I’ve been thinking about this a lot: error handling, testing, caching, observability, … are going to be required in AI applications and we’ve already (kinda) figured it out for the web, so how can we transfer knowledge?
The new shift in Software 2.0* is uncertainty and that brings a whole new set of considerations.
Love it!
I’ve been thinking about this a lot: error handling, testing, caching, observability, … are going to be required in AI applications and we’ve already (kinda) figured it out for the web, so how can we transfer knowledge?
The new shift in Software 2.0* is uncertainty and that brings a whole new set of considerations.
So many interesting challenges to work on!
*: https://karpathy.medium.com/software-2-0-a64152b37c35