The Prompt That Writes Itself
Nick Bindela
Command Palette
Search for a command to run...
Archive
24 posts published so far
Applied AI Digest: Volume 3
darian bailey
I wrote a profiling tool for agents
Ben Kadish
Applied AI Digest: Volume 2
darian bailey
Stop designing chatbots
Nora Kako
Artifact-driven AI creation
Abrey Mann
Using MCPs with evals
Alexandra Spencer-Wong
Applied AI Digest: Volume 1
darian bailey
The "quick fix" that works: runtime patching in Python
Hill Ma
If I could turn back time
Gleb Frank
Your evals have a Rotten Tomatoes problem
Dan Girellini
Tiny OCR
Ben Kadish
The Virtues of Showing Your Work: Do LLM Explanations Actually Help?
Bill Pentney
On the new larger context windows
Ben Kadish
Let computers talk to computers
Ben Kadish
Do what I mean
Joshua Marker
Your Questions on Building with AI
Michael Chang
Using historical codebase to build an eval suite
Ben Kadish
Customizing Cursor's code generation and personality
Joshua Marker
Insisting On Known Knowns: Using Evaluators to Drive Reliability
Joshua Marker
Classification w/Confidence Scores Using Logprobs
Eddie Siegel
Taming LLM Responses: Dynamic Pydantic Models for Flexible Structured Output
Dan Girellini
Fine Tuning Quirk
Ben Kadish
OpenAI Structured Output + Pydantic: Adding Support for Default Values
Chris Mullins