Blog
- Apr, 2024
- After evals, flywheels
- Recommended tutorial on achieving Structured Outputs in DSPy
- Recommended read: Your AI Product Needs Evals by Hamel Husain
- Fine-tuning LMs as a way to move compute back from inference to training
- Mar, 2024
- The Berkeley Function-Calling Leaderboard
- RAG 2.0?
- Building AI tools for an audience of one
- Short: Differential privacy in a RAG setting
- Short: RAFT
- Sep, 2023
- Major news: I am co-founding amass
- Apr, 2023
- Getting started as a technology team lead: books and resources I recommend
- Mar, 2023
- Recommending scientific articles interactively
- Feb, 2023
- Book review. Hands-On Healthcare Data by Andrew Nguyen
- Jan, 2023
- To grow, leave your comfort zone
- TIL: f-string formatting - a cheat sheet
- Dec, 2022
- GitHub Copilot generating PyTorch code comments: an anecdote
- Nov, 2022
- TIL: saying `yes` the Unix way
- Keeping sensitive information out of Jupyter notebooks stored in git version control
- Aug, 2022
- Book tip. Designing Machine Learning Systems by Chip Huyen
- Open source text-to-image diffusion
- Comparing Oura personal health data over the years
- Jun, 2022
- Multi-label classification using 🤗 Hugging Face Transformers AutoModelForSequenceClassification
- May, 2022
- PyScript: looking beyond the hype
- Apr, 2022
- Hosting Machine Learning apps easily and freely via Hugging Face Spaces
- Feb, 2022
- One JupyterLab, many projects
- Oct, 2021
- Video: Create a GitHub Profile README in a few minutes
- Python 3.10: Structural pattern matching and other new features for data science
- Jul, 2021
- Generating fake tokens to find out about security breaches
- Apr, 2021
- Experimenting with ML-powered search in Amazon Kendra
- Deleting old tweets
- Mar, 2021
- Labeling data in Amazon SageMaker Ground Truth
- Feb, 2021
- Spotlight: New TaskFlow API in Apache Airflow 2
- Dec, 2020
- Deploying a custom Python machine learning model as an AWS SageMaker endpoint using MLflow
- Nov, 2020
- %autoreload: reload code before execution in Jupyter
- GitHub Actions: Setting up poetry and running CI
- Oct, 2020
- Simple NER visualization using displaCy
- Jun, 2020
- Using a Raspberry Pi as a sound-activated recorder
- May, 2020
- Deploying fastAPI to AWS Lambda via Amazon API Gateway
- Apr, 2020
- Book tip: Inspired by Marty Cagan
- Mar, 2020
- Building a Vue/Vuetify application to label articles
- Feb, 2020
- Querying arXiv preprints using Airflow
- Jan, 2020
- Sanity checking your git commits
- Feb, 2019
- Starting a new job
- Jan, 2019
- Trying out Docker Compose
- Nov, 2018
- Packaging a Python library: first steps
- Oct, 2018
- CoCoScore preprint available
- Book tip. Machine Learning Yearning by Andrew Ng
- Sep, 2018
- Visiting the BioNLP group at NCBI
- Mar, 2018
- Illuminating the Druggable Genome (IDG) phase 2 kick-off
- Feb, 2018
- Book review. Python Tricks: A Buffet of Awesome Python Features by Dan Bader
- Nov, 2017
- News: CoCoScore proposal accepted at BLAH4
- Migration to blogdown
- Dec, 2016
- Datathon for Diabetes
- Oct, 2016
- First (minor) contribution to scikit-learn
- Sep, 2016
- Hack4DK - analyzing children's health care data
- Jul, 2016
- Review - Google's Deep Learning Course on Udacity
- Short video about our clustering project released
- Towards reproducibility with (bio)conda
- Apr, 2016
- Book review. RNA Biology - An Introduction by Gunter Meister
- non-coding RNA talks in April 2016
- Mar, 2016
- Analyzing my Fitbit data. Step 2 - Cleaning step and sleep data and looking for trends
- Analyzing my Fitbit data. Step 1 - Downloading Fitbit data via the API
- Main events organized by the ISCB Student Council in 2016
- The explainr R package
- Feb, 2016
- Website/blog launch
