White Circle

Runtime safety and alignment infrastructure for AI in the real world.

[White Circle @whitecircle]

we raised $11m to stop your AI from accidentally doing rm -rf /

[White Circle @whitecircle]

@zeeg 🤍🤍🤍

[White Circle @whitecircle]

@nikitaandersso3 @mixedenn 🤍

[White Circle @whitecircle]

@DynamicWebPaige 🤍🤍🤍

[White Circle @whitecircle]

@gerund_os ⚪⚪⚪

[White Circle @whitecircle]

@bensicard 🤍🤍🤍

[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 ↓

[White Circle @whitecircle]

@Igralino

[White Circle @whitecircle]

@karp_e_ 🤍🤍🤍

[White Circle @whitecircle]

https://t.co/qUEaZp8Nir

[White Circle @whitecircle]

@ironcarbs 🩶

[White Circle @whitecircle]

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 ↓

[White Circle @whitecircle]

@satpugnet thx so much! 🩶

[White Circle @whitecircle]

@nikitaandersso3 🤍

[White Circle @whitecircle]

@ednevsky it's a very bad day to be russian obese atheist with no phone

[White Circle @whitecircle]

@JulienBlanchon true! v interesting idea

[White Circle @whitecircle]

@nikitaandersso3 🤍

[White Circle @whitecircle]

@JulienBlanchon @grok how do you feel re this

[White Circle @whitecircle]

@amaanbuilds v interesting!

[White Circle @whitecircle]

@Thom_Wolf thx Thom ⚪⚪⚪

[White Circle @whitecircle]

@frankterpo ⚪

[White Circle @whitecircle]

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 https://t.co/ruBnNTF1qU

[White Circle @whitecircle]

Far-right is targeted far more than anyone else