Sitemap - 2024 - The AI Frontier
AI lets you scalably do things that don't scale
Compound AI, test-time compute, and wasting your users’ time
Throw more AI at your problems
Customers want more AI, not better AI
AI companies should be AI-first
AI workers will ignore your Slack messages too
AI products should be built for human coworkers
In defense of vibes-based evaluations
There's no silver bullet in AI
OpenAI is too cheap to beat (redux)
AI applications are more than an LLM
AI is breadth-first, not depth-first
AI news roundup: You see what you want to see
How to build your first LLM evaluation
Open LLMs don’t need to beat OpenAI
AI must be more than a checkbox
How to talk to someone who doesn't trust AI
Lessons from customer evaluations of an AI product
You can't build a moat with AI
We need better LLM evaluations
RunLLM: The custom assistant for developer tools
Untangling concerns about consolidation in AI
Don't build your application on a single LLM call
There's more to LLMs than chat
LLMs are the variable interest credit card of tech debt
An introduction to evaluating LLMs
Prospecting in the AI Gold Rush