k__

9 hours agodiscuss

Yeah, DeepSeek V4 (Flash and Pro) is below $0.004 for 1M cache hits.

Even with usage based billing I'm below $1 writing code all day.

k__

2 days agodiscuss

[dead]

k__

6 days agodiscuss

"Europe's rapid warming is partly the result of [...] a drop in the number of tiny polluting particles in the air. This means that less of the Sun's energy is reflected back into space, leaving more energy to heat the Earth's surface."

Hmmm...

k__

7 days agodiscuss

I tried DS4 Pro yesterday for one particular task that Flash struggled with.

That one Pro task cost $1.50 and the whole day of using Flash cost me $5.

k__

9 days agodiscuss

Thanks!

I'll try that.

k__

9 days agodiscuss

Yeah, v4 flash is dirt cheap, but it's running in circles quite often.

Might very well be that a better model is cheaper if it gets things right the first try.

Maybe I should route to a better model when v4flash hasn't solved after a specific number of tokens.

k__

9 days agodiscuss

Nice.

I paid $6 yesterday for DeepSeek V4 Flash on OpenRouter. That's like $120 dollar for a month, and it's not even a good model.

k__

12 days agodiscuss

Llama3.1 instruct seems to be doing okay on that page, mostly because it's dirt cheap.

k__

12 days agodiscuss

So, their incentive is to promote AI music, since they don't have to pay royalties for them.

k__

23 days agodiscuss

Did Nim 3 go all-in on compile time memory management?

k__

23 days agodiscuss

I'm curious about Denuvo's opinion on that.

k__

23 days agodiscuss

Maybe, you could pipe it through T5 or something.

k__

24 days agodiscuss

Training DeepSeek was magnitudes cheaper than training the SOTA models it relied upon.

In theory, other countries should be able to replicate that effort and improve it.

k__

24 days agodiscuss

As I understood it, they were only a US thing anyway. Because of healthcare issues etc.

k__

25 days agodiscuss

I tried some smaller Gemma4 and Qwen3.6 quants on my MBA with M5/16GB and had like 20-60 tokens per second. At 60 it felt pretty okay and that hardware is on the lower end.

I'd assume a Mac with 32-64GB memory would get some reasonable results.

k__

25 days agodiscuss

I thought the joke was that people aren't paying enough money.

k__

27 days agodiscuss

100K seems quite much.

I had the impression, models would get inconsistent after just 3000 words.

k__

last monthdiscuss

Why doesn't Mistral distill?

k__

last monthdiscuss

I tried it with embedded programming, and failed miserably.