I’ve been thinking about personalising Retrieval-Augmented Generation (RAG) lately. This is partly because my team is now building a chatbot that answers questions using a RAG setup. It’s a continuation of my work …
Blog
Mentoring toolkit
I had the privilege of mentoring two junior software engineers over the past year. It was my first time doing something like this, so there was a lot to learn! To be honest, I don't …
Notes from AIAI London 2024
I attended the AI Accelerator Institute's Generative AI Summit that happened yesterday in London - AIAI London in short. Here are my notes. These are by no means exhaustive. Just a bunch of things I found …
Thoughts about AGI
There's a lot of buzz these days around AI, and AGI in particular. It seems like everyone is busy sharing their thoughts on AGI on the internet. I would love to do the same on …
Starting a tech book club!
I'm kickstarting a technical book club! It's going to be based around a mailing list with one thread per week discussing the scope covered that week. I have some ideas for what to read, but …
A non-review of half of Designing Data-Intensive Applications
I read the first seven chapters of "Designing Data-Intensive Applications" before deciding to stop. It's about half of this hefty book. In the spirit of learning in public through this blog, I'll reflect on what …
Anthropic is onto something interesting with Artifacts
A few weeks ago, Anthropic released a new feature to their Claude chatbot — Artifacts. It was announced together with Claude 3.5 Sonnet. You can find more details in the section about the feature. It's …
In-browser LLM on Chrome Canary
The nightly version of Google Chrome ships with an on-device LLM. The model it runs is Gemini Nano. Some documentation about this can be found here.
It's not surprising to be honest, that tiny LLMs …
The Pragmatic Programmer Review
The Pragmatic Programmer 20th Anniversary Edition, by David Thomas and Andrew Hunt, offers high-level, actionable advice for software engineers. Unlike many technical books that focus on specific coding practices or languages, it focuses on cultivating …
Thoughts about Anthropic / OpenAI work on interpretability in LLMs
A few weeks ago, Anthropic came out with this paper, showing how they found interpretable features in one of their models. This means that they could see which features activate when the LLM generates, and …