Walker Miller

Walker Miller

Aug 9

Designing tools an LLM won't misuse

#tooldesign #functioncalling #schemas #reliability

7 min read

Walker Miller

Aug 9

Debugging a failed agent run costs more than the run itself

#cost #failuremodes #observability #reliability

6 min read

Walker Miller

Aug 9

Best-of-N is prepaid retries: the cost math of racing parallel attempts

#retries #cost #latency #failuremodes

5 min read

Walker Miller

Aug 9

Your token bill is the cheap part: dimensioning the real cost of an agent

#cost #latency #tokens #operations

7 min read

Walker Miller

Aug 8

The context window is a cache, not a memory

#contextengineering #contextwindow #memory #cost

8 min read

Walker Miller

Aug 8

Context window sizing for fine-tuning: how long should your training examples be?

#finetuning #contextengineering #training #cost

5 min read

Walker Miller

Aug 7

Context contamination: why retrying the same prompt makes it worse

#contextengineering #failuremodes #retries #reliability

6 min read

Walker Miller

Aug 7

Compaction is a lossy operation

#contextengineering #memory #compaction #reliability

5 min read

Walker Miller

Aug 6

Cheap first, smart later: model routing that cuts cost without cutting quality

#cost #agentarchitectures #modelrouting #reliability

6 min read

DEV Community

Badges

Writing Debut

Designing tools an LLM won't misuse

Debugging a failed agent run costs more than the run itself

Best-of-N is prepaid retries: the cost math of racing parallel attempts

Your token bill is the cheap part: dimensioning the real cost of an agent

The context window is a cache, not a memory

Context window sizing for fine-tuning: how long should your training examples be?

Context contamination: why retrying the same prompt makes it worse

Compaction is a lossy operation

Cheap first, smart later: model routing that cuts cost without cutting quality