Masa Matsuoka's Avatar

Masa Matsuoka

@bobmatnyc.bsky.social

Product engineering lead. Traveler, gardener, snowboarder, bass player, mezcal fan, partner to Joanie, father of daughters.

1,147 Followers  |  833 Following  |  367 Posts  |  Joined: 10.11.2023
Posts Following

Posts by Masa Matsuoka (@bobmatnyc.bsky.social)

Preview
Context Memory and Search: The Secrets to Effective Agentic Work Why search and memory systems matter more than smarter AI models

open.substack.com/pub/hyperdev...

26.02.2026 13:15 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

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.

26.02.2026 13:15 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
The Evidence for β€œLittle AGI”: What’s Real and What’s Speculation Separating signal from viral speculation

open.substack.com/pub/hyperdev...

23.02.2026 12:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image Post image Post image

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.

23.02.2026 12:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Get Claude.ai Cowork. Paste the sheet into a new that. Ask it what you want. It will likely handle it for you.

23.02.2026 06:30 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Why I Switched To Claude Code for Writing The Power of Local Workflows

open.substack.com/pub/hyperdev...

19.02.2026 12:45 β€” πŸ‘ 2    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
Post image Post image Post image

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 Codeβ€”files on my filesystem, editable in Obsidian.

Here's the workflow.

19.02.2026 12:45 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Video thumbnail

Wow.

17.02.2026 03:59 β€” πŸ‘ 35735    πŸ” 16565    πŸ’¬ 1291    πŸ“Œ 2461
Preview
2026 Will Be The Year Of Software And The Year SASS Sees A Major Contraction

open.substack.com/pub/hyperdev...

16.02.2026 12:45 β€” πŸ‘ 3    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0
Post image Post image

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.

16.02.2026 12:45 β€” πŸ‘ 4    πŸ” 2    πŸ’¬ 1    πŸ“Œ 0
Post image Post image Post image

Stack Overflow still gets read.

It stopped getting written.

Question volume collapsed 95% from peak. The archive is a museum nowβ€”visited, but not lived in.

Where did developers go? Everywhere else.

open.substack.com/pub/hyperdev...

12.02.2026 13:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Or lazy, which is wise mode than oblivious though not as bad as sociopathic. Perhaps the combination of the two is the third?

12.02.2026 06:20 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

*sociopath to be fair.

12.02.2026 06:13 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

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.

12.02.2026 06:13 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0

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.

12.02.2026 06:10 β€” πŸ‘ 4    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

Yes

12.02.2026 06:09 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Your IDE Is a Comfort Blanket And It’s Smothering You

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 inβ€”and it points to one mistake: mixing generation and editing in the same interface.

open.substack.com/pub/hyperdev...

11.02.2026 13:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
ARTICLE: Opus 4.6 and Agent Teams Anthropic’s Multi-Agent Coding Push

open.substack.com/pub/hyperdev...

06.02.2026 13:30 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

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.

06.02.2026 13:30 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
HyperDev’s Three Golden Rules A Manifesto for Professional AI Work in 2026

open.substack.com/pub/hyperdev...

04.02.2026 01:35 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

"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.

04.02.2026 01:35 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Says the cretin who knows less about β€œwhat America was about” than any person I know.

02.02.2026 05:26 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 1
Post image

open.substack.com/pub/hyperdev...

30.01.2026 13:40 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

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.

30.01.2026 13:40 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image 24.01.2026 22:29 β€” πŸ‘ 35    πŸ” 16    πŸ’¬ 3    πŸ“Œ 1
Preview
Trust Is Procedural, Not Cognitive What Compiler History Teaches Us About AI Code

open.substack.com/pub/hyperdev...

21.01.2026 12:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Only 3.1% of developers highly trust AI-generated code. Yet 51% use AI tools daily.
That gap doesn't close through belief. It closes through process.

Full analysis with the research, frameworks, and practical verification stack: πŸ‘‡

21.01.2026 12:45 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0
Preview
When β€œClaude Code for Productivity” Meets Reality A review of Anthropic's new Cowork

open.substack.com/pub/hyperdev...

19.01.2026 12:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Anthropic just shipped Coworkβ€”"Claude Code for the rest of your work." I've been testing it while prepping for a new CTO role.

The tool itself: solid step forward. Handles long-running tasks without crashing. Saves output to your filesystem. Works.

19.01.2026 12:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Video thumbnail

Watching the planes land at Maho beach in St. Martin.

14.01.2026 19:31 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0