1. apfel.franzai.com gives you an interface to the local LLM Apple ships on macOS. It has a small context window and is interesting perhaps for the way you could use it to wire inference into a shell script. It’s right about some things. I hope nobody from Planet Apple plans a roadtrip to Oregon with it.

  2. apfel gives you an interface to the local LLM Apple ships on macOS. It has a small context window and is interesting perhaps for the way you could use it to wire inference into a shell script. It’s right about some things. I hope nobody from Planet Apple plans a roadtrip to Oregon with it.

  3. “Folk are getting dangerously attached to AI that always tells them they’re right”

    I don’t see this as particularly distinguishable from a large volume of social media interactions generally. Maybe we’ve achieved AGI after all.

    www.theregister.com/2026/03/2…

    "Overall, deployed LLMs overwhelmingly affirm user actions, even against human consensus or in harmful contexts," the team found.&10;&10;As for how AI sycophancy affects humans, the team had a considerable sample size of 2,405 people who both roleplayed scenarios and shared personal instances where a potentially harmful decision could have been made. AI influenced participant judgments across three different experiments, they found.&10;&10;"Participants exposed to sycophantic responses judged themselves more 'in the right,'" the team said. "They were [also] less willing to take reparative actions like apologizing, taking initiative to improve the situation, or changing some aspect of their own behavior."
  4. Using my RSS triage tool, I’ve almost completely isolated the most obnoxious parts of The O. They use stringers/syndicators for their thinnest content. Gives me an idea to add an author lookup to check the tool’s memory for associated articles and just permablock them.

  5. I’ve been using macOS screen sharing between MacBook and mini and I’m a little surprised at how responsive it is. No more running upstairs when a CLI process opens a browser for oauth grants or whatever. In fullscreen and dynamic scaling I sometimes forget I’m in Screen Sharing.

  6. A while back I added some instructions to Claude to push back when I have a big idea that is not something I’d call one of my purposes. It took some back and forth to get the right level of pushback, but I appreciate past me for thinking of it.