balefulboy

it seems the older models were capped at 10kusd for the runs though?

28 days agodiscuss

Damn, that beam of light was a flashbang. I wouldn't call this tasteful UI design, but maybe I just need to go to sleep.

balefulboy

28 days agodiscuss

Greentext is eh. Very formulaic, in fact very similar to the bottomless pit one, which I'd argue is better because of it's absurdity. I have to ask, did you mention the older GPT version to fable in the prompt?

balefulboy

28 days agodiscuss

i got a 502

balefulboy

last monthdiscuss

METR's time horizon is not a reliable metric of LLM capability growth: https://www.transformernews.ai/p/against-the-metr-graph-codi...

balefulboy

last monthdiscuss

yeah man this sucks. i genuinely do not know how people find this stuff appealing

balefulboy

last monthdiscuss

I still don't know why people are saying this. I don't really code but from what I've heard on here the models haven't improved since Opus 4.5

comments