You are viewing a single comment's thread from:

RE: LeoThread 2025-10-18 14-48

in LeoFinance2 months ago

Part 4/15:

Of particular importance was the Atari deep reinforcement learning effort in 2013—a significant early foray into agents that interact with environments. However, Karpathy views this as a misstep, especially for general intelligence, since game environments don't align well with real-world complexities. Instead, he advocates for agents that interact with actual digital environments, like web browsing, knowledge work, and coding, which provide richer representation and practical utility.


The Limitations of Early Agent Efforts