HN user

laser9

65 karma
Posts1
Comments7
View on HN

This is the garbage in, garbage out principle in action. The utility of a model is bottlenecked by its inputs. The more garbage you have, the more likely hallucinations will occur.

Good read but I wouldn't fully extend the garbage in, garbage out principle to the LLMs. These massive LLMs are trained on internet-scale data, which includes a significant amount of garbage, and still do pretty good. Hallucinations are due to missing or misleading context than from the noise alone. Tech debt heavy code bases though unstructured still provides information-rich context.

A good Friday morning laugh! I think the tiles are not just honest, they are brutally honest. Some of my fav ones:

- Amazon finally adds a feature that has been standard since 2005

- Texas accidentally does something good for privacy

Would it possible to add a feature where hovering over a title displays the original title?