn GitHub: tester-army/e2e
We stayed up till 3am wiring real data into a prototype.
Real data = every edge case. We spent the night making it work instead of thinking about what we were testing.
If you're testing an idea, don't make it real.
Find the human moment in every workflow and make it thin.
Agent fills the queue. Human approves, revises, or rejects. Agent executes. Humans own judgment and taste, the agent owns everything around it.
Recording + playbook on the Evermuse blog.
Ian Pilon used to hand field research to engineers and wait.
Now he leaves the customer's site, prototypes that night, and goes back the next morning.
The rate of learning is daily. That's the real shift.
Really trying to wrap my head around why X Money is a good idea for me and not just X. Grok couldnât help.
xitter.cf/i/grok/share/894f9e22dâŚ
Something I took from studying Buddhism: thought and feeling depend on each other.
AI mimics the steps of thinking remarkably well. Ask it for the post about what you believe that others don't, and it can't write it. It doesn't believe it.
That gap is where judgment lives.
Every AI product I look at has a memory story. Most are too generic to matter for product.
Remembering yesterday's chat is table stakes.
What product teams need: patterns in customer behavior, usage tied to revenue, and whether the loudest voice is one person or a real trend.
You can spot AI-built UI from across the room.
Inter everywhere. Purple-to-blue gradients. Cards nested in cards. A rounded icon tile above every heading.
Every model trained on the same SaaS templates.
Impeccable gives your coding agent taste:
â 24 design commands (polish, audit, critique, distill, harden...)
â 61 slop detectors that run with no LLM, no API key
â A hook that checks every UI edit while the agent works
â PRODUCT.md first, so design starts from audience & purpose
Claude Code, Cursor, Codex, Copilot + 13 more. Free & open source. 76.8K stars.
Taste NOT templates.
On GitHub: pbakaus/impeccable
Ian Pilon told my favorite Crowdcast story:
Every stakeholder wanted their product above the fold.
Then the team saw the brokers' brochure drawers. Top ten: worn. Bottom ones: dusty.
The users had already done the information architecture.
Nobody argues with dust.
The pull toward autocratic leaders is really a pull toward 'let's start over.'
But there's no undemocratic country better to live in than a democracy.
Keep the democracy. Restart everything AI touches instead. That's where big change belongs.
The biggest win for AI would be if it took enough menial tasks away from us, leaving us time to care for each other and ourselves like we should.
Want.
For years, maybe a decade, I've wanted to build a writing tool that just did a few things I couldn't find anywhere else.
A system that mimicked how I think when I write. A system that provided clear affordances, features, and places to do the things I wanted to do. A way to play with my writing as I'm writing it. A way to settle into just the right way to say something.
It never made sense to make it a 37signals product because it's not commercially viable, nor would it be worth pulling people off their other work to hack on this. Plus, it would have taken months the old way.
So this weekend I just made it myself, with Claude's help.
It's called Write_On and the short video walks you through it.
Essentially it's "alternative control" at the word, sentence, and paragraph level, plus a way to dim stuff back, and stash stuff near by. Not version control, but alternative control. You'll see what I mean when you watch the video below.
So here it is. Write_On.
Discovery hack from Ian Pilon: ask customers for 20 minutes. Block 50.
When it's flowing: "this flew by, got 5 more minutes?" Most say yes.
You've shown you respect their time. That's what earns the second call.
The fantasy of collapse is really a wish to restart.
AI is the first real chance to restart how we live without breaking everything first.
Not automatic. Forces will try to point it at the same old targets. We get to decide.
If you designed furniture and refused to learn about wood, we'd call you a bad furniture designer.
Product people used to get a pass on not knowing code. That pass is gone.
The barrier was never a good thing. Walk toward the code.
The MCP marketplace is not the next App Store.
Apps had no other home in 2008. MCPs already do. If your agent can't talk to Salesforce, I don't pick a different tool. I pick a different agent.
The right analogy is the internet, not the App Store.








