Sign in

Jess Martin

@jessmart.in
1.7K followers 376 following 730 posts

🛠 Tools for a better tomorrow 🧠 Architect-philosopher 💼 Building lifebuild.me 🏠 jessmart.in 📍Fuquay-Varina, NC

PostsRepliesMedia
Jess Martin @jessmart.in · 01/05/2026
Feeling this every single day. Trying to restructure my practices and habits to go deep on comprehension and understanding. aicoding.leaflet.pub/3maqpvianlc2...
aicoding.leaflet.pub
Code Was Never the Asset - The Phoenix Architecture
Why AI makes the hidden economics of software unavoidable
181
Jess Martin @jessmart.in · 12/03/2026
Coolest thing I’ve read all year
030
Jess Martin @jessmart.in · 12/03/2026
> In principle, arbitrary programs can be compiled directly into the transformer weights, bypassing the need to represent them as token sequences at all. > That would make weights themselves a deployment target for software. New App Store just dropped
040
Jess Martin @jessmart.in · 12/03/2026
Winner
011
Reposted by Jess Martin
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 11/03/2026
www.percepta.ai/blog/can-llm... As a research lark at Percepta, Christos embedded a computer into an LLM, showed that it could solve the hardest Sudokus, and then as a side bonus built an exponentially faster attention
2131359
Jess Martin @jessmart.in · 05/03/2026
irc.freeq.at
irc.freeq.at
freeq
IRC for the open web. AT Protocol identity. Pronounced like 'freak'.
000
Jess Martin @jessmart.in · 04/03/2026
congrats!
010
Jess Martin @jessmart.in · 19/02/2026
we're using this "library" approach right now to build lifebuild.me and it's working pretty well. longer write-up coming. early version is here if you want to peruse: github.com/sociotechnic...
lifebuild.me
LifeBuild — Reclaim Your Sovereignty
LifeBuild helps you design, track, and achieve the life you want to live. Take back control of your time, energy, and priorities.
010
Jess Martin @jessmart.in · 19/02/2026
I will say a *lot* more soon, but here's the gist: - Software can be defined by documentation about the software (context) - Software can be autonomously built to keep up with changes in the documentation Working on building both the Library + the Factory More here: sociotechnica.org/notebook/
sociotechnica.org
Lab Notes
SocioTechnica Lab Notes - thoughts, experiments, and works in progress.
100
Jess Martin @jessmart.in · 16/02/2026
the context is the software the code is just a cache
110
Jess Martin @jessmart.in · 10/02/2026
every developer a 10x developer
000
Jess Martin @jessmart.in · 10/02/2026
I wonder if GitHub is ready for 100-1000x in volume
120
Jess Martin @jessmart.in · 09/02/2026
Godspeed!
010
Jess Martin @jessmart.in · 06/02/2026
Overnight on lifebuild.me I asked Codex to: - Swap out my in-product agentic loop for pi.dev - Refactor the entire UI, removing dead code - Create custom project icons in-app w/ Nano Banana Pro - Create a LifeBuild MCP server 📈 models ➡️ 📈 ambition
000
Jess Martin @jessmart.in · 05/02/2026
Something people don't talk about enough when working with AI is just how much *fun* it is. It's not just about productivity! Claude Code is fun. Conductor is fun. ClawdBot is fun. Lean into the joy, folks!
010
Jess Martin @jessmart.in · 04/02/2026
First batch of alpha invites going out for lifebuild.me Nervous, but excited! Feels so janky right now and there's a million things I want to fix, but really important to just get it out there.
lifebuild.me
LifeBuild — Reclaim Your Sovereignty
LifeBuild helps you design, track, and achieve the life you want to live. Take back control of your time, energy, and priorities.
001
Jess Martin @jessmart.in · 04/02/2026
bsky.app/profile/jess...
010
Jess Martin @jessmart.in · 04/02/2026
openclaw feels like a glimpse of the future: - gateways to interact (right now, chat, but could be GUIs) - tool-using LLM in a loop - can bootstrap itself with new skills (discovered + new) - can modify it's own code and manage its own config why don't more apps work this way?
100
Reposted by Jess Martin
Jake Lazaroff @jakelazaroff.com · 04/02/2026
i mean i'd love to see more efforts like OCIF but failing that i think people could start cramming their app's data into HTML, PDF, etc. wouldn't make interop seamless but it would be easier to read and adversarially edit or script around
canvasprotocol.org
Open Canvas Working Group | OCWG
Working group for establishing interoperability between different infinite canvas tools.
041
Jess Martin @jessmart.in · 04/02/2026
Same energy: bsky.app/profile/jess...
000
Jess Martin @jessmart.in · 03/02/2026
so cool! I still have an AE-1 at my parents house. would love to revive it.
110
Jess Martin @jessmart.in · 03/02/2026
sociotechnica.org/notebook/con...
sociotechnica.org
The Context Library of Alexandria (Part 1)
Why agents make poor micro-decisions, and a five-dimension framework for delivering the context they're missing.
010
Jess Martin @jessmart.in · 03/02/2026
We're talking hundreds of simultaneous agents. For that, you need context to maintain alignment. And that takes a Library. I'm not saying we the best solution yet, but I am saying this is going to be a MAJOR problem that more people need to start thinking about.
130
Jess Martin @jessmart.in · 03/02/2026
So far, I've written about the Software Factory and the Software Library. Factory has gotten all the play. No one knows what to do with Library (or why they even need one). People saying things like "I run 3-4 agents at a time, life is good! we've arrived!" That's not the factory. Not even close.
110
Jess Martin @jessmart.in · 03/02/2026
What will you do with your one wild l̶i̶f̶e̶ LLM-enhanced senior eng sw dev skillz?
000
Jess Martin @jessmart.in · 03/02/2026
The easiest path to malleable software: put an agent inside your app that has access to the repo for the product and can implement fixes and push PRs in response to the user pointing out problems. "Self-healing software"?
