HN user

theflyestpilot

47 karma
Posts2
Comments36
View on HN

you are awesome.

I was thinking about creating a mw2 multiplayer lobby resume. Doing the whole.Create a class thing for job history. absolutely admire this. well done!

I spent 1500 this month. Crunch time on a project so I went for it.

opus 4.5-4.6 costs of about 250 per day

had requests vary between 5 cents and 45.74 per call...

Hand to God, truly not that many calls per day. Just constant steering.

I essentially gave them my lunch money hand over fist.

opus performance was fantastic.

Though the cost confusion with cursor pricing and well known upcharge is why I'm intending to churn next month to go direct to source with Claude code... without the middle man.

compose 1.5 might keep me from churning now that I'm across the finish line on the project. But 1500usd could have given me Claude code for the year.

Frankly they could be making sh*t up with the cost per call... "Nobody is going to know."

Everyone in America is going to be a farmer. There will be a scramble for establishing homestead properties.

Using 3-5 robots to managed whatever small acreage they amassed. From harvesting,canning and storing into a food pantry. Nearly every household has this automated and 100% owned. Robots get repaired by hand or by another robot. Robots or human operation manage Aeroponics/Aquaponics systems for growing more 'exotic' food items

The neighborhood becomes and micro economy where we barter with each other casually for swapping ingredient inventory.

Probably pretty enjoyable for the first generation or two that previously had corporate 9-5s. Maybe the kids growing up in that environment get bored and crave some other type of lifestyle. I would probably be pretty satisfied to spend my day cooking things I grew myself or shared with neighbors.

I mean think about implementing a proper permaculture food system on your property, like Mark Shepard, but automated...

A solar punk-ish future awaits.

people will definitely still fight over water resources. if not more than ever.

idk, just the scenario I fantasize about when owning a few bots. maybe I would take up some craftsmanship of some kind when I'm not debugging some robot that stalled out in the fields.

Hmmm, I think of prompts more like recipes than an algorithm. Similar in both regards, but to the layman, I think prompts are becoming as common practice in daily lives as recipes.

Recipes can be trade secrets but not IP.(Unless it's a super rare circumstance that proves uniqueness in a 'Food Science' way).

I surely hope no one can patent a prompt. That would be an annoying world to live in.

a short story to address explaining what vibe coding is for non developers:

Picture this- are tools like Devin "vibe coding"?

if we break down the mechanics of what interfaces it's looping through:

1)Chat 2)IDE 3)CLI 4)Dev console/Browser

and it's effective copy and pasting what it sees while trying to complete an objective it doesn't fully comprehend. Blissfully ignoring the ramifications of desired combinations as long as decent version control practices are being applied. iterating / adjusting prompts subtlety along the way to debug when getting stuck in a thought loop. changing your prompt from "fix it" to something with more "pizazz" as the key to breaking this cycle.

how is it any different than when I do all this manually?

Slog through this game of 4 square long enough and you can pretty much vibe anything together.

Yah this is what I was afraid of. The UI is kinda rough. I need to go back to the drawing board with building trust in that regard.

I guess technically you could put a spending limit on it, but from your perspective that's a really long onboarding flow.

See the " ...why install? " link.

The PWA really is only useful when it's installed. It makes it really easy to send a recipe from the browser directly into the pwa. Bypassing having to scroll through any ads.

Question. Are you referring to converting a hardcopy of a recipe you already have?

Personally, I like taking a snapshot(s) of a recipe from cookbooks I own. That way I can bring my phone into the kitchen and leave the recipe book out of the splash zone.

I'm pretty sure people these days frequent their phone to obtain/cook with a recipe they got from the internet. Not everyone does, but I'd wager it's pretty common.

Looking for alpha testers to provide feedback on my PWA:

I'm practically always cooking with a phone these days. So, I thought I'd make my own app to combat some of the UIUX challenges I think most home cooks still face these days. Despite a plethora of cooking apps.

It's far from perfect, but I think Android users will be delighted with the Web Share workflow. It's the most frictionless way to obtain recipe from the browser(imo).

It's just a recipe scraper now, but I hope to make it more of a tool to help encourage people to steadily level up their cooking game.

I have a general idea where I want to take the UIUX, but this a side quest that I'm avoiding until I include more core utility/functionality.

I gave my self a deadline to post this by March 31st. So here it is in all it's unpolished glory. ----

Note on pricing/cost(since you must bring your own keys):

Each recipe conversion API costs are typically fractions of a cent. You can pretty much enjoy this "pay as you go" model and not go above $1.00 the whole year. Which seems fair(to me) for you to foot that bill. The costs I incur are the monthly server and development costs. I'll have to come up with a way to afford these if it gets MAU, but I think donations would be all I need to keep this going.

I think the primary reason the avg young person doesn't adopt the plethora of cooking apps out there is that: the payment structure is out of balance. I have a lot of speculations why, but i think I'll leave that for another post. ----

PS- Favorite feature:

cooking facts/quotes.

zeitgeist observations regarding this:

haystack editor is a neat canvas based IDE

codesee recently got acquired by GitKraken (wish they'd sell individual licenses for function maps rather than only for enterprise)

Sometimes I wish I could code within an obsidan.MD canvas

I think a lot of developers generally want to code on a useful node graph IDE ---- the Gource time travel idea is interesting!

Would love to see your idea pulled off! I'm rooting for you