Skip to content
View edarsem's full-sized avatar

Highlights

  • Pro

Block or report edarsem

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 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
edarsem/README.md

I build stuff to learn and to actually use.

Personal projects

  • 🏃 training-os — my own training platform with a coach that actually sees my sessions. FastAPI backend, MCP-based LLM chat that can actually query my Strava data, reverse eng of Corros with TL/ATL/CTL/ACWR analytics. Born out of frustration of lack of integration between chatbots and physiologic data.
  • ♟️ chessformer — a transformer trained from scratch to play a human moves, not the best moves. Eventual goals: feeling bar instead of eval bar, cheating detection, player style imitation, clock-situation aware engine, beatable bots at every level. Currently 50M parameter model trained on 100M tokens (100k games, 6 epochs).

Stuff I've worked on

  • 🧠 ReWiSe — my MSc research at Mila / LAMA-WeST. Knowledge extraction from LLMs with relation-wise self-consistency. Won LM-KBC 2025.
  • 🎮 ConnectZero — self-play dynamics for RL agents on Connect 4.

Pinned Loading

  1. training-os training-os Public

    A personal agentic training coach : LLM coach using MCP tools to query your sessions, training load analytics (TL, ATL, CTL, ACWR), UI/UX with calendar and analysis hub, all with strava sync

    Python 1

  2. chessformer chessformer Public

    Building from scratch a transformer playing human chess. The eval bar doesn't show how the player feels, now it does.

    Python 3

  3. Lama-West/ReWiSe Lama-West/ReWiSe Public

    Python 2

  4. ConnectZero ConnectZero Public

    A project exploring self-play settings and agent performance in Connect 4.

    Jupyter Notebook 1