Bits of Logic

Designing in Dialogue

How the Logic team uses semantic design tokens to build features at scale

Nov 18 • joe

March 2025

When AI Writes the Code, What Do Programmers Do?

AI's Rapid Progress in Coding

Mar 6 • Steve Krenzel

1

February 2025

Predicting the Super Bowl with LLMs

Using LLMs to pick NFL winners better than 94.5% of humans.

Feb 7 • Steve Krenzel

January 2025

The AI Programming Paradox

Revisiting Paul Graham's 2004 "Python Paradox" in the age of AI.

Jan 27 • Steve Krenzel

3

Baby, It’s Warm Inside

Temperature and Large Language Models

Jan 2 • Jess Garms

2

It's beginning to look a lot more readable.

LLMs will usually perform better with human-friendly inputs and outputs.

Jan 1 • Mark Golazeski

December 2024

Getting gpt-4o-mini to perform like gpt-4o

Few-Shot Knowledge Distillation

Dec 30, 2024 • Steve Krenzel

6

1

Making a List and Checking It Twice

Structured Output with LLMs

Dec 30, 2024 • Jess Garms

The Perfect Holiday Cookie

The role of embeddings and rerankers in semantic retrieval.

Dec 29, 2024 • Steve Krenzel

MCP: Merry Christmas Protocol? No, it's Anthropic's Model Context Protocol!

How to use Claude to control your computer!

Dec 28, 2024 • Martha Schumann

He Slacks You When You’re Sleeping, He Slacks When You’re Awake

Using LLMs to drive your runbook in Slack

Dec 27, 2024 • Mark Golazeski

Santa Paws Is Coming to Town

Generating high-quality photos of our favorite fluffy friends.

Dec 24, 2024 • Steve Krenzel