Blog

The Reliability Gap: Agent Benchmarks for Enterprise

Agents

Is agentic AI ready for enterprise use? A review of the key benchmarks and the state of the art.

2026-01-04

Pivoting to a Career in AI and Data

Career

How to leverage your existing domain knowledge, prioritize what to learn and prove your new skills.

2025-12-17

A Philosophy of AI Coding

Productivity

How principled software design enables better AI coding, and how AI helps maintain consistent design.

2025-08-27

When (Not) to Use Agentic AI

Machine Learning
Agents

A framework for deciding when agentic AI adds value versus when simpler approaches work better.

2025-03-01

ModernBERT vs LLMs for Detecting Adverse Drug Reactions

Machine Learning
HuggingFace recently released ModernBERT (Warner et al. 2024), an updated version of the BERT language model (Devlin 2018) which backports many improvements from LLM…
2025-01-12

Diagrams as Code: Supercharged by AI Assistants

Productivity
Diagrams as code are an efficient way to communicate complex ideas and document software architecture. In this post I’ll explain how an AI assistant makes them even better.
2024-12-28

When to use Direct Preference Optimization (DPO)

Machine Learning

Introduction to Direct Preference Optimization (DPO) and when to use it vs supervised fine-tuning (SFT) for customizing LLMs.

2024-12-22

Type-safe LLM agents with PydanticAI

Machine Learning
Python
Pydantic AI is a new agent framework by the company behind Pydantic, the popular data validation library. Pydantic has transformed how I write Python, so I’m excited for…
2024-12-16

Constrained by Context, Not Reasoning

Productivity
Machine Learning
Frontier LLMs rarely give completely wrong answers. Even when their responses aren’t exactly what we need, they’re usually logical given the information provided.
2024-12-14

Aspect-based Sentiment Analysis with DSPy

Machine Learning
Python
Last year, my colleague Paavo Huoviala and I explored prompting and fine-tuning large language models for aspect-based sentiment analysis (ABSA) (Simmering and Huoviala 2023)…
2024-11-24

From 5-7-5 to Thousand Lines: The Case for Longer Prompts

Machine Learning
Prompts are the key to guide LLMs for any task, from a chatbot to a text classifier. Longer prompts are usually better than shorter ones, as I’ll argue below. There is a…
2024-09-01

OpenAI’s structured output vs. instructor and outlines

Machine Learning
Python
On August 6 OpenAI released structured outputs in their API. Is structured outputs a replacement for instructor, outlines and other libraries that provide structured outputs…
2024-08-10

Levels of Abstraction in the LLM Stack

Machine Learning
Training and serving LLMs requires a tall software stack. You can engage with this stack at different levels of abstraction, from low-level frameworks like CUDA to…
2024-08-08

Less stress, more focus: How to handle waiting times in development

Productivity
It’s unfortunate, but there are many waiting times in data science. Dealing with them well can make work more productive and enjoyable. Common waiting times include:
2024-07-28

Text Tournament: Rank Marketing Copy with LLMs

Machine Learning
Python
Marketing
The launch of the review analysis project has me working on various marketing tasks. Naturally, I built a tool to let LLMs help with the creative process. It’s called Text…
2024-07-23

Let Research Settle Before Consuming It

Productivity
The pace of publishing in machine learning is extremely high. There were 242,290 AI publications in 2022. That’s 663 per day, or one every two minutes. Based on comments on…
2024-07-20

The World is Large and Very Detailed

Economics
It’s easy to underestimate how vast and heterogeneous the world is. For entrepreneurs and developers this has two implications:
2024-07-13

Rich Personal Wiki in Quarto

Productivity
Machine Learning
Machine learning is a deep and constantly evolving field. In an applied project, the details of models are typically compressed into a few lines of a configuration file.…
2024-07-07

Fast and good

Productivity
Career
The adage goes: fast, good, cheap. Pick two. As a developer, you probably don’t want to be cheap labor, so I suggest that you strive for fast and good. Not just good, and…
2024-06-22