020
Jess Martin @jessmart.in · 30/01/2026
But you're kinda right: Factories are the ultimate nerd-snipe. "You mean instead of (having an agent) writing software, I can build a factory that (has agents) writing software for me?"
110
Jess Martin @jessmart.in · 30/01/2026
aren't we all? 😏
100
Jess Martin @jessmart.in · 30/01/2026
Full initial writeup with the five-dimension framework: sociotechnica.org/notebook/co... PS: If you're building in this space, I want to compare notes.
sociotechnica.org
The Context Library of Alexandria (Part 1)
Why agents make poor micro-decisions, and a five-dimension framework for delivering the context they're missing.
000
Jess Martin @jessmart.in · 30/01/2026
And we're building an AI librarian to maintain it. His name is Conan. Conan watches context streams, decomposes into atomic notes, establishes links, assembles slugs on demand. His human boss makes judgment calls. Conan handles volume.
120
Jess Martin @jessmart.in · 30/01/2026
We're calling this a Context Library. There are two related context: - The Library: complete knowledge base covering past, present, future - The Context Constellation: curated context assembled for a specific task
100
Jess Martin @jessmart.in · 30/01/2026
Give an agent the full context and the micro-decisions improve. Not because the model got smarter—because the context got richer. This is a management problem, not a model problem.
110
Jess Martin @jessmart.in · 30/01/2026
What they don't get: - WHERE: What's adjacent? What breaks if you touch it wrong? - WHEN: What did we try before? Why did it fail? - WHY: What objective does this serve? WHERE, WHEN, and WHY are the missing bundle.
110
Jess Martin @jessmart.in · 30/01/2026
None of this gets written down. Almost none of it reaches the agent. Agents typically receive: - WHAT: specs, requirements - HOW: codebase, process instructions
100
Jess Martin @jessmart.in · 30/01/2026
The real issue is we've been starving agents of context human devs absorb by osmosis: - Hallway conversations about why the last approach failed - The senior engineer who says "we tried that in 2024" - Ambient awareness of what's adjacent, what's fragile
100
Jess Martin @jessmart.in · 30/01/2026
There's a growing body of work on why separate AI agents struggle to make aligned decisions. They miss nuance. Break adjacent systems. Repeat past mistakes. The usual diagnosis is the agents aren’t good enough yet. But I think that's wrong.
100
Jess Martin @jessmart.in · 30/01/2026
The Software Factory solves an operational problem: how do we orchestrate agents to deliver high-quality software. Once you know what to build, the factory gets to work. It doesn't solve the alignment problem. How do you keep the factory fed? Let me explain. x.com/jessmartin/...
241
Jess Martin @jessmart.in · 29/01/2026
I was wrong. It's not JUST the year of the Software Factory. It's the year of agent orchestration, generally. Across all domains. I wasn't seeing the larger movement. Now I can't un-see it.
000
Jess Martin @jessmart.in · 28/01/2026
I live here
030
Jess Martin @jessmart.in · 27/01/2026
I use conductor.build every day and love it. I wonder if they are thinking about higher-level orchestration? I hope so! someone needs to to build it.
conductor.build
Conductor - Run a team of coding agents on your Mac
Create parallel Codex + Claude Code agents in isolated workspaces. See at a glance what they're working on, then review and merge their changes.
020
Jess Martin @jessmart.in · 27/01/2026
*glean
000
Jess Martin @jessmart.in · 27/01/2026
How might this change software architectures? You should be looking for things like @chadfowler.com's Phoenix Architecture: aicoding.leaflet.pub/
aicoding.leaflet.pub
The Phoenix Architecture
Generative AI coding demands what we've always known: modularity, clear boundaries, disposable components. Principles that scaled human teams are now table stakes. Here, we make the implicit explicit
010
Jess Martin @jessmart.in · 27/01/2026
If you want to catch up on the latest hot projects in this space, Yegge's Gastown is quite interesting. Check out @maggieappleton.com's breakdown of Gastown to clean the good stuff: maggieappleton.com/gastown
maggieappleton.com
Gas Town’s Agent Patterns, Design Bottlenecks, and Vibecoding at Scale
On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code
220
Jess Martin @jessmart.in · 27/01/2026
Props to @schickling.dev—he sent me down this path last July with this tweet: x.com/schickling/...
100
Jess Martin @jessmart.in · 27/01/2026
It’s not just theory, fascinating as that is! We're trying out the factory approach while we build an app called LifeBuild. lifebuild.me
100
Jess Martin @jessmart.in · 27/01/2026
I wrote this up here: sociotechnica.org/notebook/so...
sociotechnica.org
The Year of the Software Factory
110
Jess Martin @jessmart.in · 27/01/2026
We don't know the limits yet. Individual devs using AI are already seeing 5-10x. A factory line? Maybe 100x? The next Google might be 10 people operating a finely-tuned factory.
100
Jess Martin @jessmart.in · 27/01/2026
Why does this matter? In a factory, improvements compound to the whole org. Optimize one station and every task that flows through benefits. Forever. This is why manufacturing ate craft production. Not skill—system. And hand-crafted software will get eaten the same way.
100
Jess Martin @jessmart.in · 27/01/2026
Here’s the shift I imagine: tasks flow through a factory line. Imagine software dev as a literal factory. Each stage a station. Tasks enter and flow through, station by station, and emerge as deployed software. Developers don't shepherd. They build and operate the line.
110
Jess Martin @jessmart.in · 27/01/2026
For 50 years, developers have shepherded tasks through the software development lifecycle. You pick up a ticket, carry it from planning to implementation to review to deploy. I think that model is ending.
120