Skip to content
View bquast's full-sized avatar
👋
👋

Highlights

  • Pro

Block or report bquast

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
bquast/README.md

Bastiaan Quast

Current projects

  • autoresearch-mesa - an adaptation of Karpathy's autoresearch, in turn an OpenClaw 🦞 style AI agent to explore hyperparameters. Uses the python ABM framework mesa.
  • autoresearchABM - an adaptation of Karpathy's autoresearch, in turn an OpenClaw 🦞 style AI agent to explore hyperparameters. This framework is adapted to task the AI agent to fine-tune the parameters of an ABM model, such as as the epidemiological SIR recovery model. Custom-built ABM framework that runs headless, logs everything.
  • autoresearch-mesa-prompt - using the autoresearch paradigm to probe ABM models using the mesa framework, using only prompts in Claude web.

Pinned Loading

  1. autoresearch-mesa autoresearch-mesa Public

    Forked from karpathy/autoresearch

    autoresearch for ABM simulation parameter sweeps

    Python

  2. rnn rnn Public

    Recurrent Neural Networks in R

    R 77 27

  3. attention attention Public

    R package that implements a basic attention algorithm

    R 2

  4. HEtools HEtools Public

    Tools for Homomorphic Encryption in R

    R 1

  5. transformer transformer Public

    simple from-scratch implementation of the Transformer architecture in R

    R 1 1

  6. microgpt.R microgpt.R
    1
    # --- Dataset Setup ---
    2
    input_file <- "input.txt"
    3
    if (!file.exists(input_file)) {
    4
      names_url <- "https://raw.githubusercontent.com/karpathy/makemore/refs/heads/master/names.txt"
    5
      download.file(names_url, input_file)