Alexander Junge's website

This weekend, our five-year-old son really wanted us to make our own racing game and what he wanted was super clear: only stingrays (his favorite pet animal) racing each other, and they should say “oh my days” when they crash.

Performance optimization is a crucial aspect of web application development, especially when dealing with concurrent requests.

I am a happy user of pydantic and instructor, the latter being a well scoped tool with a well-defined surface area to use pydantic for structured outputs and validation for large language models.

Let’s assume you have a few evals for your AI product in place that allow you to get a good idea of how well the underlying (set of) model(s) is doing and attract a few first users.

I am a big fan and active user of instructor to make interactions with inherently probabilistic LMs more structured and reliable in the form of their output.

I really like this blog post by Hamel Husain entitled ‘Your AI Product Needs Evals’.

As I was reading this review paper on tool use for language models (LMs) over the Easter holidays, a thought crossed my mind: There is an interesting trend when working with LMs in production to perform more and more computations at inference time.

Function-calling (aka tool-use) is essential to enable LLMs to run internet searches, write and execute code, generate images, use a calculator, … whenever that makes sense to solve the current task.

This blog post on “RAG 2.0” by Contextual AI got me thinking.

With modern AI tools just being an API call away for most developers, the bottleneck to creating entirely new, powerful experiences is no longer a lack of access to technology but a lack of human creativity, understanding of the problem space, and an inab…

Why The usefulness of modern AI systems dramatically increases when the underlying AI models have access to recent, relevant data in addition to the information captured in the models’ internal parameters.

RAFT: Adapting Language Model to Domain Specific RAG From the Gorilla LLM project, Retrieval Aware Fine-Tuning (RAFT) combines retrieval-augmented generation and fine-tuning to adapt language models to domain-specific knowledge.

Major personal news today: I have joined amass as a co-founder solving challenges every life sciences researcher and R&D organization is facing: How to keep up with scientific knowledge, in all its shapes and sizes, both internally and externally?

As I briefly mentioned in a previous post, I went from an individual contributor (IC) role to tech & team lead over the last few years.

TL;DR There are too many interesting research papers to read.

I recently finished reading Andrew Nguyen’s book “Hands-On Healthcare Data” published by O’Reilly in September 2022.

Photo credit: Suzanne D.

I am a big fan of f-strings in Python.

I have used GitHub Copilot, an ML pair programming tool based on OpenAI Codex, for a few months now when working on hobby projects and wanted to share a short anecdote here illustrating its usefulness and where it currently fails.

Today (well, earlier this week but let’s not be picky here) I learned about the Unix core utility yes.

Jupyter notebooks are very useful to quickly prototype ideas in data science projects because they allow seeing code, the output of that code, and a narrative explaining its logic right next to each other.

I recently finished (and enjoyed) reading Chip Huyen’s book “Designing Machine Learning Systems” published by O’Reilly.

This is the obligatory post playing with text-to-image diffusion models recently made very popular by tools such as OpenAI’s DALL-E 2 or Google’s Imagen.

I have been wearing an Oura ring for a few years now to track my nightly sleep, daily activity, and other health variables.

🤗 Hugging Face Transformers AutoModelForSequenceClassification offers a quick way to fine-tune a pre-trained language model for a text classification task.

PyScript was announced on April 30th 2022 at PyCon US by Peter Wang, CEO of Anaconda Inc., and in an accompanying blog post.

Data science and machine learning (ML) projects frequently involve prototyping models as part of ML apps, showing them to potential users to get feedback, and iterating to improve both model as well as problem-solution fit.

Jupyter notebooks edited in JupyterLab are my tool of choice when working with and exploring data in Python.

GitHub Profile READMEs are a great way to present your programming projects, interests and experience to the world.

Structural pattern matching (aka the match statement) is a new feature introduced in Python 3.10 which was released on October 4th, 2021.

I recently came across Canarytokens, a service generating trap tokens (URLs, images, PDF, and much more) that notify the owner when used.

Amazon Kendra is a managed search service offered by AWS.

It’s good to clean up regularly.

Acquiring and cleaning data, including reliable labels for supervised learning, determines the fate of every data science project and usually takes up about 80 percent of project time.

I recently switched to version 2 of Apache Airflow which was released in December 2020.

Deploying a trained machine learning model behind a REST API endpoint is an common problem that needs to be solved on the last mile to getting the model into production.

As I keep forgetting the following and keep finding outdated answers/documentation when searching online, I hope this will be useful to others and to future me: Autoreload all imported packages in Jupyter %load_ext autoreload %autoreload 2 Autoreload spec…

This weekend, I set up my first GitHub Action to run continuous integration using Pytest for one of my repositories.

displaCy, a component of the excellent spaCy NLP library makes it super easy to visualize named entity recognition (NER) results from a Jupyter notebook.

Using a Raspberry Pi 4 Model B and a Seeed ReSpeaker Mic Array v2.0 connected via USB, I built a simple sound-activated recorder.

I started experimenting with AWS and as a first tiny project I deployed a fastAPI-based REST API to AWS Lambda, a serverless framework.

I recently read the book ‘Inspired: How to Create Tech Products Customers Love’ by Marty Cagan and can wholeheartedly recommend it to anyone interest in learning more about digital product management.

As described in my last post, I used Apache Airflow to query articles from arxiv.org.

Querying arXiv preprints using Apache Airflow I experimented with Apache Airflow to schedule hourly workflows fetching recent preprint articles from different arXiv categories via the public arXiv.org REST API.

Most projects I am working on enforce specific code styles, minimal requirements for documentation, or other rules every code contribution needs to follow.

On February 1st 2019, I left my position as a postdoctoral researcher at the University of Copenhagen and started working as a data scientist in pharmaceutical R&D at Novo Nordisk A/S.

Docker containers are well-suited to ship software because they allow a fast, flexible, and efficient deployment in any computing environment - be it on premise, in the cloud, etc.

A central goal in the development of CoCoScore is to make it as easy as possible for new users to get start with context-aware co-occurrence text mining.

Our preprint describing CoCoScore was posted on bioRxiv yesterday.

I just finished reading Andrew Ng’s new book ‘Machine Learning Yearning’ and would like to recommend it to everyone interested in learning more about managing machine learning projects.