The best library for structured LLM output

Machine Learning
Python
By default, Large Language Models (LLMs) output free-form text. But many use cases such as text classification, named entity recognition, relation extraction and information…
2024-05-11

Evaluating an LLM for your use case

Machine Learning
In the last two months we’ve seen releases of flagship LLMs like Llama 3, Mixtral 8x22B, and Claude 3. The title of Mistral’s announcement summarizes the dynamic well: Cheape…
2024-04-28

How to get gold standard data for NLP

Machine Learning
With the attention on new LLM releases, it’s easy to forget that correctly labeled examples are still a critical factor for accuracy in most NLP tasks. I think they’re the…
2024-03-10

LLM Price Comparison

Machine Learning
Cloud
Economics
This article is about prices as of January 11, 2024. For current prices and more comprehensive analysis, check artificialanalysis.ai (not affiliated with me).
2024-01-11

The Grug Brained Data Scientist

Productivity
The Grug Brained Developer is a funny essay on advice for software developers. The lessons resonated with me. This is my own version, geared towards data professionals.
2023-12-09

NLP escalation ladder: Use the simplest NLP model that does the job

Machine Learning
With all the hype and breathtaking demos, it’s tempting to see LLMs as the universal tool for every language problem. And yes, GPT-4 in particular will achieve decent to…
2023-11-12

Large language models for aspect-based sentiment analysis

Machine Learning
A finetuned GPT-3.5 Turbo model achieves state-of-the-art performance in aspect-based sentiment analysis (ABSA). Zero-shot and few-shot settings with GPT-4 and GPT-3.5 reach…
2023-11-01

One-stop NLP: Multi-task prompts for LLMs

Machine Learning
Python
In NLP, we often want to extract multiple pieces of information from a text. Each extraction task is typically done by one model. For example, we might want to classify the…
2023-10-29

Dataset Size vs. Label Correctness: What is more important for training a model?

Machine Learning
Python
Supervised models are trained on labeled data. The more data, the better the model. But what if the labels are wrong? How much does the quality of the labels matter compared…
2023-10-28

Future Directions for Large Language Models

Machine Learning
Large language models (LLMs) have taken the world by storm in the last year. It’s not even been one year since ChatGPT was released, and we have seen countless applications…
2023-10-21

A Critical Evaluation of Github Copilot and GPT-4 in a Data Science Workflow

Productivity
AI assistants like Github Copilot and ChatGPT promise breakthrough productivity improvements for developers. In this article, I’ll explore how these tools can be used in a…
2023-04-10

Twitter API data collector with Modal

Python
Cloud
Data Engineering
In this article, I’ll show how to build a Twitter data collector in just 100 lines of code. Twitter data has many applications, from social science research to marketing…
2023-01-26

Investing in data science skills for the long run

Career
Data science is a field that is constantly evolving and requires a lot of practice to master. Picking the right skills to focus on is critical for career development.
2023-01-09

Tidy Tuesday: analyzing yarns with polars

Python
Tidy Tuesday
In this article, I’m taking the Python data frame library polars for a spin. Polars is a super fast alternative to pandas, implemented in Rust. It also has a leaner…
2022-10-22

FANGMANT: Tech stock analysis with pandas

Python
The acronym FANGMANT stands for Facebook, Apple, Netflix, Google, Microsoft, Amazon, Nvidia and Tesla. Large, highly profitable US tech companies that dominate their…
2021-12-27

Data frame wars: Choosing a Python dataframe library as a dplyr user

R
Python
I’m a long time R user and lately I’ve seen more and more signals that it’s worth investing into Python. I use it for NLP with spaCy and to build functions on AWS Lambda.…
2021-12-20

Exploring echarts4r

R
Data Visualization
As web-oriented presentation in R Markdown and Shiny becomes more and more popular, there is increasing demand for interactive graphics with R. Whereas ggplot2 and its vast…
2020-02-08
No matching items