All episodes

Open LLMs like Gemma or Qwen are AMAZING!

Open LLMs like Gemma or Qwen are AMAZING!

9m 0s

I've slept for too long on open LLMs like Gemma, Llama, Qwen, DeepSeek etc.
They're AMAZING!
Using them is simple (with LM Studio or Ollama) and they're not far behind the "big models" you can access via ChatGPT etc. At least in my experience.
I'm using them for all kinds of tasks...

React Compiler Release Candidate Released!

React Compiler Release Candidate Released!

7m 37s

React Compiler RC (Release Candidate) was released!
Almost one year after its initial release (back then in experimental status), it's now almost ready for production use.
And it can save you LOTS OF time of writing useMemo(), useCallback() and memo()!

A2A - Google's bet on AI Agents

A2A - Google's bet on AI Agents

14m 31s

Google released a couple of AI Agent related products & services!
The A2A protocol is maybe the most interesting initiative. Also because it kind of clashes with MCP. Or does it?

It's named COpilot for a reason!

It's named COpilot for a reason!

8m 16s

It's essentially ONE key feature I really don't want to miss anymore.
Well, maybe 1.5 features...

MCP: Hype or Useful?

MCP: Hype or Useful?

19m 45s

MCP has been a hot buzzword. But what exactly is that model context protocol thing about? And who do LLMs actually use tools?

Why

Why "vibe coding" is NOT my future

17m 16s

Originally coined by Andrej Karpathy, it describes a way of coding where you don't write any code but you just ask (and blindly trust) LLMs.

React Router 7 is too amazing to settle on suboptimal docs

React Router 7 is too amazing to settle on suboptimal docs

13m 29s

React Router 7 is pretty amazing. It always has been.
But v7 especially is exciting because it offers "library mode" and "framework mode".
But "library mode" then actually can be used in at least two different ways.
And the docs don't necessarily cover that very well...

There's An AI Skill Gap Growing

There's An AI Skill Gap Growing

9m 28s

ChatGPT & co are becoming better and more capable all the time.
Soon, every human will be able to use AI assistants to do pretty much anything they want.
Maybe.
But maybe, we'll also see a different outcome.