Shawn Hartsock

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

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.

  




  

    

      

  

    
Optional experiments

    
Labs

    
A place to try things. Each lab has its own workbench; choose the experiment you want to explore.

    
For the guided curriculum, head to Courses. These labs are side experiments, not required lessons.

  


  

    

      
Conversation & page Q&A

      
Browser chat

      
The original chat lab: six model cards, a conversation pane and smoke tests. Say hello, add a public article as context, and see what a small model can answer on your hardware.

      
Open browser chat →

    

    

      
Next-token experiment

      
Model comparison

      
Give three models the same opening words. Compare their continuations and next-token odds side by side, starting with a recorded trial from Session 3.

      
Open model comparison →

    

  

  
Opening a lab does not download a model. Live experiments load only when you ask them to; hardware, memory and browser settings affect the results.