Where answers come from

Some pages can ask a language model questions. Set this up once; your choice is remembered in this browser for the whole site.

Model source
Use another source instead

Smallest-to-largest weight downloads. Qwen3.5 0.8B is our starting choice for page Q&A. GPU estimates are not total RAM: leave room for the browser, context and temporary buffers. Hardware changes speed and capacity; answers still need checking.

Session-only loading avoids saving model weights, uses extra RAM and downloads again after unloading. Turn it off to save downloads. Delete-data-on-exit or private browsing may impose a much smaller storage limit than the displayed estimate.

You sign in on OpenRouter; it gives this page a key for your account.

A free account does not make every model free. Choose a model with a listed :free variant; merely adding that suffix does not create one. Check free-model availability and pricing.

Chat

AI assistant, not Shawn Hartsock. It does not speak for him.

Inspect the page excerpt

Up to 4,800 characters, not the whole site. Recent conversation turns are retained within the model’s context limit.

Ask about this page, or just say hello.

Ready when you are.

Not saved or uploaded automatically. Closing keeps this conversation in this tab; changing pages starts a new one. Model replies can be wrong.

Space-time tradeoff

Originally published .

My half of a chat conversation:

“In computer science, a space-time or time-memory tradeoff is a situation where the memory use can be reduced at the cost of slower program execution, or vice versa, the computation time can be reduced at the cost of increased memory use.”

From: http://en.wikipedia.org/wiki/Space-time_tradeoff

… so in a very general and theoretical sense… if there was enough ram on your system, your OS should put everything in RAM to make things faster… not just because Hard Drives are slow… but because it is faster to look up the answer to 32 billion divided by 8 than it is to compute 32 billion divided by 8. The more time it takes to compute an answer the smarter it is to save that answer so you can look it up later.

More RAM makes software many many times faster.

However, Database design teaches the exact opposite: only save that which you can’t compute, and save that information in the most terse compact form possible. Which is why database engines tend to do a lot of on-the-fly computation, caching, and indexing. The reason for this is that Databases are concerned with consistency and accuracy of data and that is easier to maintain for terse, tight, inter-related groupings of data without any redundancy.

Explore the map · Browse by topic and date