I know about each benchmark, but there are infinite ways to game these benchmarks, even ARC.

How many attempts? How is the final score picked, best, average, worse?

Are tools allowed? Is the model cheating with a tool handcrafted for solving ARC AGI?

Also noticing the score is on the “semi-private” benchmark, if thats even a thing.

The private one has a slower score.

I mean, I downvoted because these benchmarks are gamed and only serve as promotion material. Unless there are any other content of high-significance here, I don’t believe this post should rank higher on any feed.

That’s easy, you just join us at our matrix space: https://matrix.to/#/#space:ani.social or https://chat.ani.social/

congratulations

based

maybe Anon is just starving for any non-animal sexual relationship

If only there were some kind of regulations or a regulatory body to prevent this kind of monopoly and abuse.

Thats what they get for training on my code

I miss khyleri art

This guy has a public identity and even has some very starred repos. I wonder if he gave so much as a thought regarding his whole company seeing his disgusting attitude.

Didn’t you know? They have drop rate protection after 50 rows you get a legendary spell

every time Subaru dies, they nerf Emilia’s tits 10%

postman has the latest opus model, just sayin

I wish I had reset by death, keeping in the weekend cycle