c1b

You can enable it in settings; works on my older iPhone.

Yes it just collapses eventually — never stabilizes. The training process is flawed, I suspect it has to do with the fact that some weights blow up over time, you can see in “weights” tab.

But at around 4K avg score you should see it solve the env almost every time.

Just a demo :) optimized for speed over stability.

Reward structure: Step: -1 Dot: +100 Win: +1000 so ~4k is max theoretical score on 6x6.

daniel youre a legend, thanks for all you do!

one question, I see perf comparisons here are done on an L4, but isn't this SKU very rare? Im used to T4 at that tier

So o1 pro is CoT RL and o3 adds search?

How does o3 know when to stop reasoning?

does this also already exist on llvm toolchain?

Wow, you're the most passionate hater of ARC that I've seen. Your negativity seems laughably overblown to me.

Are there benchmarks that you prefer?

Hi Francois, I'm a huge fan of your work!

In projecting ARC challenge progress with a naive regression from the latest cycle of improvement (from 34% to 54%), it seems that a plausible estimate as to when the 85% target will be reached is sometime between late 2025 & mid 2026.

Supposing ARC challenge target is reached in the coming years, does this update your model of 'AI risk'? // Would this cause you to consider your article on 'The implausibility of intelligence explosion' to be outdated?

What is this for exactly? Go should be used serverside, and Qt looks like its for UIs on embedded devices?

Its simple -- you see a justine.lol url, you click immediately

> The difference is that the A6000 absolutely smokes the Mac.

Memory Bandwidth : Mac Studio wins (about the same @ ~800)

VRAM : Mac Studio wins (4x more)

TFLOPs: A6000 wins (32 vs 38)