Programming

Fixing Common Pitfalls of Codemods

So far the codemods that Juntao Qiu has described are fascinating, but r...

Emerging Patterns in Building GenAI Products

Everyone is fascinated about using generative AI these days, and my coll...

Podcast with Luca Rossi

Luca Rossi hosts a podcast (and newsletter) called Refactoring, so it's ...

GenAI Patterns: Retrieval Augmented Generation (RAG)

A pre-trained GenAI model lacks recent and specific information about a ...

Bliki: Forest And Desert

The Forest and the Desert is a metaphor for thinking about software develo...

Embeddings in GenAI Products

GenAI systems, like many modern AI approaches, have to handle vast quant...

GenAI Patterns: RAG Limitations and Hybrid Retriever

Today Bharani Subramaniam and I outline four limitations to the simple R...

Panel at goto Copenhagen: "Where is SW development Going

was on a panel at goto Copenhagen last September with Holly Cummings, T...

GenAI Patterns: Query Rewriting

Users often have difficulty writing the most effective queries. Bharani ...

The DeepSeek Series: A Technical Overview

The appearance of DeepSeek Large-Language Models has caused a lot of discu...

GenAI Patterns: Guardrails and RAG overview

Gen AI systems are gullible, and can easily be tricked into responding i...

What role does LLM reasoning play for software tasks?

Recent LLM models have provided “reasoning” capabilities. Birgitta Böckel...

GenAI Patterns: Reranker

LLMs struggle with large amounts of context. Bharani Subramaniam and I e...

I've been kidnapped by Robert Caro

I've always enjoyed reading, and for most of my life I've particularly e...

The role of developer skills in agentic coding

As agentic coding assistants get more capable, Birgitta Böckeler is try...

Commenting on removing "X" on US passports

The new US administration has decided to eliminate the “X” option for gender/sex...

GenAI Patterns: Fine Tuning

While RAG is the most common way to focus a foundation model on material...

Guiding an LLM for Robust Java ByteBuffer Code

AI editors like Cursor can generate code with remarkable speed using LLM...

Updating yesterday's post on social media engagement

Some people asked about how many people clicked through the links on the...

Social Media Engagement in Early 2025

A few years ago, whenever I published a new article here, I would just a...

Building TMT Mirror Visualization with LLM

Creating a user interface that visualizes a real-world structure — like...

Additional explanatory material for the Deepseek Overview

A couple of months ago, my colleague Shayan Mohanty published a technical ...

Node v20.8.1 (Current)

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies.