What I’m not sure to understand is that if you want to just run Claude code or openclaw type software with llm apis or subscriptions (and not run local models) to benefit from a local file system and always-on capability for ‘second brain’ type of workflows, I guess you don’t need a Mac mini but can run it on a raspberry pi or an old laptop ? Does anyone have experience with that ?
If you think about it as a game and not a typing exercice it's quite good, feels a bit like a typing guitar hero, and the animations are fun. Also learned some words. It lacks an accessible about page, you only reach it once going through a complete round.
Quite a bad piece, the end note is ironic: the author doesn’t seem to be paying a lot of attention for a film critic apparently interested in litteralicity.
> An earlier version of this article incorrectly described the ending of “A Complete Unknown.”
I cannot see any common denominator in the multiple examples that the author gives and cannot relate to them (what point is there to put on an equal footing a micro analysis of a dialogue in Megalopolis -voluntarily grotesque- and the choice of film format in The Architect?).
Maybe there’s an intuition here, but I feel it is not well illustrated. The author probably hopes that she will be remembered for coining this wishy washy concept.
I’ve been using Strudel.cc lately which provides a live REPL for a JavaScript equivalent to Tidal, it’s wonderful (although there’s a lack of community forums / discord which would be nice for beginners)
Prompt engineering and now ”context engineering” are really the poor man’s engineering work when you’re subject to model iterations and cannot control any of the stochasticity of the models… what we need is better science to understand how to control large model’s output, not more LinkedIn AI influencers