Trellis just crossed 10,000 stars on GitHub. We never optimized for stars. We optimized for one thing: your coding agent shouldn't start from scratch every session. That number is really thousands of devs who got tired of re-explaining their codebase to an AI — and decided specs, tasks and memory belong in the repo. In January this was an empty repo. Thank you all very much! What's next: docs.trytrellis.app/advanced… Check out Trellis here: github.com/mindfold-ai/Trell…

Why does everyone have to invent new phrases for old concepts?

AI never tells you your request was too vague. it just guesses, confidently, and hands the mess back to you.

Honest question for anyone running coding agents daily: When you've got 3 agents going at once, how do you actually keep track of what each one is doing? Terminal tabs? A Notion doc? Pure vibes and hope? I keep hitting this wall and I refuse to believe everyone's just... fine with it.

It's the same gap as a fluent speaker who can't explain the grammar rule they follow perfectly. I tried explaining to my parents once, oh boy it did not work out well

I just realized I've called the same thing — software — three different names. And each name quietly marked a shift in who I was. When I started out, I called it "the system." I cared about being a good cog: clean code, better performance, solid architecture. Make it run stable, make it run fast. Then I started calling it "the project." Now the question was: how do I take this from zero to done — and actually ship it? These days, I keep calling it "the product." And the questions changed completely: Where are the users? What do they actually need? How do I get more people to even know it exists? Same code. Same screen. Three different jobs. You don't change titles by getting promoted. You change them by changing the question you wake up asking.

Hot take: AI made shipping easier. it didn’t make distribution optional.

underrated because it takes guts to admit your first idea wasn't it

Everyone dunks on GPT wrappers. But the wrapper isn't the problem, having nothing that compounds underneath is.

So each decision becomes a thing that can be pointed back to? From my experience, big builds go off track not because the planning is too long. They go off track because many decisions are quietly made during the build, and are never written down. So session 3 quietly does not match session 1. A decision map has a payback only when the decision is still alive after the session boundary.

Everyone's a founder now. Most will quit in 6 months — and it won't be the product's fault. AI removed the friction that used to filter people out early. So the real filter just moved downstream, to the part it can't fake for you: still showing up when the launch dopamine wears off. Building was always the easy 10%. Anyone disagree?

The math does not require cheating, but it also does not reward honesty. 15% per month compounds whatever thing you point it toward. A product that people love, and a product that people cannot put down, draw the same curve. So "clean" is not the default that the math hands to you. It is a choice you make early, about what you are optimizing, and then exponential growth makes this choice very big. PG is right that you can get there clean. The problem is that the engine will not keep you clean for you.

We work hard everyday on making Trellis even better github.com/mindfold-ai/Trell…

Ralph loop — a dead-simple way to let an AI coding agent run itself until the whole spec is done. It's the technique behind all the "loop engineering" noise right now. Ralph was coined by Geoffrey Huntley. Google's Addy Osmani gave the wave its name — loop engineering. Even Boris Cherny, who runs Claude Code at Anthropic, says he "doesn't prompt Claude anymore." One open-source take already has 20k+ stars. Here's the problem it solves: Coding with an AI today means babysitting it. It writes a chunk, stops, waits for you to read it and feed the next instruction. Two options, both bad — hover over it line by line, or walk away and come back to find it stalled halfway. Hands-off and trustworthy were a pick-one. Ralph kills that tradeoff. The core is almost insultingly simple — one line: while :; do cat PROMPT.md | claude-code ; done Write the spec to a file. Let the agent read it and work, over and over. Every pass starts on a fresh context; progress lives in files and git, not in the model's memory. Tests and lint are the brakes — get something wrong, the next loop fixes it. Huntley's rule: "sit on the loop, not in it." So a pile of things that used to need you now happen on their own: Drop in a PRD checklist, wake up to every box ticked The agent notices it's not done and keeps going — no nudging A bad pass doesn't need your rollback; failing tests just trigger a redo Your job shifts from writing prompts to designing the loop and watching it run Letting AI work unattended no longer means choosing between hands-off and reliable. Start here 👉 github.com/snwfdhmp/awesome-… Want to just run it 👉 github.com/snarktank/ralph #AIAgents #VibeCoding #ClaudeCode #OpenSource

A not-even-frontier model running on someone's own machine is doing work that used to bill by the hour. The trick isn't a stronger model. It's that someone mapped exactly where it's weak and built a system around those weak spots — a fallback for when it errs, an external memory for what it can't hold. The model is just the engine. The value is the car built around its blind spots. Staring at parameter counts misses the part that actually matters.

Everyone's first instinct for making an AI smarter is "retrain it." There's a cheaper move. Let it finish a task, reflect on what worked and what didn't, and write the lesson into a playbook. Next run, it reads the playbook first. No retraining. Just a notebook that keeps getting thicker — and an open small model starts closing the gap with the expensive closed ones. Turns out the thing agents lack usually isn't brains. It's a record of their own mistakes. Are you letting your agents keep one?

LMAOOO

Anthropic is now the new CLOSED AI

🛠️ Notion shipped an official hosted MCP server. It lets Claude, Cursor, or ChatGPT read and write your entire Notion workspace — no code, no copy-paste. For a while, getting AI into your Notion meant one of two things: → wire up the API yourself: create an integration, copy the secret token, paste it into a config file. Powerful, but a pain to set up and easy to break. → or just copy-paste pages into the chat. Simple, but the content is frozen — edit the page in Notion and your AI is already out of date. Connected vs. effortless. You had to pick one. Notion's official MCP kills that tradeoff. One OAuth click inside your AI tool and the whole workspace is wired in. The AI reads and writes live, exactly like you can — no token to copy, nothing to paste. So a bunch of things that used to be a chore are now just default: - Claude searches your entire workspace for you — you copy nothing - finish a research pass, tell it to write the results back as a clean new page - update project status and tasks right in the chat, never switching back to Notion - Cursor, ChatGPT, VS Code — same single auth, connect once and it works everywhere It's officially maintained, and Notion is now steering everyone here — they're even deprecating their older self-hosted MCP in favor of it. developers.notion.com/docs/m… #Notion #MCP #AItools

I used to measure progress by how fast the code shipped. I thought that was the win. Now I see it was the old game. The new game isn't writing code faster — it's how many AI agents you can keep pointed at the same target without them drifting apart. A year ago "AI-assisted" meant one engineer, one copilot, one file at a time. It felt unstoppable. Until the codebase got big enough that the agent forgot what it decided yesterday. The team of 2025: a handful of engineers, one copilot each, every session re-explaining the same context, work quietly redone. The team of 2026: one engineer, a swarm of agents, every one of them reading from the same spec. The bottleneck isn't typing code anymore. It's keeping agents that spawn agents aligned — so they stop undoing each other's work. Almost nobody has solved that. That's what we're building at Trellis. github.com/mindfold-ai/Trell…