Boris' Mindset Sparked My Rapid Iteration Journey
I have to say this interview changed my life. Hearing how Boris thinks about software spurred me to work much harder on releasing my own way of doing things and on iterating fast on how I build. Hard to believe it has only been a month since this one.
Real-Time User Feedback Drives Instant Feature Updates
I am proud to publish my personal stack but the coolest thing I have enjoyed so far is getting direct feedback from thousands of others who tell me what they want And I can launch a fix that same day. Or...
BART Hides Equity Consultant Fees Behind Fare Enforcement Claims
BART is claims they always took fare enforcement seriously. Why won't they respond to kane's public records request asking them how much they paid equity consultants to argue it didn't matter (and had "detrimental effects on the community")? https://t.co/wAHE5AYPf5
How to Escalate Comcast Business Outages Efficiently
🦇 SF @garrytan bat signal engaged Comcast Business is down again at your office? Step 1: Call their dedicated business line 1-800-391-3000. Step 2: Demand a ticket number. Step 3: Escalate to retention.
Gstack Now Available in Claude Code Distribution
I guess gstack is now in distribution in Claude Code You can just open a blank window and say install gstack and it works now https://t.co/w4ERSXrjFC
JPM100 Attendees Live‑Launch New Open‑Source AI Framework
I wonder how many other attendees at JPM100 at Big Sky Montana today are live-launching new version of their open source AI agentic framework https://t.co/J4AJTbyCdd
Smart Defaults Automate GStack, Accelerating Deployment Speed
I'm improving the /land-and-deploy skill in GStack and I am amazed that this is going to work I recommend most GStack users get the hang of /plan-eng-review and other plan skills, but once you get it and get sick of so...
Asset‑Seizing Forces Oppose Job‑Creating Datacenters
Datacenters create jobs and prosperity Is it a surprise that the forces that want to seize all assets also want to stop building all datacenters? https://t.co/d4JVZfWDLu
IPhone Should Be Open, Not a Walled Garden
If I could wave a magic wand to bring the future into the present faster, iPhone would become an open platform with open APIs and real consumer choice instead of a walled garden that is increasingly behind the times like...
Custom AI Tools Automate Reviews, Boost Reliability
Building your own tools like GStack is an amazing experience. You come up with something you think might work and then two days later it replaces what you were doing before. Instead of /plan-ceo-review and /plan-eng-review sequentially, I find myself using...
Testing 20 Workers Forces Local Postgres Max_connections Scaling
I've scaled app servers, I've scaled HAProxy, I've scaled Postgres replica dbs, I've scaled job servers Never until today have I had to scale my local max_connections for Postgres but once you run 20 simultaneous workers doing full tests, now I...
Latent Space Is Powerful, Not Just Simple Prompts
Latent space is amazing, and "it's just prompts" is a lie Also I'm giving it away for free, so if you want, I can pay you back what you paid me.
Aiming for 90× Code Output, Already 13× in 80 Days
I am literally tracking to create more 90X the code output I did in 2013 In 80 days I’ve done about 13X already
YC W26 Sets Record: 3× $1M Startups, 14%
YC Demo Day for W26 is in full swing The craziest stat: 3X more companies in this batch reached $1M annualized revenue than W25 Also crazy: the fastest revenue growth rate of YC history at 14% week on week growth *on average*...
GStack Streamlines Massive Legacy Codebase Integration
Just created my first PR into the Y Combinator codebase (1.84M lines of code total, this PR was 2400 lines) I got the YC internal/bookface codebase to run natively in @conductor_build - and it was hairy since it's a gargantuan...
10 PR Bug Fixes and CI Test Refactor Improve Stability
Cooking with GStack today. I just dropped 10 PR bug fixes from the community plus a big refactor of E2E CI tests, which should help stability overall. https://t.co/xJDTIpixTy
GStack: Accelerate Software Projects and Build Faster
I released GStack 2 weeks ago and we're still growing I made it because I was realizing: every software engineering project is changing. How could I accelerate the way I saw @steipete accelerate? GStack is my gift to everyone who wants...
Infrastructure Flaws Outpace Code Bugs in Hacks
I just shipped /cso v2 based on feedback I got on X from 24 hours ago when I dropped /cso v1 in GStack It's true - you're much more likely to get hacked via infra attack surface than code bugs (remember hire...
Open‑source AWS Alternative Promises Massive Cloud Cost Savings
Ubicloud is building the open source alternative to AWS and it's unbelievable what that means for running compute in the cloud Imagine this savings for every bit of your cloud spend. It's going to be marvelous. @UbicloudHQ https://t.co/LUrNXgpnYW
GStack Delivers Daily AI-Powered Coding Feature Updates
GStack is your personal AI coding toolkit, I'm dropping multiple new features per day right now
GStack Relies on Codex for Every Code Review
GStack actually will use Codex for code and plan reviews and I use it 100% of the time now
Unlock Value by Unleashing Tokens with Frontier Models
Oh this is probably an under-rated part of what is happening. You have to let the tokens rip. The magic happens because you use the frontier model and you have to be doing things that have economic value such that...
GStack Offers Just a Fraction of YC Batch Intensity
GStack is only 10% power of what it's like to actually come and go through a Y Combinator batch
Made GStack Office Hours Tougher After Feedback
Chinese Twitter said that /office-hours in gstack was not hard enough on founders, so I made them harder https://t.co/gBNbhtzPAw
Building Gstack as the New Claude for Chrome
I guess I am basically building gstack into what Claude in Chrome MCP was supposed to be https://t.co/tuRwixFRbu
1M‑Token Opus 4.6 Eliminates Context Limits
I underestimated how powerful Opus 4.6 with 1M tokens is. Even last year we were absolutely hitting context limit problems constantly. 1M tokens means you can do much more complex analysis entirely in context. Claude Code is so much better....
