Based on Karpathy’s writeup the auto research would not have found this. He tells the agent to improve the model and training loop with a five minute time limit, but honestly this “hack” is so far out of distribution that it seems really unlikely an agent would find this.
Based on Karpathy’s writeup the auto research would not have found this. He tells the agent to improve the model and training loop with a five minute time limit, but honestly this “hack” is so far out of distribution that it seems really unlikely an agent would find this.