Stories by iamwil

Iterate, iterate, iterate your prompts

Grading scales matter for eval consistency

Building an Autotuned Kazoo [video]

Leverage Code for System Evals

Where is the sandbox in your code base?

Defining good metrics for LLM system evaluation

Defining good metrics for LLM system evaluation

Defining good metrics for LLM system evaluation

eBook on building LLM system evals

Visual programming should start in the debugger

Where is the sandbox in your code base?

Go from zero to building LLM evals zine

Illustrated Primer on LLM Evals

AI Interfaces

PaintsUndo: A Base Model of Drawing Behaviors in Digital Paintings

Zine on LLM Evals

Where is the sandbox in your code base?

Show HN: Zine on LLM Evals

QP-Tries

1
2
3
4
5
6
7
8
9
10