@farzyness Grok 4.7 needs a few more days to cook.
We might have penalized response length too much (or something) in RL, as it still gives up on hard tasks (that it can do!) too early and isn’t yet sufficiently rigorous in checking its work.
@sharbel Hey man, how are you using Claude models after they banned OAuth? Or did you switched to other models? Can you list them? The answer would greatly help me.
@sharbel Hey man, how are you using Claude models after they banned OAuth? Or did you switched to other models? Can you list them? The answer would greatly help me.