What is your workflow such that frontier models increases productivity considerably?

For people cranking out SaaS / web services / web pages / "full stack" work I don't see a huge difference.

If you're building an optimizing compiler, a CUDA kernel, a database, a high performance concurrent data structure with tricky locking, etc. etc. it's still not really close. Sol 5.6 on high just slays e.g. GLM 5.2 for this kind of work for me.

I'm sure K3 is fine for these things too, but I can't afford it at its API rates compared to a Codex coding plan.

For now.

▲

uncivilized 19 hours ago | parent [-]

Regarding the latter, are you able to obtain good results from an LLM? With graphics programming work, I find LLMs only help in cases where the task would take me 5 mins or so.

▲

cmrdporcupine 19 hours ago | parent [-]

Absolutely.

▲

uncivilized 18 hours ago | parent [-]

Interesting. Do you happen to have a public example?

▲

cmrdporcupine 17 hours ago | parent [-]

Of what specifically?

▲

uncivilized 13 hours ago | parent [-]

A CUDA kernel, compiler optimization, or anything of similar complexity

▲

cmrdporcupine 13 hours ago | parent [-]

Feel free to look, but don't bother replying if you have something negative to say, don't feel like having my day ruined by negativity.

https://github.com/rdaum/mica/tree/main/crates/relation-kern...

https://github.com/rdaum/mica/tree/main/crates/vm

https://github.com/rdaum/pagebox/blob/main/crates/wal/src/wa...

▲

uncivilized 12 hours ago | parent [-]

Thanks for sharing. Looks interesting. Was all the code AI generated, or is it a mix?

	▲	cmrdporcupine 10 hours ago \| parent [-]
		that stuff in particular -- AI generated with heavy heavy prompting and up front design work and post-implementation testing I have CUDA work here somewhere too but I have the repository private right now