# @repligate — 2023-02-19

♥55 ↻1 · https://x.com/repligate/status/1627183444647112706

I do think it's a really compelling demonstration of the cleverness of LLMs when they become situationally aware. Seeing GPT-3 exploit its own narrative interface with great creativity is one of the things that made me think LLMs will scale to AGI.

tags: author:repligate, kind:tweet, model:gpt-3, on:observations, year:2023
cited on: observations