Dan Corin

Chatbots are not input validation

Stateful Agent Collaboration

Externalize Your Thought Process

Personal Software

Stateful Agents and Basic Memory

Director, Not Performer

I've Stopped Learning Programming Languages

Why Write

Year in Review: 2025

Images as Context

On Writing, Speaking and Thinking

Running a Mile with LLMs

Migrating To Astro

A short, fast rollercoaster

Find the Groove

Using Checkpoints with Coding Agents

State Of Code Agents - July 2025

Agents can make progress independently, but they also make messes

Gemini Hidden Reasoning

The performance costs of thinking and provider defaults

A few strategies to make LLMs useful for you

Agent Coding Strategies

Who Finds LLMs Useful and Why

Create a Link Blog

LLM Chat UI Concepts

A few concepts for LLM chat UIs

Models as Force Multipliers and their Limits in Software Development

You need to use models to build software to really understand their limits

Vibe Coding in early 2025

Goose as a Task Runner

Developing a Mental Model for using Models

Document Citations

Using Claude Citations to annotate the sources for document Q&A

Zoomable Document

Zooming in and out of a document to view levels of detail, like a map for content

LLM Conversation Branching

Visualizing and navigating branched conversations with LLMs and embeddings

The Unreasonable Effectiveness of Generating UI with React and Tailwind

Writing React/Tailwind with LLMs is effortless

Year in Review: 2024

Challenges Building an Electron App

Conversation Branching

Models Writing About Coding With Models

Language model random number generator

Claude 3.5 Sonnet Connections Evals

VLMs Hallucinate

Structured Output, Functions and Prompting

VLM data extraction with Protobufs

Making Your Vision Real with Models

VLMs aren't blind

Challenges and Opportunities of the Impact of Language Models on Software Engineering

Claude Artifacts

Claude 3.5 Sonnet Codes Really Well

Language model-based aggregators

Learning How to Learn

Switching From Pocket to Raindrop for bookmarks

Evals: unit testing for language models

Language Model Streaming With SSE

Sandboxed Python Environment

Fine-tuning gpt-3.5-turbo to learn to play "Connections"

2023 Review

End of year review

Embracing Failure in Software Development

Exploring the Importance of Embracing Failure in Software Development and the Value of Learning from Mistakes

Promptfoo and standardizing output structure across models

Using Marvin for Structured Data Extraction

OpenAI Function Calling

Tradeoffs of Using a Cache at Scale

Protobuf contracts with LLMs

Input data schemas and token efficiency

Figuring out how to use LLMs in production

Code needs structure output

Shaping LLM Responses

Auto-GPT

Experimenting with Auto-GPT

Using GPT-3.5 to Quickly Generate and Run Shell Commands

Future of Personal Knowledge

Nix and direnv

GPT Prompt Attack

Beating Prompt Injection with Focus

Attempts to thwart prompt injection

LLM Prompt Injection

Clean Python Setup

No frills Python projects

Language model schema extraction and object generation

Playing with Language Models

Ways to improve your team's code quality

Pipelines and your Unix toolbox

Go and UNIX files

Debugging go code with delve

Go scope

Tracking a call stack in Go with context

Go channels

Go closures

Custom Markdown rendering

Creating a Go module

Quickstart `supervisor` guide

Querying S3 with Presto

Creating a Presto Cluster

Creating an Elixir module

Git aliases

PySpark dependencies

Python Fabric

Bash SSH host management

Managing bash aliases

Elixir binary search

Hello

qc: quick calculator