flâneur

On AutoGPT - LessWrong

lesswrong.com · 14,336 words · saved by 1 readers

The primary talk of the AI world recently is about AI agents (whether or not it includes the question of whether we can’t help but notice we are all going to die.) …

x On AutoGPT — LessWrong Chain-of-Thought Alignment GPT Language model cognitive architecture Threat Models (AI) AI Curated 248 On AutoGPT by Zvi 13th Apr 2023 Don't Worry About the Vase 25 min read 47 248 The primary talk of the AI world recently is about AI agents (whether or not it includes the question of whether we can’t help but notice we are all going to die.) The trigger for this was AutoGPT , now number one on GitHub, which allows you to turn GPT-4 (or GPT-3.5 for us clowns without proper access) into a prototype version of a self-directed agent. We also have a paper out this week whe

related reading