Skip to content
View JayThibs's full-sized avatar
🎯
Focusing
🎯
Focusing
58 followers · 120 following

Achievements

Achievement: YOLOAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor
BetaSend feedback

Achievements

Achievement: YOLOAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor
BetaSend feedback
Block or Report

Block or report JayThibs

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
JayThibs/README.md

Hi there, I'm Jacques - aka JayThibs 👋

Website Twitter Follow

I'm a French Canadian working on AI Alignment!

  • 📄 Here's my resume and my LinkedIn profile. For my AI alignment takes, here's my LessWrong profile.
  • 🥅 2024 Goals: Publish at least 3 AI Safety related papers. Become a world-class research engineer capable of implementing research ideas at high iteration speed. Over-deliver on my independent researcher grant projects.

Current Project(s)

  • Collaborating on the Supervising AIs Improving AIs agenda (making automated AI science safe and controllable). The current project involves a new method allowing unsupervised model behaviour evaluations. Our agenda.
  • 🌱 Accelerating Alignment: augmenting alignment researchers using AI systems. A relevant talk I gave. Relevant survey post. If you are think AI Safety is important and you have a strong application development background, please reach out to me to collaborate!
  • I'm a research lead in the AI Safety Camp for a project on stable reflectivity (testing models for metacognitive capabilities that impact future training/alignment).

📕 Latest Blog Posts

➡️ more blog posts...

Pinned

  1. moirage/alignment-research-dataset moirage/alignment-research-dataset Public

    A dataset of alignment research and code to reproduce it

    HTML 64 16

  2. Weak-Supervised-Learning-Case-Study Weak-Supervised-Learning-Case-Study Public

    Exploring NLP weak supervision approaches to train text classification models. The project is also a prototype for a semi-automated text data labelling platform. Approaches: Snorkel and Zero-Shot L…

    Jupyter Notebook 22 4

  3. map-floodwater-satellite-imagery map-floodwater-satellite-imagery Public

    This repository focuses on training semantic segmentation models to predict the presence of floodwater for disaster prevention. Models were trained using SageMaker and Colab.

    Jupyter Notebook 30 7

  4. CER-REC/esa-data-bank_banque-donnees-ees CER-REC/esa-data-bank_banque-donnees-ees Public

    BERDI's environmental and socio-economic assessment (ESA) data extraction method | Notre méthode d'extraction des données pour les évaluations environnementales et socioéconomiques (« EES ») de CIBER

    Python 6 1

  5. hyperdrive-vs-automl-plus-deployment hyperdrive-vs-automl-plus-deployment Public

    Comparing models trained with HyperDrive and AutoML, and choosing the best model to deploy and consume in AzureML Studio.

    Jupyter Notebook 1

  6. spacy-example-deployed-service spacy-example-deployed-service Public template

    This is an example project to get started on quickly deploying an NLP service with FastAPI, SpaCy, Docker, Poetry, and your cloud service of choice.

    Python 4 1