LLM

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…

9 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…

10 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…

10 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.…

10 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…

11 months ago

What are AI Agents? A Precise Answer

What are AI Agents? Although it seems every bit of software claims to be an agent, there are real agentic…

11 months ago

The Archive pt 3: Don’t Hack Away on Vibes Alone

Let's not hack away on The Archive on vibes alone; let's evaluate our code. Using Promptfoo!

11 months ago

Why Programming Benefits the Most from AI Assistance

There's a few reasons that programming is best suited to using AI, but mostly it is that AI is simply…

12 months ago

The Archive, Pt 2: Giant Vector Databases with Big GPUs

A naïve implementation of a vector database would take 190GB of system memory. We'll need to make several kinds of…

12 months ago

The Final Invention We Need

A matrix of numbers in an AI can create new knowledge, even though it was created from existing data. It…

12 months ago