MemCast
MemCast / episode / insight
Scaffolding around models gives diminishing returns as model capabilities jump
  • Adding elaborate pipelines can improve performance 10‑20 %.
  • However, a newer model release often eclipses those gains entirely.
  • Therefore, investing heavily in scaffolding can be wasteful.
  • The team prefers to wait for the next model and keep the system lightweight.
  • This philosophy reduces technical debt and speeds up iteration.
Boris ChernyLenny's Podcast01:05:38

Supporting quotes

Scaffolding can improve performance 10‑20 % but gets wiped out by the next model. Boris Cherny
We should wait for the next model rather than over‑optimizing now. Boris Cherny

From this concept

The Bitter Lesson: General vs Specialized Models

Across AI research, broader, more general models consistently outperform narrow, task‑specific ones. Anthropic embraces this by betting on future, larger models rather than fine‑tuning current versions.

View full episode →

Similar insights