I've been in crypto for over 10 years and I’ve Never been hacked. Perfect OpSec record.
Yesterday, my wallet was drained by a malicious @cursor_ai extension for the first time.
If it can happen to me, it can happen to you. Here’s a full breakdown. 🧵👇
Huge thanks to all the open source projects that've made a lot of the tech we rely on in the world possible:
Linux
Git
FFmpeg
PyTorch & TensorFlow
Apache & Nginx
MySQL, PostgreSQL, SQLite
Chromium & Firefox
GCC & LLVM
Docker & Kubernetes
Also, all the open-weight LLMs... and all the programming language interpreters, compilers, and frameworks.
I can list 100+ more "niche" open source projects I've used & loved (e.g., OpenCV ❤️). But I just wanted to give a continued big thank you to the open source community for everything you do for humanity 🙏
trader just bagged $1.33m in 7 days on hyperliquid while someone's running $93m long at 25x
platform already eating 36% of binance's open interest. $12.1b total positions open
traders know where the real liquidity is
Sharing some quick personal learnings from building AI agents so far, and why frameworks like Eliza are useful.
I've mostly been building AI agents from scratch so far, not for any particular reason other than I enjoy understanding the fundamentals of things.
But once you reach a certain level of complexity in your agent(s), where you need stuff like:
· Interesting characters & responses
· Agent memory and search/retrieval system
· Real-time data from multiple sources
· Consistent agent personality across multiple platforms
· Standard way for agents to communicate
Building out the agent yourself becomes a lot of work with these features. I have no problem with the work, but it does feel like reinventing the wheel of what's already been built.
Frameworks like Eliza offer all of this out of the box and are built through the collaboration of hundreds of developers (meaning it's likely higher quality than building it yourself).
Eliza provides these core essential pieces for your agent and is highly extensible for you to build custom behaviours for the agent.
So while I learned a lot by experimenting with building agents from scratch, I now see a tonne of value in why these frameworks exist.
And I'll likely be creating some tutorials on Eliza soon!