Comment by andriy_koval
9 hours ago
> Today my "coding" sessions often enough begin with real life problems
intuition is that your sessions consists of 10% of domain related reasoning, and 90% of code plumbing. Those 90% could be moved to cheap and efficient specialized and focused model.
But that 10% is the most important part! Getting the plumbing wrong means you might have bugs or your code is brittle. Getting the domain-specific business logic wrong means your product doesn't fundamentally solve the correct problem.
[dead]
Possibly! It's just hard to reason about from the outside. When does the model benefit from all the ambient knowledge? Idk.
Regardless, it's fairly obvious to me that none of what I do now will require "frontier models" for much longer. Models are getting better more quickly than my problems are getting harder.