Two weeks ago I wrote about my side-project with Claude Code. The project is now done, and it was built 100% with Agentic AI. It’s an app called Notebook Navigator, and it combines the best of note-taking apps like Apple Notes, Bear, Evernote, Google Keep and Notion into one single app. It is built as […]

Read more…

Should I require all my developers to start using AI? I often get that question. The answer is not a strict yes or no, but more “it depends”. If you are using a code base built on Go, Typescript, Rust or Python then the answer is always YES, go ahead, give Claude Code with Claude […]

Read more…

I listen to a lot of audio books, and always keep a book playing when out for a walk or a run. The joy of finding an amazing narrator like Bill Homewood reading The Count of Monte Cristo by Alexander Dumas is one of many reasons I keep listening. There are however many books at […]

Read more…

The past week I have been using Claude Code a lot, Anthropic’s CLI-based code editor. I have used it on existing large code bases, and I have used it to create complex new applications. Claude Code with Claude Opus 4 is truly the next-level code generation AI we have all been waiting for. 90% of […]

Read more…

Last week was one of the biggest so far just in terms of sheer volume of AI news. Google I/O was all about AI this year and Microsoft Build was very AI centric too. I have tried summarizing everything the best I can below, but all in all it was probably over 30 AI-related news […]

Read more…

If you are developing software with AI, most of your prompts probably include “act like a senior developer”. The reason is that the large foundation models we use for programming like o3 and Claude 3.7 are not specifically tuned for this task, which means you have to explicitly tell them how they should act. “Do […]

Read more…

In Sweden there are still AI consultancy companies strongly defending what they call “Mogen AI” (“Mature AI” in English) – traditional machine learning based on manual feature engineering. The argument is that it’s “good enough” and that you really don’t need to invest in deep transformer skills. And I agree that this is often the […]

Read more…

Last month Shopify CEO Tobi Lütke sent out an internal memo saying that before employees ask for more headcount or resources, teams must first show why they “cannot get what they want done using AI”. And last week it was Duolingo’s turn, with their CEO Luis von Ahn sending out an internal memo saying “headcount […]

Read more…

Last week Swedish startup Lovable launched version 2.0 with a new feature called “multiplayer workspaces” where you can now vibe code apps together. Their motto is “idea to app in seconds, with your personal full stack engineer”. What started as a prototype called “GPT Engineer” is now a product used by over 300 000 monthly active users, and Lovable is […]

Read more…

Last week OpenAI launched five new models: GPT-4.1 (including mini and nano variants), o3 and o4-mini, together with a new command-line tool called Codex CLI. You now have six models to choose from in ChatGPT: GPT-4o, GPT-4o with scheduled tasks, GPT-4.5, o3, o4-mini, and o4-mini-high. If you use the API you can add GPT-4.1, GPT-4.1-mini […]

Read more…