arxiv:2509.18058
Evgenii Kortukov
kortukov
AI & ML interests
LLM interpretability, AI safety
Recent Activity
updated a dataset 4 days ago
honeypot-redteam/strategic_lies updated a dataset 9 days ago
future-probes/per_sentence_probabilities published a dataset 9 days ago
future-probes/per_sentence_probabilities