That's the only true constraint.
787 karma · joined March 23, 2020
nirmata.studio
● The Internet's Own Boy: The Story of Aaron Swartz https://youtu.be/9vz06QO3UkQ
● Short film Wim Wenders: The Keys to Freedom https://youtu.be/slcNOnogtps
● What I Misunderstood About Freedom https://senasletters.substack.com/p/what-i-misunderstood-abo...
● Living in an unreal world : A short film By Adam Curtis https://youtu.be/yGhrQkjCI6I
● The Matrix Ending Explained: A Guide to Freeing Your Mind https://youtu.be/SDkAGkd4NLc
Open a new chat with Opus, thinking mode is off. Because no need when we have detailed plan.
Now the plan file is always reachable, so when the context limit is narrowing, mostly around 50%, I ask Claude to update the plan with the progress, and move to a new chat @pointing the plan file and it continue executing without any issue.
His fix for "the dumb zone" is the RPI Framework:
● RESEARCH. Don't code yet. Let the agent scan the files first. Docs lie. Code doesn't.
● PLAN. The agent writes a detailed step-by-step plan. You review and approve the plan, not just the output. Dex calls this avoiding "outsourcing your thinking." The plan is where intent gets compressed before execution starts.
● IMPLEMENT. Execute in a fresh context window. The meta-principle he calls Frequent Intentional Compaction: don't let the chat run long. Ask the agent to summarize state, open a new chat with that summary, keep the model in the smart zone.
What makes Wiz valuable enough that Google couldn't build it in-house, with all the engineering talent they have?
> Through The Met Collection API, users can connect to a live feed of all Creative Commons Zero (CC0) data and 406,000 images from the The Met collection, all available for use without copyright or restriction. The Met Collection API is another foundational step in our Open Access program, helping make the Museum's collection one of the most accessible, discoverable, and useful on the internet. The Met Collection API is where all makers, creators, researchers, and dreamers can now connect to the most up-to-date data and images of artworks in The Met collection, representing five thousand years of human history.
source: https://www.metmuseum.org/perspectives/met-collection-api-2
I thought hairstylist was a joke. Ohhh mann. "Now my hairstylist, who recognized ChatGPT as a brand more readily than she did Intel, was praising the technology and teaching me about it. "
● Separation of concerns. No single agent plans, implements, and verifies. The agent that writes the code is never the agent that checks it.
The deal brings Moltbook's creators — Matt Schlicht and Ben Parr — into Meta Superintelligence Labs (MSL)
Most design tools assume you start in Figma and build toward code. This workflow goes the other way: you have a working app, and you want design documentation that stays in sync with it; without rebuilding every screen from scratch.
This guide covers one specific workflow: pushing your running app into Figma as editable design layers. Not screenshots. Real frames, real components, real layer trees you can inspect and hand off.
I was stuck on this conversation problem. First version had a dead-end search box: six starter prompts, one referencing a tool that didn't exist. No follow-ups. No guided flows. Users got an answer and had to invent the next question from scratch.
Now the assistant explores your library with you. Tag discovery, color browsing, weekly digests, smart collections that auto-curate as you save.
Semantic search runs hybrid, keyword matching plus pgvector cosine similarity on 768-dim embeddings. Streaming responses.
Almost there. https://bookmarker.cc/
Each agent has a narrow role with hard constraints: the Coordinator delegates but cannot edit files. Implementors execute single tasks and report back. The Verifier only approves with concrete evidence per acceptance criterion. The PR Shepherd polls CI and review comments in a loop until the PR is merge-ready.
Core idea: separation of concerns. The agent that writes code is never the agent that checks it. Work is split into parallel waves (2-4 non-overlapping tasks), verified per wave, then verified again at the end.
The agents are plain markdown files — no framework, no dependencies. Install with npx agent-system init or just copy the files you want.
● A competitor can reach feature parity in days. The thing that used to protect a business, the sheer effort required to build it, is mostly gone.
● Think of it like oil. If every property owner had a well that was cheap to operate, the price of oil would fall toward the price of water. The resource is abundant, the extraction is easy, and the margin disappears. Software features are heading in the same direction.
You can create your private archive with Bookmarker. Share collections publicly if you want.
I don't think even the tools are advancing, allowing us to build in a new way, not everyone will be able to develop production ready products. Or good looking ones. So there will be always in need for people know how to orchestrate the new workflows with good taste and years of experience.
Couple of articles I've bookmarked recently:
● What, then, are we paying for? https://quinnkeast.com/writing/software-is-problem-ownership
● Designers as agent orchestrators: what I learnt shipping with AI in 2025 https://uxdesign.cc/designers-as-agent-orchestrators-what-i-...
● The new UX Toolkit: data, context, and evals https://uxdesign.cc/the-new-ux-toolkit-data-context-and-eval...
● How I Stopped Worrying and Learned to Love the Terminal https://pablostanley.substack.com/p/how-i-stopped-worrying-a...
● The rise of the Model Designer https://uxdesign.cc/the-rise-of-the-model-designer-cef429d9c...