open.substack.com/pub/hyperdev...
05.03.2026 13:45
👍 1
🔁 0
💬 0
📌 0
I replaced enterprise developer productivity tools costing $36K-92K annually with a custom system that costs $0.05 per report.
GitFlow Analytics: 154 developers, 100+ repos, automated leadership reports. Built in couple weeks.
When intelligence costs pennies, everything else becomes optional.
This innocent little girl was killed by our bomb, with our money, in our name, without our permission. Shame on the United States. We have become a stain on the planet.
Last week I gave three directives on a project. Three minutes total.
Batch the LLM calls. Use a cheap model. Use Bedrock.
Three sentences. Three completely different categories of concern: performance, economics, infrastructure.
The AI didn't suggest any of them. The AI implemented all of them.
Guten morgen Berlin.
My prompts have gotten shorter. A lot shorter. Mid-2025 they averaged 12-15 words. Now they're 6-8. "Check logs." That's it.
What changed: search and memory. Not smarter models.
This piece is about why information architecture matters more than model capability for serious agentic work.
Went down a rabbit hole on AI consciousness ("Little AGI") research this week.
The viral claims? Overblown.
The actual papers? Way more interesting. Models that know when they're being tested. 20% accuracy on detecting their own internal states. Misalignment that emerges from narrow training.
Get Claude.ai Cowork. Paste the sheet into a new that. Ask it what you want. It will likely handle it for you.
There are two cognitive modes when working with text: generating and editing.
AI is great at generating. Traditional editors are great at editing. I spent months trying to force Claude.ai to do both.
Then I switched to Claude Code—files on my filesystem, editable in Obsidian.
Here's the workflow.
Wow.
GitHub: 100+ million new repositories in 2024. 25% YoY growth.
My Head of Product friend: "We're seeing 2-3x output from our top engineers. PMs and designers can't keep up."
2026 won't be remembered for AI. It'll be remembered for the software explosion AI enabled.
New post on what's coming.
Stack Overflow still gets read.
It stopped getting written.
Question volume collapsed 95% from peak. The archive is a museum now—visited, but not lived in.
Where did developers go? Everywhere else.
open.substack.com/pub/hyperdev...
Or lazy, which is wise mode than oblivious though not as bad as sociopathic. Perhaps the combination of the two is the third?
*sociopath to be fair.
You move on. If you don’t look for an opportunity to connect to a hand reached out in a mutual acquaintance-making, you are either oblivious or a psychopath. Neither bode well.
I think we’re learning that it’s not him, per se. in a normal world he’d be just pathetic as he was in NYC. It’s his enablers. Never forget them.
Yes
The IDE isn't the villain. AI code generation layered on top of it is.
41% more bugs. 30% more warnings. An "illusion of competence."
The research is in—and it points to one mistake: mixing generation and editing in the same interface.
open.substack.com/pub/hyperdev...
Anthropic just released Agent Teams in Claude Code - multiple AI agents working in parallel on the same codebase, coordinating autonomously.
A researcher stress-tested it by having 16 agents build a C compiler from scratch. Cost: $20K. Result: 100,000 lines that compile Linux.
"Just ask GPT" is productivity theater.
Three rules that actually work:
AI writes its own instructions
Strategic context beats document hoarding
Different model checks the first
Nine months of testing. New manifesto on HyperDev.
Says the cretin who knows less about “what America was about” than any person I know.
open.substack.com/pub/hyperdev...
I built claude-mpm to orchestrate AI agents for coding. Then I used it to onboard as CTO.
One week. 5 hours of my time. 267 analysis documents.
And answers to questions most new executives don't get to ask for six months.
The "new guy card" is comfortable. I wanted to walk in like a veteran.
