pinkgolem

You are right... Sorry about that comment

A night goes 8 hours or so, so you need 50gw of nuclear

You might want to update your numbers, 1 kwh is somewhere between 50€/kwh to 75 including electronics... No economics of scale, shipping included..

That makes 300B

Eu pricing

Just out of interest, what model are you running?

Are you giving the model context? Industries XYZ with special words zyx

In our use case it's better then the human transcript comparison

I mean some argue the 3d is creativity.

But I am sure people had the same question marks back then, for what's comes next

i mean, i am using 3.8 live to take notes in dialog mode, allowing it to asks questions.. its working fantasticly, switching between german/english with no effort and i have a rather hard accent

no, but the quality jump in the last ~2 years is immense

as is translating text, deepl/google where okaisch, llm's are on another level

marketing is one of those domains, if everyone gets better, no gets better in the end

We did the same, quit happy

i mean, you way is certainly one way..

but ai is perfectly capable of adding/enable matching monitoring so you can check what processes are used... or ai can

I found it impressive for 4 day old product, surprisingly feature complete for my usecase

I mean, the team building that product is talking to customers, it's just 3 people, not five, and no one with a programming background

There is no AI bro software? Claude code is clearly a vibe coded mess, and I would argue the most sucesfull dev software of the last 2 years.

Claude design eliminated figma & power point use for us.

We have a product out there as a test balloon, which only gets architecture & automated reviews.

Dev speed has been incredible, customers love it.

The mess that hey is, is also out there and not yet bankrupt.

And I know at least 1 startup, which only hired a dev after having 20+ B2B customers. They sure do not go around advertising themself as vibe coded.

No, they would not, as one side could keep there evidence, so if after x years the opposite side has Destroit/lost/forgotten there evidence of the transaction you could "prove" something invalid

That is, btw, a thing that is already happening.

One example is people leaving the church, the state deleting the evidence after 10 years, and the church asking for it after 11

I mean, there are very valid reasons behind it.

People are not expected to hold onto there documents forever, humans forget.. and change

Figuring out what happened 3 years ago is hard, figuring out what happened 30 years ago is near impossible & often wrong

i mean you wrote yourself that users are frequently running into this..

i do not know why/in which context you are running this, and how frequently your users are executing forkbombs(i assume school/kids?)

my server is also running 400 something processes, one postgres instance alone is like 40?

i am not sure what you are arguing, but if user frequently run into it.. it seems hostile?

if you have a paid tier which offers more, you do you

if this is internally and you are a service provider to people.. why?

also 256 is not much today, my mac with a few things open is at 800

that might depend on usecase, half of my cost is cache reads usally

i mean, i had multiple gaps filled in the last few month for things i was longing for.. but all for free.

I mean in a market where production cost goes down & competition increases while demand stays the same... That's exactly what I would expect.

I would assume 1/2 are discussed beforehand?

What really important things are human reviews catching in your org?

I just feel more and more like the effort invested in manual reviews is not worth it

The free one in Google has major hallucinations..

Yes, but those are more expensive normally

deepseek is a lab, the models are open weight(atleast after a bit)

they have a somewhat selfhostable model(flash), but are mostly known for having super cheap api access

no zdr ofcourse.

Only if opencode uses the agent sdk/Claude -p

June 15 changes would be the keyword to check, but at least in anthropics case it's... Complicated

Open ai is allowing subscription use, anthropic also paused the effort to stop subscription use.

My argument is, you recognize the style because you know it..

5 years ago, you would not have been able to determine that this was the case, and just have assumed it's a know it all character.

Tell your offshore developers to use caveman or so

You can also change the writing style with a prompt quit easily, if the same person would publish millions of articles, we would also recognize them.

Does it? I found llms to be great for straight conversions

At least if tescoverage is good, but well... That's something llms can also be used for