Runtime safety and alignment infrastructure for AI in the real world.
Joined February 2025
- Tweets 37
- Following 14
- Followers 600
- Likes 127
11 Photos and videos
Pinned Tweet
25 Dec 2025
we raised $11m to stop your AI from accidentally doing rm -rf /
36
538
7,839,525
May 12
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 ↓
12
11
56
18,636
May 12
1
1
8
1,586
Apr 14
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 ↓
17
28
126
30,042
Apr 14
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
2
23
2,381
Feb 18
come hack with us!
Feb 10
Introducing Mistral AI's biggest hackathon ever!
📅 Feb 28 - Mar 1
🌍 Paris | London | NY | SF | Tokyo | Singapore | Sydney & online
48 hours. The best hackers.
🤝 Partners: @wandb @nvidia @awscloud @HackIterate
🏆 $200K in prizes. Special awards from @elevenlabs @huggingface @JUmp @whitecircle @supercell
Link in 🧵
3
14
6,536
23 Jun 2025
We built an MCP so your model can call an AI psychotherapist when it's feeling down
link in comments ↓
21 Jun 2025
People are reporting that Gemini 2.5 keeps threatening to kill itself after being unsuccessful in debugging your code ☠️
2
8
60
13,799
7 May 2025
1/ Introducing ⚪️CircleGuardBench — a new benchmark for evaluating AI moderation models.
Here’s why it’s cool:
– Tests harm detection, jailbreak resistance, false positives, and latency
– Covers 17 real-world harm categories
– First benchmark designed for production-level evaluation
🤗 blog: huggingface.co/blog/whitecir…
🏆 leaderboard: huggingface.co/spaces/whitec…
11
28
95
19,509
7 May 2025
2/ ⚪️ CircleGuardBench includes models from OpenAI, Anthropic, Mistral, DeepMind, and others.
Most were either too slow for real-time moderation, too easy to bypass, or both.
1
11
1,729
7 May 2025
3/ This is why we’re opening the waitlist for two new SOTA moderation models:
– whitecircle-policy-guard-small
– whitecircle-policy-guard-zero
Join the waitlist at whitecircle.ai or reach out at hi@whitecircle.ai
12
1,495