You're only looking at half of the equation here. Following your logic, if my time is worth $100/hr, I should be willing to pay $99/hr for a haircut. But reality is that a haircut isn't just worth some utility value based on time saved, it's worth the lowest amount where suppliers' willingness to provide it at a given quality and buyers' willingness to pay meet.
So while the $99/hr haircut might technically save me money/time, suppliers of haircuts are generally willing to give the same haircut for $30/hr. If one supplier tried to pin their prices to the growth of their customers' income, they would go out of business. That is because the value of the suppliers time isn't increasing at the same rate.
I'm mostly bald... I got tired of paying as much as I did for haircuts and now mostly just use a pair of clippers on myself, since my goal is to take off all of it. I've paid for more beard trims the past few years than haircuts, though I mostly do that myself too.
Note, I usually use clippers on myself about once a week. Sometimes I'll use a shaver to get a closer shave, but generally doesn't matter as I don't care if there's a little growth, which is noticeable unless I literally shave daily anyway... which I'm too lazy to do, and definitely not able to pay someone else to do.
This is pretty incredible to watch. I initially thought she must be pulling some kind of trick to make that look so fluid, but the fact that she is making very small typos and correcting them as she goes make it look very believable. This is really the first time I've watched someone use one of these tools and it feel like a musician using a new kind of instrument.
If you go back to the older videos she has like a decade of experience messing around with modular synths to make music live that is actually listenable.
She is also a main developer on the strudel project. If you want to contribute, it is open source:
Yeah, I'm watching more. These are incredible. I really like how she describes what she's doing in tempo with the music as she does it. The description is basically part of the performance. Really unique and engaging approach.
she is a producer, not making anything innovative music wise (she must have done similar things thousands of times), with a long experience in live music, and she is a/?the? core dev of the tool she is using.
honestly i think the planning is at most a few minutes long (once she decides what she will go for) then she probably let the experience talk.
This is essentially my exact workflow. I also keep the plan markdown files around in the repo to refer agents back to when adding new features. I have found it to be a really effective loop, and a great way to reprime context when returning to features.
Exactly this. I clear the old plans every few weeks.
For really big features or plans I’ll ask the agent to create linear issue tickets to track progress for each phase over multiple sessions. Only MCP I have loaded is usually linear but looking for a good way to transition it to a skill.
In general anything with an API is simply saying "find the auth token at ~/.config/foo.json". It mostly knows the rest endpoints and can figure out the rest
Agreed. The first half of this post is actually interesting, but the second half quickly transforms into an ad. That disappointed me, because I believe the author has something interesting to say.
There is only a sentence worth of interesting in the entire post, and most of that is the quote at the very beginning. The rest is a massive BS cloud. Everything after the word "vacuum" is hogwash.
This first half of this definitely struck a chord. I spent the first three quarters of this year taking care of a terminally ill parent, then seeing them through hospice. If that sort of experience doesn't make a person step back from their life and question what they're doing nothing will.
I decided to step away from my job as an engineering VP and try something I actually wanted to do. It's terrifying, especially in this economy, but I wake up and feel excitement in the morning instead of dread for the first time in as long as I can remember.
I made this comment on the Cursor announcement post:
I wonder about this. Graphite is a fantastic tool that I use every day. Cursor was an interesting IDE a year ago that I don't really see much of a use case for anymore. I know they've tried to add other features to diversify their business, and that's where Graphite fits in for them, but is this the best exit for Graphite? It seems like they could have gotten further on their own, instead of becoming a feature that Cursor bought to try to stay in the game.
I wonder about this. Graphite is a fantastic tool that I use every day. Cursor was an interesting IDE a year ago that I don't really see much of a use case for anymore. I know they've tried to add other features to diversify their business, and that's where Graphite fits in for them, but is this the best exit for Graphite? It seems like they could have gotten further on their own, instead of becoming a feature that Cursor bought to try to stay in the game.
I just checked, and I've had an O'Reilly account since March of 2014 without major interruption, back when it was called Safari. It is by far the best source for high quality tech content out there. There is so much filler content in tech blogs, that I'm happy to pay to get access to high quality.
I must be on some grandfathered plan though, as I'm not paying near $500/year. That is a very steep price.
Same. Mine is grandfathered in price from long ago. I couldn't work without it, although LLMs are becoming a good substitute for some subjects. The mobile app is a roach motel though.
My account is from 2007ish and even cheaper. I just hope there won't ever be a problem with my yearly payment because obviously they won't reopen it on old terms.
Well, it's good business for them and for me. I can access books when it comes to my mind (not that often). They get the money. I would certainly never subscribe again at current rates.
Really good, and glad that you're taking this technique further into a docker network plugin. I wouldn't be surprised to see a Kubernetes CNI appear using this approach, seems entirely viable unless I am missing something.
I'll definitely be coming to check you all out at Kubecon.
I'm a bit surprised to see so many negative comments targeted at HubSpot. I got to final round interviews with them a little while back and came away with a very positive impression. Where does all the hate come from? Just their association with marketing in general and the fight over the book about them?
So while the $99/hr haircut might technically save me money/time, suppliers of haircuts are generally willing to give the same haircut for $30/hr. If one supplier tried to pin their prices to the growth of their customers' income, they would go out of business. That is because the value of the suppliers time isn't increasing at the same rate.