memoryleakgame

Openrouter its just so much easier to use openrouter

Me too, im a bit nervous because I also have evals proving that flash models are actually getting worse at specific task on newer versions and one of my prime use cases peak around flash 3 and tanks in 3.8. So it would be very very horrible for me if they kill old flash models on open router.

Yay google, love living in fear of a vendor that they will rug pull me at any point because they can.

<Rant> I have been working on a product for months and for 1 of the specific models have become the number 3 user and very likely soon the number 2.

Its a google model. The edge cases are crazy to deal with and have taken a long time to find. I am also finding that since it has no fallbacks but no published rate limit I am single handedly taking the model down on what I thought were a reasonable amount of request. There is no other fallback that isn't google. I'm worried that with sustained usage from my users on launch in a few days. Clearly google can't be making that much money on it it im like 10% of the usage and the top 2-3 user of it spending several hundred a month in pre launch testing.

So why would they care to help a small time start up? I will have to jump to a cost effective different model and find the footguns all over again at somepoint.

Not sure where im going with this but just wanted to let others know </rant>

So its a monte carlo simulation but I can't enter growth rate country time horizons or anything like that?

Brother I have a better claude code vibe app than this in an hour

You need to really talk to a financial planner and learn what the proper inputs are

If these benches from their site hold up (they likely wont)

Wouldn't this compress ai revenue like 15x quickly

If they really have a 4.7 opus high equivalent at 1/16 the cost wouldn't this significantly effect all the current capex and planing

Maybe they are getting elon to cover cost

With spec driven development

We are largely now doing proof of functionality and a skim read and making sure it runs locally and deployed to a lower environment

All in all its still time consuming and we have discussed moving to a dark factory but there is still immense value in at least knowing what each file is for and maintaining good isolation of code

800 commits in a year...