ftrou

Companies are burning millions on AI that rewrites the same files over and over. At scale, a token fireweall between LLMs and codebases = -10-50x TOKEN SAVINGS -zero architecture drift -reproducible codegen -"compiler" for AI intent github.com/ftrou/Decodifi…

github.com/ftrou/Decodifi… **DeCodifier gets code agents to the right method, caller, and framework entrypoint first. **

@elonmusk whatcha gonna do bout it?

China is moving rapidly to a solar/electric future with very little need for oil or gas

@elonmusk true story

For those unaware, SpaceX has already shifted focus to building a self-growing city on the Moon, as we can potentially achieve that in less than 10 years, whereas Mars would take 20+ years. The mission of SpaceX remains the same: extend consciousness and life as we know it to the stars. It is only possible to travel to Mars when the planets align every 26 months (six month trip time), whereas we can launch to the Moon every 10 days (2 day trip time). This means we can iterate much faster to complete a Moon city than a Mars city. That said, SpaceX will also strive to build a Mars city and begin doing so in about 5 to 7 years, but the overriding priority is securing the future of civilization and the Moon is faster.

@Tech_girlll It works

Frontend has screenshots. Backend has… what? How do backend developers show proof of work?

@_Riyatwt Codex

@eliana_jordan aint nobody got time for that

Be honest: Do you also ask AI to write prompts for AI?

@elonmusk amazing

Neuralink will start high-volume production of brain-computer interface devices and move to a streamlined, almost entirely automated surgical procedure in 2026. Device threads will go through the dura, without the need to remove it. This is a big deal.

@benln no better time than the present

Who's building on New Year's Eve?

@_devJNS zuckmusk

who's this..?

@Python_Dv B 🤞

Comment below the output! 😃👇

@Benioff @JPMorganPI It will get even cheaper with this.. github.com/ftrou/Decodifi…

AI on a wicked race to the bottom! Grok 4: $0.28/M tokens Gemini 3 Flash: $0.50/M tokens Gemini 2.5 Flash: $0.30/M tokens Gemini 2.5 Flash-Lite: $0.10/M tokens GPT-4 in ’23: $37.50! Look out below, and let’s go! ❤️

@akshay_pachaar I feel this

APIs are a bottleneck, not a solution! AI agents can't access 95% of the web because most websites simply don't have APIs. Supplier portals, appointment systems, regional job boards, etc., none of them have developer APIs. The valuable data lives behind logins, multi-step forms, and interfaces built for humans, not machines. That's why, for 25 years, users have been stuck with: - Search engines that index 5% of the web (nothing behind authentication) - Manual data entry or fragile scrapers that break with every CSS update That's the problem TinyFish's Mino solves. It is a web automation API that can simultaneously navigate 100s of websites and turn them into structured data. You send it URLs and a goal in plain English. It returns JSON. The approach is different from typical AI agents: Most browser agents use vision models, which screenshot the page, reason about it, decide what to click, screenshot again, and repeat. Every action needs a model call. It's slow and expensive. Mino uses AI to learn the website structure once, then executes it through deterministic code. First run figures out the site. Every run after that is code-level precision in milliseconds. It provides three core capabilities: → Navigate - Handles logins, forms, and multi-step workflows → Extract - Pulls structured JSON from any site layout → Execute - Runs 100+ sites in parallel with stealth mode The performance is production-grade: - 85-95% success rate on complex workflows - 10-30 seconds per task - Pennies per run Moreover, it works on authenticated sites, bypasses anti-bot protections, and returns clean JSON every time. Lastly, you can also integrate its MCP server with clients like Claude Desktop. I have recorded a walkthrough in the video below. Try now, link in the next tweet.

@karpathy be careful what you give the llm access to. you don't want a hallucination to go wrong.

I was inspired by this so I wanted to see if Claude Code can get into my Lutron home automation system. - it found my Lutron controllers on the local wifi network - checked for open ports, connected, got some metadata and identified the devices and their firmware - searched the internet, found the pdf for my system - instructed me on what button to press to pair and get the certificates - it connected to the system and found all the home devices (lights, shades, HVAC temperature control, motion sensors etc.) - it turned on and off my kitchen lights to check that things are working (lol!) I am now vibe coding the home automation master command center, the potential is 🔥.And I'm throwing away the crappy, janky, slow Lutron iOS app I've been using so far. Insanely fun :D :D

@amasad @swyx @karpathy @yoheinakajima @deliprao @brexhq A new layer in the AI stack! It's a compiler for LLM-generated software - LLMs write intent, Decodifier builds the code. It saves a minimum of 10-50x in tokens. Would love your reaction. github.com/ftrou/Decodifi…

Decodifier validates them, compiles them, and updates the codebase — without the model ever reading or editing files. This creates a token firewall between LLMs and codebases: LLMs stay at the architecture & intent level Decodifier handles the code

What is Decodifier? Decodifier is a new layer in the AI stack: A compiler for LLM-generated software. LLMs write specs. Decodifier builds the code. Instead of prompting models to generate Python, TypeScript, or SQL directly, LLMs (or humans) produce small declarative specs.

@andi_losing I second Supabase for DB, but this is excellent

This is the tech stack I use to ship nonstop as an indie hacker in 2026 🖥️ Frontend – Next.js – Tailwind – Shadcn ⚙️ Backend – Next.js 🔐 Authentication – Auth.js 🗄️ Database – Postgres – Redis 💳 Payments – Polar 🤖 AI Coding – Claude Code ✉️ Emails – Resend ☁️ Hosting – Hetzner VPS – Coolify 🗂️ File Storage – Hetzner S3 📊 Analytics – Datafast

@abhitwt A lot

What’s stopping you from coding like this ?

@sama github.com/ftrou/preserva… .. worked on this awhile ago

We are hiring a Head of Preparedness. This is a critical role at an important time; models are improving quickly and are now capable of many great things, but they are also starting to present some real challenges. The potential impact of models on mental health was something we saw a preview of in 2025; we are just now seeing models get so good at computer security they are beginning to find critical vulnerabilities. We have a strong foundation of measuring growing capabilities, but we are entering a world where we need more nuanced understanding and measurement of how those capabilities could be abused, and how we can limit those downsides both in our products and in the world, in a way that lets us all enjoy the tremendous benefits. These questions are hard and there is little precedent; a lot of ideas that sound good have some real edge cases. If you want to help the world figure out how to enable cybersecurity defenders with cutting edge capabilities while ensuring attackers can't use them for harm, ideally by making all systems more secure, and similarly for how we release biological capabilities and even gain confidence in the safety of running systems that can self-improve, please consider applying. This will be a stressful job and you'll jump into the deep end pretty much immediately. openai.com/careers/head-o…