AI Release 📌 Let's discuss: YandexGPT looped for 37 minutes and burned 300,000 tokens without result. We set YandexGPT on a

AI Release 📌 Let's discuss: YandexGPT looped for 37 minutes and burned 300,000 tokens without result. We set YandexGPT on a real agentic task — and the model entered an infinite loop: 295 repeated tool calls, 296 context rebuilds, 37 minutes and ~300,000 tokens. Useful answer — zero, stopped manually. The main question: the service has no protection against its own looping, and billing is running for