🛡 FOMO Firewall is live.
Real-time Solana exit-liquidity intelligence — powered by @birdeye_data.
Every trending token gets a TrapScore 0–100, so you see when smart money has already exited the pump.
You are not early. You are the trap.
🧵 features + links ↓
#BirdeyeAPI
A guy quit your company 14 days ago. He still has access to your code. He still pays for Slack. Nobody noticed.
I built something that finds this in 1.4 seconds. ↓
For every problem it finds, it writes:
• a Slack message to IT • a Jira ticket • an offboarding checklist
You read them, hit Approve. Done.
Every action gets a permanent receipt with a hash — auditors love it.
@karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer.
The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling.
We talk about what it means to build seriously in the agent era. Not just moving faster. Building new things, with new tools, while preserving the parts that still require human taste, judgment, and understanding.
I just finished creating a guide that connects NotebookLM + Antigravity
Spent 67 hours creating this system that turns your knowledge base into an AI agent that actually takes action
BONUS: Complete guide for building 10 workflows + copy-paste prompts
Like & Comment "FREE" and I'll DM it to you as fast as i can
Three products on one engine:
Copilot · revenue teams Receptionist · inbound calls Personal · the conversations that change your life
All open: https://t.co/cEDRzgH3FO
@elevenlabs + @vercel + @rendercom — the stack that made sub-second whispers possible. @paul_asjes@isnit0
Built Vought for the @elevenlabs hackathon.
It whispers what to say next — privately into your earbud, in your own cloned voice — at sub-second latency.
Live: https://t.co/VwtloXQSCg Code: https://t.co/cEDRzgH3FO
Used the full Speech Engine surface, not just TTS:
➤ speechEngine.attach() — STT+TTS+turn detection on one socket ➤ AbortSignal threaded through the LLM stream ➤ voices.add() — 30s clone ➤ retention_days = -1 — zero-retention
Real code: https://t.co/JNu4QJejgJ
Built solo, in 3 days , for the ElevenLabs hackathon. If this is the future or if it's the end of something, retweet — either way, people should see it. #ElevenHacks@paul_asjes@isnit0
I showed 5 people a demo of an AI that whispers in your AirPod during a live conversation. In your own cloned voice. Sub-second.
Three asked where to buy it. One asked if it's legal. One went quiet for a minute.
Here's what I showed them.
Live demo, no signup, runs in your browser: https://vought-web.vercel.appPut on headphones. Speak into the mic. The AI whispers back, in a cloned voice, in under · 500ms. Try the moment.