We have coworkers, partners, and other people we know and interact with who are sentient. They pass the Turing test, they are “AGI,” and yet: we still have a hard time conveying instructions, ideas, and concepts among each other.
Det är rimligt att tro att context engineering kommer fortsätta vara en grej även när modellerna blir bättre. Vi har ju fortfarande problem att göra oss förstådda i mellanmänsklig kommunikation.
Long contexts let you fit in more information, but they also let you fit in more errors.
Thankfully, we’ve developed a pretty good toolbox. Surprisingly, even as new challenges have emerged (we’ll get to those in a minute), this set of tools has remained the same.
These six of them.
Vidare till källan: dbreunig.com