Skip to content
View ayush-alag's full-sized avatar
4 followers · 3 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2

Block or report ayush-alag

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
ayush-alag/README.md

👋 Hi, I’m Ayush!

👀 I’m interested in compound AI systems, meta & reinforcement learning, trading systems, and hip hop.

🌱 I’m currently learning how to play tennis and whistle

📫 Shoot me an email at aalag@stanford.edu!

Previously, I was a Software Developer at Five Rings Capital in NYC for 2 years, a CS master's student at Stanford, and a CS undergrad at Princeton.

Pinned Loading

  1. Cabo_RL Cabo_RL Public

    Simulation + Policy framework for Cabo card game; outperforms naive player

    Python 1

  2. gpt2_xl_from_scratch gpt2_xl_from_scratch Public

    Transformer built from raw Pytorch + DDP, optimizer sharding + data pipelines + SFT/GRPO post-training

    Python

  3. DataAuditing DataAuditing Public

    ML Calibration Model w/GANs to audit ML models

    Jupyter Notebook

  4. tscs_synthetic_data_curriculum_rl tscs_synthetic_data_curriculum_rl Public

    Two-staged synthetic data + curriculum learning with SFT and RLOO

    Python

  5. model_selection_sandbox model_selection_sandbox Public

    Remote LM choosing local LMs prior to query

    Python

  6. rjintu/TigerLink rjintu/TigerLink Public

    HTML 4