Skip to content
View arpjw's full-sized avatar
⚙️
⚙️

Organizations

@Laplace-AI-Research

Block or report arpjw

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
arpjw/README.md

what's up 👋🏽

intro: i'm arya, a 20-year-old researcher interested in machine learning, reward hacking, and crypto.

now: building laplace research and probably experimenting with something I saw on X this week.

Pinned Loading

  1. Laplace-AI-Research/tarot-draw-8b Laplace-AI-Research/tarot-draw-8b Public

    Tarot-Draw 8B, a calibrated no-retrieval probability estimator for binary events.

    Python

  2. reward-function reward-function Public

    Experiments with reward functions: derivations, audited scientific records, frozen source and CPU reproduction

    Python

  3. grokking grokking Public

    Replicating grokking (delayed generalization) in a small transformer trained on modular arithmetic

    Python

  4. velocity velocity Public

    Prediction market velocity signals mapped to equity positions via Robinhood's agentic trading MCP

    Python 2