Skip to content
View wassname's full-sized avatar
🙃
🙃
328 followers · 189 following
  • I'm just a guy who likes to machine learn
  • IAU #90377 (Sedna), IAU #137924 (2000 BD19), IAU #85770 (1998 UP1), IAU #66063 (1998 RO1), and minor planet 1992 TY₁. from 2025 Feb 25.
  • X @wassname
  • LinkedIn in/mclark52

Achievements

Achievement: QuickdrawAchievement: Starstruckx3Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: QuickdrawAchievement: Starstruckx3Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Organizations

@pmlg @makehuman-js @3springs

Block or report wassname

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wassname/README.md

I'm just a guy who likes to machine learn. I want the good ending not the bad one.

Projects:

Work on alignment of LLM's:

Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card

Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card

Readme Card Readme Card

Experiments on World Models:

Readme Card Readme Card

Experiments on timeseries and spatial data:

Readme Card Readme Card Readme Card Readme Card Readme Card

Misc:

Readme Card Readme Card Readme Card Readme Card

Readme Card

Elsewhere:

Lol

STOP DOING MATH!

Gists

Gists: https://gist.github.com/wassname/public

Pinned Loading

  1. attentive-neural-processes attentive-neural-processes Public

    implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)

    Jupyter Notebook 99 23

  2. makehuman-js/makehuman-js makehuman-js/makehuman-js Public

    A library to build 3D human characters in the browser

    JavaScript 314 75

  3. world-models-sonic-pytorch world-models-sonic-pytorch Public archive

    Attempt at reinforcement learning with curiosity for Sonic the Hedgehog games. Number 149 on OpenAI retro contest leaderboard, but more work needed

    Jupyter Notebook 32 3

  4. It turns out LLM's can generate the ... It turns out LLM's can generate the STOP DOING MATH meme https://knowyourmeme.com/memes/stop-doing-math
    1 
    
              
    
              
    
                2
                
    **STOP DOING MATH**
    
              
    
              
    
                3
                
    
              
    
              
    
                4
                
    - NUMBERS WERE NOT SUPPOSED TO BE GIVEN NAMES
    
              
    
              
    
                5
                
    - YEARS OF COUNTING yet NO REAL-WORLD USE FOUND for going higher than your FINGERS
    
              
    
          
    
    
    
  
    

    5. 

      
  5. 
  
    
    
    
      
    
        
    
            
          open_pref_eval  open_pref_eval          Public
        
    
      
    


      
    
        Hackable, simple, llm evals on preference datasets
      
    

      
    
          
  
  Python


          
            
    

            2
          
      
    
    
    
  
    

    6.