Skip to content
View belumume's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report belumume

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. 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
belumume/README.md

Ubaid

I tinker with AI, and I try not to accrue too much cognitive debt.


Projects

  • dlai-roadmap: a study-plan generator for DeepLearning.AI's 130-plus courses. Since February 2026 it has had more than 1,100 visits, two-thirds of them from the DeepLearning.AI community forum, and over half of those visits produced a study plan. Try it
  • claude-skills: a collection of Claude Code skills (46 stars).

About

CS.

I beta-test courses at DeepLearning.AI, and spend time on agentic systems and AI safety.


GitHub Stats

Total Stars

GitHub Streak

Profile Views

Pinned Loading

  1. proof-jenga proof-jenga Public

    Pull ideas out of Mathlib and see which Lean proofs of infinitely many primes fall. Every dependency is computed from kernel terms.

    Lean 1

  2. cisfalcon cisfalcon Public

    A live pre-synthesis specificity gate for AI-designed enhancers: a frozen external measured-activity model plus a multi-agent Claude verifier. Cross-lab AUROC 0.80 on 93,435 independent designs.

    Python 2

  3. zeroclaw-solana zeroclaw-solana Public

    Self-hosted deny-by-default Solana agent: device-signed DePIN feed, x402 earning-node, merchant terminal. On-chain program bounds the agent.

    Python 1