Build your own agents which are controlled by LLMs | Hacker News
Andrew Ng: State of AI Agents | LangChain Interrupt
youtube.com
3 days reading through the code of the paper that solved this, here are some notes:
- Long term interactions: the promise of LLM agents is to potentially run over weeks. A lot of the ideas in the paper tackle exactly this problem
- Memory: It’s easy to write down interactions of agents. But how do we track these over time? How do these change with ti... See more
- Long term interactions: the promise of LLM agents is to potentially run over weeks. A lot of the ideas in the paper tackle exactly this problem
- Memory: It’s easy to write down interactions of agents. But how do we track these over time? How do these change with ti... See more
Sanyam Bhutani • Tweet
An LLM is trained by allowing it to adjust the connections in its neural network until it reliably gives good answers, a process that Hinton compared to “parenting for a supernaturally precocious child.” But because AI can “know” vastly more than we can, and “thinks” much faster, Hinton concludes that it might ultimately supplant us: “It’s quite co... See more
Philip Ball • AI Is the Black Mirror
