There is no way this is true, no? This'd mean literally all codebases people are working with have been trained on. There's no way anyone would use these guys if that was the case?
They're supposed to be focused on genuine training improvements over existing data, including via RL. Gathering data under the table is misaligned behavior.
[–] bethekidyouwant 3 days ago
[–] popinman322 3 days ago
[–] degamad 2 days ago
Can you please expand on what you believe RL looks like in this context?