A reinforcement learning run of the Llama 3.2 1B model on the Lab platform finished in under 30 minutes for less than $1 in credits
Screenshots posted by Kalomaze and Andrew Drozdov showed the results.
——0——
Screenshots posted by Kalomaze and Andrew Drozdov showed the results.
Positive users congratulated Kalomaze on his featured appearance in the AI Overview section of a dark UI screenshot, while negative users accused him of stolen valor or mocked the recognition with dismissive jokes.
6 comments with sentiment.