LLM

The Unprompting Notecard: Simple Advice for Using AI

You don't need to learn prompt engineering to get incredible results from AI. A few short tips and practice are…

3 months ago

Why Chat is the Best (and Worst) Interface to AI

Why do most AI products use chat as their interface? Because conversation allows us to more carefully direct it to…

4 months ago

Human-Orchestrated Agents for Better Autonomy

AI cannot operate on its own for very long. But with a human-in-the-loop, we can execute long and useful plans.…

4 months ago

The Hubris of Scale: A Lesson From Junkmail Detection

Scale won't solve every problem, and won't even solve the main problem of today's AI!

4 months ago

Beyond Prompting: The Other Ways to Influence LLM output

Beyond prompting, learn every other thing that you can do to an LLM, like the sampler, runtime modification, optimization, and…

5 months ago

Why Social Media Search is So Bad, and How to Fix It

Social media search is terrible because it's a harder problem than web search. Yet I implemented my own search engine…

5 months ago

The Magic Promise of Inference-Time Compute

How much is it worth to solve humanity's biggest problems? If only there was someone to pay! Agents may enable…

5 months ago

AI’s Hardest Problem: Teaching Us to Use It Better

Not only is AI smarter than us in most ways, but it is so much smarter than us that we…

6 months ago

The Tyranny of Chat Interfaces to LLMs

So much of our interaction with LLMs is via a singular chat box. It doesn't have to be that way.…

6 months ago

AI Videocasts and Digging Your Way Out of a Hole

AI gets into a rut as you talk longer, as I found out when I worked with ChatGPT to debug…

6 months ago