This piece was originally published on David Crawshaw's blog and is reproduced here with permission. This article is a summary of my personal experiences with using generative models while programming ...

ChatGPT, Google’s Gemini and Apple Intelligence are powerful, but they all share one major drawback — they need constant access to the internet to work. If you value privacy and want better ...

With tools like Ollama and LM Studio, users can now operate AI models on their own laptops with greater privacy, offline ...

Forever a Luddite, I’ve only just started using ChatGPT. I’m not like some (far more productive) grad students who can recite whether Claude or o4-mini or whatever else is best for coding; I pretty ...

The best thing about self-hosted LLMs is that you can choose from hundreds of models ...

As large language models (LLMs) continue to improve at coding, the benchmarks used to evaluate their performance are steadily becoming less useful. That's because though many LLMs have similar high ...

I didn't expect it to be so entertaining, but Qwen 3.6 and Gemma 4 put on a show.

Agentic AI has emerged as a game-changer, with the potential to fundamentally transform how organizations operate and scale. Agentic systems are designed to break down complex objectives into subtasks ...

“Government” is often synonymous with “procedures.” Thousands of procedures are managed by government and public sector offices every day, generating congestion and delays most of the time. It's ...

To operate, organisations in the financial services sector require hundreds of thousands of documents of rich, contextualised data. And to organise, analyse and then use that data, they are ...