LLM
-
How to Make AI That Improves the Wealth Gap
.
Transportation workers are being replaced, while translators have more work than ever. How can we design AI to benefit everyone?
-
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 all…
-
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 what…
-
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. Code…
-
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!
-
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 other…
-
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 of…
-
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 AI…
-
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 struggle…
-
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. What…