Blend Proven Practices, New Trends, and First Principles
Here's a preview of the kind of builder ethos I'm going to keep building into GStack. I was trying to do parallelization of my E2E testing framework (we use Bun to wrap Claude, Codex, etc. for specific end to end...
From Coding to Voice‑controlled Mega‑control Panels
/plan-ceo-mode in GStack can do this "zoom out" trick for any thing your codebase already does. Soon my /browse skill will not just be just a Playwright wrapper but one where my Claude Code will be able to do real...
Monetize Services, Not Raw Markdown, for Dev Tools
For agentic systems founders and dev tools founders: People do not want to pay for raw markdown and they shouldn't have to. But they may pay for orchestration, hosting, updates, collaboration, portability, analytics, and managed execution. These can be great...
Fare Gates Cut Transit Crime
Fare gates are the easiest way to reduce crime on public transit. After BART installed gates, violent crime dropped 36%. Overall crime dropped 41%. NYC got the same result in 1990. Enforcement, not hand-wringing about "root causes," works. https://t.co/bh2lDWF8jA
GStack Adds Windows Support, Falls Back to Node.js
GStack just shipped Windows support. Thanks to all my Windows users for bearing with us. There was a Bun runtime error on Windows and now it falls back to Node.js. Big thanks to the GStack contributor community - sorry it...
GStack: Free Open‑Source Platform with Daily Feature Updates
Hacker News on GStack - try it it's free and open source and I'm shipping new features every day for it https://lnkd.in/gDJRzGNr
Read Claude's Thinking Traces to Guide Its Output
This is amazing, I have my own experimental mode now in @conductor_build: Expand all tool calls One of the weirder things I realize most people don't do that I do: I read all the thinking traces of Claude Code and it...
New Codex Skill Boosts Bug Detection and Design
I added a /codex skill that does plan and code review in Claude Code and it has found so many more bugs and helped with far more elegant architectural designs And tomorrow I will launch native Codex support so you can...
Codex Delivers Rapid Code Reviews, Outshines Claude Conversationally
I was at the YC Spring 2026 kickoff social tonight and founders were asking me for Codex code review / plan review support, so I came home and shipped it same night And they're right, Codex is the amazing genius friend,...
Boost Productivity with Codex Code Reviews and Chrome Fallback
Two more gstack skills in the next 24 hrs: 1/ Using Codex as your brilliant near-non-verbal code review buddy who gets called in when you need the extra brain power 2/ If /browse gets stuck, we go from headless browser to Chrome...
Paid Tutorials Now Exist for GStack on Maven
OMG someone is charging money to teach people how to use GStack on Maven https://t.co/wNQdGrSLDq
Announcing BASED Act: Push for Fair Open Markets
Now announcing the BASED Act at YC with State Senator Scott Wiener We need open platforms and open markets. We need markets that are fair for all founders. We are not asking for a leg up. We are asking for a...
Incumbents Call AI Startup Agents Parasites, Data Belongs to Users
Recent earnings call, Aneel Bhusri of Workday says startups with AI agents are "parasites" This is what system of record incumbents really think of startups. The war is just beginning. The facts: the user data belongs to the users, not...
Launch of GStack Office-Hours Skill Mimics YC Guidance
I just launched /office-hours skill with gstack. Working on a new idea? GStack will help you think about it the way we do at YC. (It's only a 10% strength version of what a real YC partner can do for...
Diagram Requests in Reviews Eliminate 90% of Bugs
/plan-ceo-review and /plan-eng-review skills basically gets you 90% of the way to done most of the time the secret in plan-eng-review is that you can always ask for a diagram, and the act of creating the diagram (user flow, data flow,...
Data‑Driven Agents Power Accurate Automated File Search
You can build an agent but it is blind without data. The founders of @RunCaptainRAG applied their NLP research in their startup to create automated file search. Really accurate results within Garry's List. Here they are at the YC MV...
GStack Automates Role‑specific Review Tracking for Startups
New innovation: Just as at a well-run startup, there are CEO, engineering manager and design reviews, GStack now helps you keep track of what reviews are run, figures out what is appropriate (e.g. CEO doesn't have to look at infra...
Upgrade Gstack in Claude Code with Simple /Gstack-Upgrade
Upgrading your gstack setup in Claude Code is now as easy as just calling /gstack-upgrade. "Markdown as code" in action https://t.co/KdLt6hIMCO
AI Promises an Amazing Future, yet Underappreciated
AI is going to create a truly amazing future, but very few people really think that ... yet
Claude Code Delivers “I Know Kung Fu” Moments
The really crazy thing about language as code is that it's just about passing the right info to the right agent at the right time, even across workspace boundaries I'm having the time of my life developing https://lnkd.in/gDJRzGNr <-- if...
LLM Evaluations Enable Consistently Better Agentic Systems
Full evals system coming to GStack shortly. LLM evals are the only way you can make fully agentic systems that are repeatably better as you improve the workflow, context engineering and prompts.
AI
AI requires high IQ right now to get the most out of it But will that be true in 10 years? Or even next year?
NY AI Ban Shields Cartel, Ignoring Uninsured Crisis
New York wants to ban AI that outscores doctors on medical exams. Over 900,000 New Yorkers have no insurance. 92% of low-income legal problems go unaddressed. Anti-AI NY bill S7263 isn't consumer protection. It's cartel protection. https://t.co/e9BdWuvvUB
GPT-5.4 Solves Two-Decade AI‑impossible Polish Math Puzzle
A Polish mathematician spent 20 years building a problem he said no AI could solve. GPT-5.4 cracked it on run 11. https://t.co/ORmXbqZrVQ