
357. ChatGPT and the Dawn of Computerized Hyper-Intelligence | Brian Roemmele
The Jordan B. Peterson Podcast
**Use Triangulation to Get The Most Out of LLMs **
Correctly built super prompts can be up to 3000-2000 words/nTokenization limits prompt length/nProbing the model can reveal its contents/nAsking questions in multiple ways is effective with language models
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.