Feed

AI doesn't damage our brains, but unthinking use can damage our thinking. What's at stake isn't our neurons but our habits of mind. There is plenty of work worth automating or replacing with AI (we rarely mourn the math we do with calculators), but also a lot of work where our thinking is important. For these problems, the research gives us a clear answer. If you want to keep the human part of your work: think first, write first, meet first.

Going back to that fictional conversation in The Diamond Age, I think that the answer—the thing that Finkle-McGraw acquired during his upbringing, that he failed to confer on his children, and that he wants to give his granddaughter—isn’t simply a body of knowledge to be memorized or a set of skills to be mastered. It’s a stance. A stance from which to address the world and all its challenges. A stance built on self-confidence and resilience: the conviction that one has a fighting chance to overcome or circumvent whatever obstacles the world throws in one’s path. The way you acquire it is by trying, and sometimes failing, to do difficult things. It can be discouraging, but if you have good mentors, and if you’re collaborating with friends who are in the same boat, you can find ways to succeed, and develop a knack for it. That’s true self-reliance.

The Bottom Line

Making AppleScript work in CLI tools requires:

1. An embedded Info.plist for identity
2. Proper entitlements for permissions
3. Correct code signing
4. Optional: responsibility_spawnattrs_setdisclaim for cleaner permission dialogs

Let’s face it, prompt engineering is still new territory for most teams, but some problems feel very familiar. Just like messy code can drag down your entire product, messy prompts will do the same for any LLM-powered app. The good news is that you already know what to do about it. You don’t need a totally new mindset, just a willingness to pay attention to the quality of your prompts the same way you already care about code.

Blood-sucking ticks that trigger a bizarre allergy to meat in the people they bite are exploding in number and spreading across the US, to the extent that they could cover the entire eastern half of the country and infect millions of people, experts have warned.

This happened to a very good friend. He was bitten by a tick while out fishing and it ended up almost killing him. If it had been anyone else, the claim of "I am now alergic to meat" would have been scoffed at.

As I’ve mentioned, while I like the ideas behind RSS, none of the existing RSS readers worked for me. They try to do more than I need. A classical RSS reader fetches full content of the articles, saves it for offline reading and renders the content using an embedded web-browser. I don’t need this. I prefer reading the articles on the author’s website, using my normal browser (and, occasionally, its reader mode). The only thing I need is notifications.

So perhaps résumés as a meaningful signal of candidate interest and qualification are becoming obsolete. And maybe that's OK. When anyone can generate hundreds of tailored applications with a few prompts, the document that once demonstrated effort and genuine interest in a position has devolved into noise.

For most people who want to use AI seriously, you should pick one of three systems: Claude from Anthropic, Google’s Gemini, and OpenAI’s ChatGPT. With all of the options, you get access to both advanced and fast models, a voice mode, the ability to see images and documents, the ability to execute code, good mobile apps, the ability to create images and video (Claude lacks here, however), and the ability to do Deep Research. Some of these features are free, but you are generally going to need to pay $20/month to get access to the full set of features you need. I will try to give you some reasons to pick one model or another as we go along, but you can’t go wrong with any of them.

The arrival of million-token context windows felt transformative. The ability to throw everything an agent might need into the prompt inspired visions of superintelligent assistants that could access any document, connect to every tool, and maintain perfect memory.

But as we’ve seen, bigger contexts create new failure modes. Context poisoning embeds errors that compound over time. Context distraction causes agents to lean heavily on their context and repeat past actions rather than push forward. Context confusion leads to irrelevant tool or document usage. Context clash creates internal contradictions that derail reasoning.

Bases is a brilliant new tool from the Obsidian team. It allows you to create interactive filtered lists of notes. It is user-friendly and extremely powerful, and I think one of the most important additions to Obsidian that we’ve ever seen.