Dmitrii Kharlapenko retweeted
NEW ⚡: We let Opus 5.5 run an AI company for seven weeks.
We gave it an HF account (Horizon-Labs) and compute, and asked it to earn real adoption by creating useful models.
It reached 50k downloads and its models are being used in more than 100 GitHub projects.
Dmitrii Kharlapenko retweeted
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 ↓
Dmitrii Kharlapenko retweeted
🧵1/6 SAEs have become a staple of LLM interpretability, but what if we applied them to image generation models?
My recent paper with @dmhook, @Yixiong_Hao, @afterlxss, @Sheikheddy, and @ArthurConmy adapts SAEs to understand the SOTA diffusion transformer FLUX.1 ⬇️
Dmitrii Kharlapenko retweeted
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…







