LLM
-
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…
-
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 some…
-
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 capabilities…
-
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!
-
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 better…