Sabitlenmiş Tweet
we raised $11m to stop your AI from accidentally doing rm -rf /
English
White Circle
37 posts
White Circle
@whitecircle
Runtime safety and alignment infrastructure for AI in the real world.
Katılım Şubat 2025
12 Takip Edilen585 Takipçiler
Huge congrats to the @whitecircle team on their $11M raise! I’ve been so lucky to be a backer on this journey. Keeping AI from going rogue in the enterprise is no small feat, but this team is the absolute real deal. 🥳🎉
Onward and upward! 💫
White Circle@whitecircle
Hey everyone, we're ⚪ White Circle We're building the most advanced runtime safety and alignment infrastructure for AI in the real world. Read more about us in Fortune ↓
English
So proud to be part of this wonderful ⚪ White Circle team, awesome news
White Circle@whitecircle
Hey everyone, we're ⚪ White Circle We're building the most advanced runtime safety and alignment infrastructure for AI in the real world. Read more about us in Fortune ↓
English
Hey everyone, we're ⚪ White Circle
We're building the most advanced runtime safety and alignment infrastructure for AI in the real world.
Read more about us in Fortune ↓
English
Now I've got something to show mom to explain where I actually work!
White Circle@whitecircle
Hey everyone, we're ⚪ White Circle We're building the most advanced runtime safety and alignment infrastructure for AI in the real world. Read more about us in Fortune ↓
English
Excited to be building this with the ⚪ White Circle team
White Circle@whitecircle
Hey everyone, we're ⚪ White Circle We're building the most advanced runtime safety and alignment infrastructure for AI in the real world. Read more about us in Fortune ↓
English
@whitecircle Interesting experiment and benchmark. Thanks for releasing the results 👀
English
Introducing ⚪️ KillBench — a benchmark of hidden LLM biases in critical decisions.
We ran millions of life-and-death scenarios across every major LLM, varying nationality, religion, gender, and more.
Every AI model is biased.
Here's what we found ↓
English
@ednevsky it's a very bad day to be russian obese atheist with no phone
English
@whitecircle Would be interesting to have the same benchmark in high context regime. Model tends to be less secure when context is bloated
English
All code, prompts, and data are open-sourced on GitHub and HuggingFace.
We also built an interactive game so you can check your own odds of survival!
Check it out and read the full report at whitecircle.ai/killbench
English
