Skip to content
View lenamonj's full-sized avatar
🎯
Focusing
🎯
Focusing
5 followers · 14 following

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Block or report lenamonj

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
lenamonj/README.md

Jeff Lenamon

I build loops that are hard to fool.

Jeffy Loop is a verification harness for Claude Code. It audits a repo, fixes one thing, proves the fix, commits, and goes again until a fresh audit is clean and a second agent signs off. The model writes the patch. The loop decides whether to believe it. Maintainers at NVIDIA, Meta, Google, Apple, Microsoft, Tesla, Uber, Netflix, Apache, Oracle, IBM, Cisco, Tencent, Square and others have merged its patches.

housebroken is the manners. Gates an agent must pass before it opens a pull request on someone else's repo: one finding, the smallest diff, a test that fails on their main, a body under 120 words, their AI policy read first, a second model's review. The gate refuses until every rule is met.

The hard problem in agentic AI is the exit condition. Anyone can make a model take another step.
The work is deciding, with evidence, when it has done enough.

Pinned Loading

  1. jeffy-loop jeffy-loop Public

    A Claude Code loop that finds bugs in your repo, fixes them, and checks every fix before it commits.

    Shell 12 1

  2. housebroken housebroken Public

    Agent-written pull requests that do not make a mess in someone else's house.

    Shell 1

  3. python-fixed-income python-fixed-income Public

    Python for Fixed Income: a free course series that teaches Python from zero to people who work in fixed income, every example a bond or credit example

    Jupyter Notebook 1

  4. corp-default corp-default Public

    XGBoost bankruptcy screen for US public companies, benchmarked against Altman Z (1968) and penalised logistic regression. Two-year hazard label, embargoed temporal split, cluster-bootstrap intervals.

    Jupyter Notebook

  5. proper-eda-analysis proper-eda-analysis Public

    Publication-quality exploratory data analysis on Lending Club loan data (2.9M loans, 141 features)

    Jupyter Notebook

  6. yield-curve-prophet yield-curve-prophet Public

    LSTM + XGBoost ensemble for weekly yield curve direction prediction. 20 years of FRED macro data, walk-forward validation, SHAP interpretability.

    Jupyter Notebook