optimization

Mar 15

Optimizing /start: The Fifteen-Step State Machine

Adventures in Claude

The /start command is a 1,400 line markdown state machine with 15 numbered steps that takes a Linear ticket ID and produces a ready-to-test implementation. I type /start AUTM-123 and walk away. When I come back, there’s a feature branch, an implementation plan posted to Linear, working code, and...

performance optimization workflow slash-commands context-window

Mar 14

One Million Tokens and Four Commands to Rewrite

Adventures in Claude

I’ve spent the few months building (and endlessly iterating to improve) four markdown state machines - /start , /commit , /staging, and /production - that together manage my development lifecycle. They total about 4,700 lines of structured decision trees. I wrote about the first two already. Now...

optimization workflow slash-commands context-window

Nov 14 2023

Suboptimization as a Healthcare Strategy

Bryan Vartabedian

Optimization has become a defining feature of modern healthcare. We optimize, review, tweak, and measure our systems and ourselves against a super-optimized standard. Better, faster, safer, more productive, efficient and effective. We’re always looking for improvement. And for good reason. 21st...

leadership productivity optimization hospitals

Jun 20 2022

Empirical risk minimization is not learning : A mathematical definition of learning and re-understanding of overfitting and Occam's razor in machine learning

msuzen

Simionescu Function (Wikipedia)PreambleThe holy grail of machine learning appears to be the empirical risk minimisation. However, on the contrary to general dogma,  the primary objective of machine learning is not risk minimisation per se but mimicking human or animal learning. Empirical risk...

risk machine learning deep learning supervised learning overfitting occam representation learning optimization empirical risk minimisation

May 23 2022

[EN] Prime numbers and speed

Sebastian Mestre

code, pre { color: #125; background: #ddd; border-radius: 2px; border-bottom: 1px solid #ccc; font-size: 0.8em; line-height: 150%; } pre { padding: 1em; tab-size: 4; } code { padding-left: 0.5ch; padding-right: 0.5ch; } pre code { border: none; } p { color: #111; }...

c++ debugging optimization competitive-programming

Mar 20 2021

Computable function analogs of natural learning and intelligence may not exist

msuzen

Optimal learning : Meta-optimization Many papers directly equate “machine” learning problem, algorithmic learning oppose to human or animal learning, with optimisation problem. Unfortunately, contrary to common belief  machine learning is not an optimisation problem. For example, take optimal...

machine learning data science optimization evalutionary computation

Mar 18 2019

[EN] The Jarvis March

Sebastian Mestre

code, pre { color: #125; background: #ddd; border-radius: 2px; border-bottom: 1px solid #ccc; font-size: 0.8em; line-height: 150%; } pre { padding: 1em; tab-size: 4; } code { padding-left: 0.5ch; padding-right: 0.5ch; } pre code { border: none; } p { color: #111; }...

c++ optimization