been building loopsmith: a mac TUI that watches your repos, figures out what you're working on, and runs autonomous loops to do it — Claude writes a PRD, Codex implements, Claude reviews, repeat until it passes.
the fun part: it's now built most of its own features.
1/ This is the full story of how I found a JupiterZ RFQ vulnerability, extracted ~$45k in a controlled white-hat test, returned the funds, and worked with the teams involved to get the issue fixed and safely back in production.
The One-Byte Heist 🧵
We ran the SpaceX $SPCX IPO through a multi-agent market simulation — thousands of AI agents playing retail, insiders, index funds, short sellers, and crypto traders.
We tested 4 scenarios. They all rhymed. 🧵
Net: structural wind is UP into ~Jul 7, danger builds AFTER.
Caveat: this is a sentiment simulation, not a price forecast — and not financial advice. But every scenario we ran told the same story. DYOR.
We ran the SpaceX $SPCX IPO through a multi-agent market simulation — thousands of AI agents playing retail, insiders, index funds, short sellers, and crypto traders.
We tested 4 scenarios. They all rhymed. 🧵
Systemic angle: a 4.3%-float, 95x-sales mega-cap forced into everyone's index funds means price is set by flows, not fundamentals. The real risk isn't day 1 — it's a de-rating at the unlocks dragging the indices.
Noticing the open source robotics space getting more traction. Not seeing a lot of chatter about security though. Makes sense considering how early we are, but curious is anyone already tackling security in this sector?
Your agent has no excuse now.
security-rig ships with a CLI + SKILL.md. Point Claude/Codex/Hermes at the repo and say:
“scan this for Mini Shai-Hulud compromise���
No installs. No sketchy payloads.
Static triage in Docker.
https://t.co/47JAYtiPru