wetoastfood

Your original design link is requiring a sign in to view it?

Probably more beneficial than "people getting reincinerated" which is how I almost read it but thought that couldn't possibly be it.

This makes me wonder how often you are doing illegal things!

I agree the time it takes to go from planning to deployed is condensing. I'm not sure the hand off is no longer necessary (though it admittedly often feels like it). Perhaps it means we need better ways of planning and collaborating faster and on larger features? So you still end up with a hand off, but it looks different, is maybe more detailed, or spans a wider implementation than we previously might?

Mavo is currently trying to solve a much smaller scope of problems: can it help alleviate some stress that comes from a busy family schedule.

For my family, this means making it not only accessible to me (a developer), but also my wife (who’s not), and potentially other family or helpers (who likely aren’t). That means I’m designing it with accessibility in mind: there’s a full featured GUI so you don’t have to talk to the AI to make changes if you don’t want to, events have built-in owners so you can assign someone or even round robin things and get notified if no one has an event covered, you can share a link with the grandparents to give them details that stay up to date, and, most importantly, you get these things out of the box without having to tinker (but you can go deeper if you prefer).

I’m not aiming for it to be a fully autonomous agent, but I’m definitely thinking about ways to make it more proactive. Events in the system, for example, have an internal notification that can wake Mavo up to check on things without pushing an alert to the house unless it’s needed.

Doesn’t seem like token costs, specifically, are increasing.

Opus cut its token pricing by 66% 6 months ago and it had previously been that higher price consistently for a year and a half (since that model launch).

GPT’s latest model is harder to track since it’s not named, but it’s historically inline with its history.

Not to mention what’s happening with other models like DeepSeek, GLM, and Kimi.

It seems to me the bigger change in costs is based on token appetite. People are discovering agentic capabilities are stronger than they used to be and use cases have broadened because of that. They’ll eventually discover too that these alternative models offer 95% of the intelligence at 20% of the price.

Your framing assumes incompetence across the board which is unlikely to be true for a framework of its popularity. Consider instead competent people are working on projects with different needs and they’ve recognized there are trade offs to both approaches and still decided Tailwind makes sense in their situation.

How do you know that?

I don't think they're measuring the _value_ of the work, just what it would've cost to have humans do it. How long would it take you to produce a report of a specific length on the history of changes to the White House approved by presidents over time that includes citations and links to sources? Let's say 40 hours? Boom. $100 per hour * 40 hours = $4,000 report and 1 weeks worth of effort produced in 15 minutes. Multiply this type of "work" by 400 and you have $1.6M in labor costs and 7.6 years of work.

Are you using 5.1 Thinking? I tended to prefer Claude before this model.

I use models based on the task. They still seem specialized and better at specific tasks. If I have a question I tend to go to it. If I need code, I tend to go to Claude (Code).

I go to ChatGPT for questions I have because I value an accurate answer over a quick answer and, in my experience, it tends to give me more accurate answers because of its (over) willingness to go to the web for search results and question its instincts. Claude is much more likely to make an assumption and its search patterns aren't as thorough. The slow answers don't bother me because it's an expectation I have for how I use it and they've made that use case work really well with background processing and notifications.

Childcare doesn't end at 1 year though. If you look at public schools as child care, most don't start until kindergarten (about 5 years old). What do you do for the remaining 4 years? And during summer break? And after-school care? This program covers all of those.

Forcing parents back into the workforce early is unfortunate and does need to be addressed. However, this program seems to be addressing a different and still vital issue.

It's the single file that is used to define the middleware function that runs. You can import whatever you want into it and decide how "you should combine [your middleware] into a single file."

Texas has all sorts of options. Most power usage here is structured where individuals can select which Retail Electric Provider (REP) to use. They essentially wholesale energy from the grid. I had the (dis)pleasure of searching for a new contract after ours expired so have a refreshed memory of options: - flat rates

- discounted for more or less spend

- credits issued at X usage (which is only good at X specifically because its generally an expensive rate but it’s a marketing ploy for filter based searches).

- free or discounted night time or weekends

- etc.

If you can imagine they charge a certain way, there is likely someone trying it.