Aleksei Khvostov's picture
1

Aleksei Khvostov

ole-tail
ยท

AI & ML interests

Independent AI Safety Researcher. AI evaluation, agent safety, red teaming, mechanistic interpretability, and governance-inspired oversight experiments.

Recent Activity

liked a model about 16 hours ago
zai-org/GLM-5.2
updated a dataset 2 days ago
ole-tail/rusafetybench
updated a dataset 5 days ago
ole-tail/agentic-execution-guardrail-eval
View all activity

Organizations

None yet