It's free for a limited number of notes. I guess you could copypaste the note summaries out to Obsidian or something, but at that point you're better off using MacParakeet, OpenWhispr, etc.
It works great on Macbook. I don't know why they don't suggest it to folks when car or train movement is detected! I have a feeling a lot of people don't know it exists.
I wish my Pixel 9 had it but I guess it hasn't trickled down yet. I think it's in the latest Android on latest Pixel devices though.
> I don't know why they don't suggest it to folks when car or train movement is detected
Apple whole idea to UX seems to be "Mostly hidden by default, let people trigger it accidentally to learn about it, or reading about it somewhere else" as even after having my iPhone 12 Mini for so long, I still "discover" new things every now and then that nothing or no one told me about.
Like how are people supposed to "discover" the whole "shake the phone to undo" shortcut unless they accidentally trigger that? I see nothing in the UI that indicates when this is possible either, some apps use that for reporting feedback instead.
Younger me used to "explore" the OS or any software by clicking all the things. It was part of growing and learning. I was never afraid to click the wrong thing. It's similar to those that take things apart just to see what's inside. I had no idea that I was the edge case of personality types.
Things that are "hidden" are just discoveries waiting to happen for those that look. For those that need their hands held and guided through the world, those things might stay "hidden". Just as you feel irked that things are hidden, I feel irked by people that don't go looking. Push all the buttons. Turn all the knobs. Click all the things.
It's somewhat intentional. Apple always pushes to prioritize the "Happy path" flow, including making it better and "Just works", and part of the way you do that often ends up making it harder, or take more work, to step off the happy path.
It's also Apple, so it's a marketing thing. There's a reason Snapchat sorta developed this feature style, and Apple targets the same demographic, or at least did for a while.
Unfortunately, this has heavily leaked into Android and Windows, and I hate it.
Yep - it's a game changer on the Pendolino trains I get to work as they tilt going around corners. Most people seem to be fine, but for me, it was impossible to get some work done on my commute until vehicle motion cues were a thing and I got > M2 MBP for work.
Thank you so much for sharing this. I’ve been saying to my wife for about a year now that I wish MacBooks had the motion cues feature… turns out I just needed to search for it!
this helped me tremendously when I had to work in the backseat of a moving car. Felt sick pretty quick when I started using the laptop until I remembered about this feature because someone on HN recently posted / commented about it
places like Charles Town, Martinsburg, and Cumberland MD are really wonderful, beautiful, but economically depressed communities. It's not quite Boise or Austin, but towns like this would be really attractive to a certain group of remote workers (esp. those with homesteading or kayaking/fishing/hiking aspirations) if they only knew about them.
I will often do "speak a long rambling set of ideas and ask the LLM to summarize it into a prompt or spec -> manually refine -> drop refined prompt into fresh conversation"
I like the fact that it ends up being a lifecycle. I know it can have different entry points based on what you ask, and which skill you trigger first, but it inherently is chaining together skills. There also seems to be logic built into it such that if the ask is small, but you've still triggered the skill with "brainstorm", it will make judgements like "want me to skip phase X and go straight to implementation?"
I've noticed among my coworkers that we all have different amounts of trust we're willing to give the agent. That seems to manifest into some people only asking questions about the existing code, but never writing anything new with it. Others are willing to do limited targeted changes with the agent, but are unwilling to do things like let it make commits, or connect MCP servers, or really do anything that isnt fully understood by the human before setting the agent loose. Then I find myself, who has dove headlong into it all. I have skills that use MCP servers to check for pull requests, and give me summaries to give me more context for code reviews. I update Jira tickets in batches of 50+. I develop complete features exclusively through prompting the agent to do everything. I know I still have the responsibility to understand it at the same level as if I wrote it my self, and defend it and debug it.
I can easily see that superpowers would be wasted on most of my coworkers, simply because the benefits compound with the complexity of my ask. My coworkers aren't willing to hand off enough control to receive the benefits of superpowers.
I am in the completely same boat as you and completely agree that you need to “give into it” more to get the most out of superpowers. I gain so much confidence out of the actual process and all of the adversarial reviews, re-reviews, refinement, etc.
Honestly, within the last few days I've gone back to a mostly vanilla installation of Claude with a handful of directives in AGENTS.md. Depending on what I'm working on, I don't feel I need the extra plugins or a context repository. (It DOES feel at times like it blows through tokens for no reason).
Been working on some things that require more targeted, smaller scale changes and the base models do perfectly fine when given good instructions.
Superpowers and Compound Engineering are the two that I hear about around our team, both seem "fine" if you're into the fully agentic engineering "big change" future technology stuff.
They just raised $85 billion and they're sitting on a mountain of cash - if their spending didn't increase in this context, it'd be bad management. The real story here is that they have decided to spend that mountain of cash on AI CapEx.
I'm referring to the equity offering that started in June and has a second component that starts in 2026Q3. Most of this raise came from the sale of Class A and Class C stock. A fraction came from the sale of convertible stock. To my knowledge, none of this raise came from the sale of bonds.
Also, looks like I got it wrong and they've only raised $45B to date. The rest will come as part of the ATM offering program that begins in Q3.
I used to transcribe his articles to a text file and post them to Usenet.
Thank you for your service.
People like you were how people in other countries learned about technology and of other cultures in the days before the internet.
Some person (people?) would post scripts from Red Dwarf on one of the networks years before the show became available televisually in the United States. I used to devour those and laughed and laughed and laughed. That kind of British humor comes through well as text.
I just spent an hour on-line reading that PC Magazine from December 1999. Amazing that it's over 227 pages. There's a piece on portable CD-RW drives, and the ads, the classifieds section, a lot to take in during that epoch at the end of the 90's. I miss those big spread ads from Compaq and CDW. But my favorite piece in this issue is the "technical excellence awards" feature. They highlight this new webapp called "Google": https://archive.org/details/PC-Mag-1999-12-14/page/110/mode/...
I had the same experience trying to see the 4th of July fireworks in an unfamiliar city. It doesn't help that there was very little information online about which roads were closed.
https://www.granola.ai/pricing
reply