You can just build things
Virginia
Joined January 2014
- Tweets4.4K
- Following1.1K
- Followers245
- Likes55.7K
We live in uncertain yet incredible times.
Since the "ChatGPT moment" two years ago, I've seen the writing on the wall as many of you have that AI will change humanity in a powerfully non-negotiable way.
Our path forward isn't to resist this change—it's to harness these extraordinary advances to elevate human potential.
Learning is the cornerstone business practice of all human development and advancement. To progress ourselves, we need to enhance and overhaul our learning system. The signal for this change has never been louder than it is today.
In my work "Learn to Adapt" I outline how we can adapt the American education system to advance ourselves in this incoming decade of AI transformation.
Read the full blueprint here -> tinyurl.com/LearntoAdapt
I'm not just sharing this as food for thought—I'm directly inviting you to join a mission through the @AdaptEducation_ project.
This rapid-development research project is funded through blockchain technology (Solana - $ADAPT). As we progress, every bit of funding drives research into methods, tools, curriculum development and more that will directly shape how AI transforms education.
Promising experiments in AI-driven education are already happening today, and we need more of them to ensure scaled and operational success across the entire US. We must fail fast and push the edge of innovation to adapt our system quickly enough to avoid the potentially catastrophic side effects of this AI revolution.
I'll continue to share my thoughts here on X about why and how we can adapt our learning system, exactly what this project will achieve, and more.
Micah retweeted
New challenge unlocked: keeping the laser fed
Only drip feeding it orders to start but man it is FAST. Chewed through a full 96x240 plate in less than 20 minutes
Muse and these other assistants are way immature. Integrations are not built in a robust way.
Muse can’t even read accurate details from facebook, it’s not even built into the core product it’s parent company owns.
Micah retweeted
human-in-the-loop
└ human-on-the-loop
└ human-near-the-loop
└ human-cc'd-on-the-loop
└ human-legally-liable-for-the-loop
Sounds interesting enough to test out. @bcherny what do you think about adding to claude?
Compaction is a mistake.
When an agent's context fills up, tools like Codex and Claude Code compact it:
1. The model prefills the entire session again
2. It writes a summary of everything so far
3. A new session starts from that summary
I measured this on a real ~400k-token session with Opus 5.5:
→ 38 s and $1.99 when the prompt cache has expired
→ 29 s and $0.17 when it hasn't
And the summary is lossy. The exact error message, the file path, the one number you needed is often gone.
So I do something new for Mainplane
Context retrieval works the other way around. Mainplane keeps the full record of every session as a file. When the context fills up, a new session starts right away with one instruction: "You are continuing session X. Retrieve key context from it as you go."
The agent searches the old session and copies the exact lines it needs, when it needs them.
Same session, same model: 15 s and $0.10 to get back to work. It does not depend on a cache hit, and nothing is paraphrased.
This is the bitter lesson applied to agent memory. Don't hand-design what the model should remember. Give it the full record and good tools, and let it decide.
Mainplane is open source (MIT). Link in the first comment.
Micah retweeted
“Commander Cody, have you completed your fiscal year Galactic Republic Cyber Awareness Training?”
“I have not general.”
“You should probably get on that.”
“Yes General.”
Micah retweeted
American glass. American metal. American silicon. American batteries. American workers. American everything.
BlueChip is the first American computer in decades. Don't let anyone lie to you and say it can't be done.
Designed in California. Built in America.
Just being real, Codex (as a harness) is a total joke. I have claude code task the CLI, but the default ChatGPT/Codex desktop app is moronic.
Can't do basic web search, can't remember that it has auth to external projects like a git repo, it cries wolf constantly saying "oh I can't do this because I lack access or tools".
These are issues I literally never run into with command line tools.
Additionally, some of the codex features are just 100% broken. Sometimes chat will show a link to something like a local .mp4, i'll click on it and nothing happens. Why?
Other times it will open the mp4 in the integrated viewer for codex. It's just totally untested and broken, very sad untested application.
This is obviously staged, people are not shipping rifles to their house without a background check, everything goes through FLLs, a fake scenario for political gain. Additionally, all Marines swear an oath to the constitution. Supporting restriction of arms would be in violation of that oath. End of story.
You're lying and you're betraying your oath.
*looks* - it's a different harness. Claude code was started as a CLI, I trust that codebase more.
it's similar, it uses anthropic models, it may even invoke some of the underlying components, but I don't really care to make the switch because of any subtle implication that a harness switch may cause.
Micah retweeted
My Claude found a critical zero day vulnerability in the Code of Hammurabi, unnoticed by developers for 3,779 years.
Micah retweeted
🔐 Node.js security updates are now available!
New releases for Node.js 22.x, 24.x & 26.x address multiple vulnerabilities, including high-severity issues.
Review the details and update your systems to stay secure.
🔗 nodejs.org/en/blog/vulnerabi…
#NodeJS #Security
