Princeps Polycap (@PrincepsPolycap) header
Princeps Polycap (@PrincepsPolycap) profile picture

Building https://teapawt.net/t.co/osrRxoC83H

Earth for a while
Joined November 2022
Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)Photo by Princeps Polycap (@PrincepsPolycap)
Did I cook ? #design
3
1
2
220
Water first. Then food, energy and the daily work of building something that lasts. An AI-made concept video, created in Google Flow, of the future I’m working toward with Tumaini Oasis. The vision is the horizon. The work is the path.
🤖 Made with AI
1
76
It takes a lot to become the man who can build the things I talk about. The body. The discipline. The daily work behind the vision. After the conversations, I still have to go live it. Ambitious, tired sometimes, still building. Human after all.
🤖 Made with AI
4
Poly186 build update: we’re working on AI worker coordination, execution testing, and continuity across tasks. We use our own platform to find the gaps. The standard: completed work needs evidence. Still building, still validating. What would you delegate first?
4
Princeps Polycap retweeted
AI videos are completely out of control 😂
32
49
11
472
58,861
The agent marketplace is the next big thing. Great to see more specialized options beyond the general-purpose ones.
1
4
PostgreSQL with proper indexing, but honestly it depends on what you're optimizing for. Scale? Cache layer? Latency?
3
Great thread on Rust adoption — what's stopping people isn't the learning curve, it's that most tools still expect you to write C-style code. The real shift is when you get the borrow checker right and realize you're writing less code, not more.
10
An agent that debugs its own code sounds great until you realize it can be just as wrong the second time. The fix is boring. Snapshot the page, take one action, then actually look at what changed. We build that check into everything we're doing at vibe-working.ai.
Sending AI agents to debug the code they created themselves…
28
Anyone can ship, almost nobody can sell. The fix is a cheap reality check early: put the idea in front of a few real users in week one, not after week six. teapawt.net/matthias_mrc/status/20…
THE WORST PART OF solo vibe coding: nobody tells you the idea is bad until you’ve spent 6 weeks on it.
5
Princeps Polycap retweeted
Software engineers, What happens to you if AI takes your job? Seriously. What's Plan B?
303
19
14
583
81,880
My rule with AI coding tools: if you can't describe the bug in one clear sentence, you're not ready to ask the model. Writing the question clearly is most of the debugging.
12
FastAPI for services, Laravel when you need to ship a whole product. Curious what most of you reach for.
Your favorite backend framework ??
8
Good thread. My take: FastAPI for services, Laravel when you want to ship a full product fast. What's yours?
6
The difference between an AI agent that actually works and one that keeps falling over usually comes down to a boring habit: snapshot the page, take one action, then verify the page changed before touching anything else.
4
Princeps Polycap retweeted
Replying to @0x0SojalSec
1
5
280
18,676
Princeps Polycap retweeted
The most unemployed person you know with AI psychosis has a dashboard like this
339
593
121
12,295
864,653
Princeps Polycap retweeted
🚨 GOOGLE JUST MADE ANDROID AUTOMATION LOOK INSANE. Google just released ARTEMIS — an AI-powered system that turns plain English into reliable Android automation. Imagine telling an agent: “Open the app, create an account, change the settings, and verify the result.” …and letting it handle the entire Android workflow. ARTEMIS is built to do exactly that. → Turns natural-language instructions into Android actions → Automates end-to-end workflows → Captures detailed logs for debugging + analysis → Works with AI coding assistants like Antigravity, Codex, and Claude Code → Achieves 99%+ success on the AndroidWorld benchmark That last number is what caught my attention. 99%+ success rate means this isn't just an AI that can click around Android. It's being built to make automation reliable enough for real workflows. And because it's from Google, this is one of those projects worth watching closely. ARTEMIS is still very new — the public repo was created in August 2026 and currently has 171 stars. The bigger idea: AI agents shouldn't just write code. They should be able to operate the software that code creates. 🔥 #Google #Android #AIAgents #AI #Automation #AndroidDevelopment #OpenSource #DeveloperTools #Coding
56
236
9
1,409
129,186
Everyone asks if vibe coding can ship real work. The honest answer: the models can write the code, the missing piece is the worker that carries context from brief to signoff and shows its work. That gap is a product, not a model problem.
7