Lack of training transparency hampers safety research; synthetic data issues often skill-based

JacquesThibs · x · 2026-08-21

JacquesThibs notes that the lack of transparency regarding AI labs' exact training processes hinders external safety efforts. It is difficult to determine if safety experiments are attacking strawman setups. He cites the claim that "synthetic data destroys models" as an example of a problem that is mostly a skill issue rather than an inherent flaw.

Original post →

More from Safety

Safety channel →