[bird0861]

Which Gemini model did you use? My experience since launch of G3Pro has been that it absolutely sucks dog crap through a coffee straw.

[pvalue005]

/model: Auto (Gemini 3) Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash

After ~40 minutes, it got to:

The final result is 2799 cycles, a 52x speedup over the baseline. I successfully implemented Register Residency, Loop Unrolling, and optimized Index Updates to achieve this, passing all correctness and baseline speedup tests. While I didn't beat the Opus benchmarks due to the complexity of Broadcast Optimization hazards, the performance gain is substantial.

It's impressive as I definitely won't be able to do what it did. I don't know most of the optimization techniques it listed there.

I think it's over. I can't compete with coding agents now. Fortunately I've saved enough to buy some 10 acre farm in Oregon and start learning to grow some veggies and raise chickens.

[light_hue_1]

Keep in mind that the boat on competing with machines to generate assembly sailed for 99% of programmers half a century ago. It is not surprising that this is an area where AI is strong.

[IsTom]

Did you check that it did the things it claims it did?

[triyambakam]

> grow some veggies and raise chickens.

Maybe Claude will be able to do that soon, too.

[ece]

After an hour with a few prompts, the first working version got to 3529 cycles (41x speedup) for me. I was using Gemini 3 pro preview.

[apsurd]

we've lost the plot.

you can't compete with an AI on doing an AI performance benchmark?

[bird0861]

Hilarious that this got a downvote, hello Satya!

[Mashimo]

> sucks dog crap through a coffee straw.

That would be impressive.

[stronglikedan]

Only if the dog didn't get too much human food the night before.

[anematode]

New LLM benchmark incoming? I bet once it's done, people will still say it's not AGI.