r0b05

293 karmajoined 8 tahun yang lalu

comments

kemarindiscuss

Relevant and well explained.

3 hari yang laludiscuss

Come on, Claude is not that bad.

3 hari yang laludiscuss

That is the conundrum, and I genuinely enjoy building software.

3 hari yang laludiscuss

This is what I do as I have learnt after much frustration.

8 hari yang laludiscuss

You are correct, but please watch out for falling pianos because we appreciate your work.

19 hari yang laludiscuss

I think this is the play

26 hari yang laludiscuss

They are out of Ampere cloud instances as well. Where is a good place to get Ampere instances with similar cost and stability?

bulan laludiscuss

What did you use qwen3.5 4b for?

bulan laludiscuss

Why do need to go with the best model for coding?

2 bulan yang laludiscuss

Okay so the recent outages are also likely due to increased load due to AI assisted development speeding up workflows.

2 bulan yang laludiscuss

It's so weird because github used to be known for rock solid stability and now the entire reputation has changed.

2 bulan yang laludiscuss

What hardware and quant do you run it with?

2 bulan yang laludiscuss

It would be more interesting to know how many simultaneous users this setup can serve. Otherwise I can just say it serves 500 users but not all of them use it at the same time which doesn't communicate the right level of detail.

2 bulan yang laludiscuss

Excellent work

2 bulan yang laludiscuss

How can a single 5090 serve 80 people? Something doesn't add up here.

2 bulan yang laludiscuss

Gosh that is a dark pattern! Now we need to be aware of injected opinions to control the narrative.

2 bulan yang laludiscuss

It's an interesting point but local gpu efficiency is not something I think about when I'm being rate limited or when my subscription costs keep rising.

2 bulan yang laludiscuss

Cool as hell!

2 bulan yang laludiscuss

That's a chatgpt summary. Actual usage would a better test.

2 bulan yang laludiscuss

This is a French model sir