| Website | https://phillipcarter.dev/ |
| GitHub | https://github.com/cartermp |
People are misunderstanding and misusing LLMs.
Their most considerable value is not what they "know" (i.e. the ability to [sometimes] answer questions) but rather their ability to reason about a given text.
With 32K tokens prompt size in GPT-4, the vast majority of work should be spent on filling this prompt with relevant context and designing the prompts to force AI to answer questions based on the prompt rather than its internal "knowledge".
> If you read this and want to keep seeing it, would you please add an emoji below?
yes, of course
Krzysztof Cieślak 💙💛
The Seven Voyages Of Steve