X · @huggingface
· X / Twitter
RT Bryan Catanzaro: Open models are more secure.
RT Bryan CatanzaroOpen models are more secure.Nicolas Pinto: The asymmetry problemWhen we started the log analysis, we first used "frontier" models behind commercial APIs. This did **not work**: the analysis requires submitting large volumes of real attack commands, exploit payloads, and C2 artifacts, and these request