goodthings retweeted
Context Loops is free and open source.
Docs and framework: context-loops.vercel.app/
If you're building with AI agents, this shows how to structure project context so work carries across sessions instead of resetting every time.
goodthings retweeted
A lot of people using AI right now aren't becoming more productive.
They're just spending tokens.
They open a new chat, re-explain their project, get some output, and start fresh the next time. It feels like progress. It isn't.
I know because I did this for months.
Most people miss two fundamental constraints of LLMs: they don’t remember anything between sessions, and even within a session their memory is limited by the context window.
Every new chat starts from zero. No memory of your decisions. No awareness of what you already tried. No understanding of what your goals are.
The result is chaos.
The AI contradicts itself.
It re-suggests ideas you rejected last week.
It feels like onboarding a new hire every morning who never read the docs.
After eight months building a production app with AI and getting this wrong more times than I'd like to admit, I stopped blaming the tools and started designing a solution.
The result is Context Loops, an open-source framework that structures your project context so AI agents can actually work across sessions.
Tickets. Session logs. Sprint records. Decision logs. All living in your repo, all feeding into every future session.
Your work carries over instead of disappearing.
The shift it creates is simple: you stop being a passive user of AI and start orchestrating it.
If you're building with ChatGPT, Cursor, Claude, or Copilot and your sessions feel like they reset every day, this is the fix I wish I had eight months ago.
The framework is free and open source. Full docs in the comments if you want to try it.
goodthings retweeted
This is such a great analogy and sage advice from @KiteVC
Machines can't replaces humans...yet. And they may never fully be able to. However, they will replace many of the tasks we have to do today.
Learning fundamentals allows us to be creative. And creativity is something that AI is going to have a very difficult time beating humans at. Never stop learning ⚡️
A young person thinking through their college degree asked:
“ If OpenAI can generate code now, why are CS degrees even useful anymore”?
My response :
“When word processing programs replaced typewriters, it didn’t eliminate the need to learn English. Those that learned how to use programs like Microsoft Word completely obliterated writers that only knew how to use physical typewriters.
They became like symphony conductors that were faster and more fluid with the words, able to iterate and refine to create great pieces.
But the word processing program by itself did not make you a great writer. The word processor totally freed you to express if you were already good at English. So learn the basics.
You may be able to ask an AI engine to create and output code for you but you STILL have to understand it to tune it; so you can become a “symphony conductor of the code” rather than a “printer” of the code that adds no more value than a toner cartridge transmitting what comes out of an AI code generator. “
goodthings retweeted
If you've ever had to train someone to takeover your job as you leave for a new one you will understand more about the challenges of AI taking over entire industries than any think piece ever could.
goodthings retweeted
Most AI success stories are demos.
Building with AI agents is nothing like what the courses or vibe-coded apps show you.
I spent 6 months shipping a real production app with agents. It leaked my database credentials. Blew past budget 4.5×. Quietly broke its core feature for three days before I noticed.
AI didn't cause the failures. It just magnified every decision I made.
The model matters far less than the context you give it.
AI handles execution. Humans handle reality.
Full case study + interactive simulator tomorrow.
goodthings retweeted
This guy literally explains how knowledge is now worth zero with AI.
Knowledge is now worth zero.
goodthings retweeted
The toxicity in crypto is driving away talented people who hate drama. This is an existential threat to the industry. Behind every protocol and project are professionals with options elsewhere. Trolling seems harmless until you wake up and your ecosystem is a ghost town.
goodthings retweeted
The fact that GPTs don't claim ownership of generated code is the biggest asymmetric opportunity since Bitcoin.
goodthings retweeted
The ability to make cheap calls to LLMs via api is a step-change that many do not yet appreciate.
goodthings retweeted
If Danny have launched a new collection when they started paying attention to ordinals instead of waiting for parent-child provenance, it would have been a totally different story.
But this is all ordinals lore. Good one imo. Nothing beat those early days.
