The online whiteboard of Kristofer Palmvik
When you have a problem with an LLM, prompting should ideally be your first approach. Reach for finetuning, or smarter more expensive models once your prompts are as good as they can be - or you're leaving money and performance on the table.
Not sure what colors to use in your designs or where to use them? Happy Hues is a color palette inspiration site that acts as a real world example as to how the colors could be used in your design projects.
Billions of people use our tools every day. We possess the skills to make those tools shine. So, what if we made the world a better place simply by building great ones?
If you are using LLMs, or if you’re directed to do so, you’re about to turn from an author of your own code into a reviewer and maintenance programmer — and maybe a tester, too — for a barely competent programmer producing mountains of mediocre and unreliable code.
For EMs, wartime means leading low-morale teams through ambiguity, hard constraints, frequently changing goals, and intense pressure to perform. It can feel like working in a house on fire. What can an EM do in this situation?
Companies with relatively young, high-quality codebases benefit the most from generative AI tools, while companies with gnarly, legacy codebases will struggle to adopt them. In other words, the penalty for having a ‘high-debt’ codebase is now larger than ever.
Since email is static, we faced the challenge of embedding something dynamic (an 𝕏 post). Given that email-safe HTML cannot embed an 𝕏 post, so we needed to find a way to convert any post to an email-friendly form.
Turn websites into LLM-ready data Power your AI apps with clean data crawled from any website. It's also open-source.
We could think of that category as things I’ve found. That’s the purpose of my link blog: it’s an ongoing log of things I’ve found—effectively a combination of public bookmarks and my own thoughts and commentary on why those things are interesting.
I suspect that we could benefit from accepting his theory as a law: the ultimate goal of software design should be (organizational) knowledge building. So the next time you choose a name, or structure a project, or ponder whether to write or omit a certain comment, rather than thinking in terms of the burden on future maintainers, think: how much will this decision affect—how much will it help or hinder—their building of a mental model of the system, of the business, of the world.
4931 links collected between and