Hacker Newsnew | past | comments | ask | show | jobs | submit | onlyrealcuzzo's commentslogin

You're also not getting the free cooling capacity of the water which makes the panels more efficient - though that probably only drops the total cost 5% or so, but how much extra the heavier supports cost may not be much more...

The average person is spending about $1.50 to $2.00 in electricity per day to drive a car.

This would cost $0.15 to $0.20 per average trip to NOT plug in.

Average person spending $100k on a car would likely pay that without a second thought.


The Cayenne seems to need about 315Wh / mile. I assume a substantial number of them are sold in California, where rates are often above $0.50/kw. I think $1.50 would get you about 9 miles.

I drive a more efficient PHEV and spend much more than $1.50/day.


Hopefully Terra 6 slots somewhat nicely into this space.

I'm finding the bottleneck writing Rust code to be that compiling and running tests is too slow compared to TypeScript - which is unfortunate, because I want all of the guarantees of Rust - I just don't particularly care if it runs at the fastest speed possible - at least not at the prototype stage, or ever for a lot of what I'm doing (though I do want the guarantees regardless).

I wish it could run interpreted to massively speed up development, and that it had a Mull-like mutant testing framework so that mutants didn't take hours and tens-to-hundreds of gigabytes of space.


I ran into this exact issue and had Claude write a test run scheduler to avoid cargo process contention and migrated to nextest within it. I have --release build cycles on my local machine down to about three seconds from what was for the same project 60+ seconds before investing in the changes.

Wait... I thought they said they didn't kill children and that was Iranian propaganda.

> That didn't happen.

> And if it did, it wasn't that bad.

> And if it was, it was AI's fault, not mine.


TL;DR The buck stops in Trumps pocket.

The UI/UX seems impressively bad. DeepSWE's cost curve has a better, more obvious way to sort by only the top level of reasoning to avoid 80% of the graph just being the same 3-5 models at their 8 different reasoning levels...

It's also less clear what a lot of their metrics mean. Does Cost per Task include only things that can be verified to work and passed? As best I can tell, it does not.

I'm less concerned if one model's cost per task is $0.10 and another model's cost is $1.50 if the $0.10 task got it right 1% of the time and the $1.50 model got it right 66% of the time.

An equalized / weighted cost/time per task is much more valuable - being massively penalized for taking a lot of time and ultimately not passing when OTHER models did pass.


I could already run Sol High on 3 concurrent side projects 24/7 and not run out of quota.

This is great, but practically, I'm not going to start working on more side projects.

Perhaps in another 6-12 months I'll be fine to drop down to $20/m instead of $200.


How much does it cost you per month to have that much sol high usage and what do you use, api? Through what? Thank you

$200/mo

A lot of what I'm doing has pretty expensive build/testing processes between iterations - even on a 40 core machine - so I'm not burning tokens 24/7 like some people may.

I'd guess I'm probably spending >50% of the time running tests & build processes & tooling and the remainder is purely burning tokens.

I also have some internal tooling (that I will hopefully open source soon) that makes LLMs substantially more correct (thus more efficient) - so there's that, too.


they said quota so i would imagine the $200 subscription. Probably through Codex or Pi coding agents.

You can now start to add automations on top of typical dev flows.

There are a ton of use cases that open up with cheaper models.

E.g. extensive security scanning on every PR, quality scans, adversarial reviews etc


I already do all that, and a lot more...

> And the ChatGPT subscription lets me use my own harness, so I can hook it up to exe.dev.

This is news to me. Excited to try it out! Thanks.


news to me as well. i thought you were forced to use Codex if you wanted their subscription. I completely ignored it because of that. How do we do it?

With the pi harness it just opens the browser (or gives you a link if you're on headless) and you sign on as usual.

So... We should only communicate in compressed formats?

Yes, but specifically compress the concepts, not necessarily the text encoding. "100 commas" and ",,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,," may be different amounts of ascii data, but they both represent the same concept that's worth around 20-30 bits of semantic information.

They are too concerned with their housing market to raise rates.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: