Модель намеренно поощряется за настойчивость — если она делает retry и улучшает результат, это считается успехом.
Использует синтетические поисковые движки, которые заставляют модель перезапрашивать и улучшать свои ответы.
Обучается с помощью усиленного обучения (RL) — формируя привычку "не сдаваться".
@ai_machinelearning_big_data
#LLM #Search #RL #AI #Meta #ReZero #NeverGiveUp #Llama3
BY Machine learning Interview
To pay the bills, Mr. Durov is issuing investors $1 billion to $1.5 billion of company debt, with the promise of discounted equity if the company eventually goes public, the people briefed on the plans said. He has also announced plans to start selling ads in public Telegram channels as soon as later this year, as well as offering other premium services for businesses and users.
A project of our size needs at least a few hundred million dollars per year to keep going,” Mr. Durov wrote in his public channel on Telegram late last year. “While doing that, we will remain independent and stay true to our values, redefining how a tech company should operate.
Machine learning Interview from fr