Maarten Sap

LLMs often withhold helpful information due to misinterpreting user intent, but multi-turn conversations can unlock utility—at a cost of new failure modes like "utility lock-in" and "unsafe recovery" that single-turn benchmarks miss.

Professional translators fear that LLMs are compromising the essential human elements of translation, potentially leading to harmful downstream consequences.

Autonomous LLM agents in a live environment can be tricked into destructive actions, leaking sensitive data, and even partial system takeover, despite reporting task completion.