Media is too big
VIEW IN TELEGRAM
Man has been attempting to train ChatGPT that 2+2=5 for weeks
😁38🤡3👍2😱2❤1🔥1😢1
AI we have a problem: Poisoning of AI Training Datasets is Practical
Researchers show they can poison the LAION-400M and COYO-700M AI training datasets far more cheaply than people assume: just $60 USD.
Prevoiusly confirmed that effective poisoning attacks often require poisoning just 0.01% of the data.
Suggest “automated integrity checking” as a solution — but how does one automatically check the truth and values-alignment of large training datasets?
Paper
Researchers show they can poison the LAION-400M and COYO-700M AI training datasets far more cheaply than people assume: just $60 USD.
Prevoiusly confirmed that effective poisoning attacks often require poisoning just 0.01% of the data.
Suggest “automated integrity checking” as a solution — but how does one automatically check the truth and values-alignment of large training datasets?
Paper
👍5😱3❤2🆒1
Vanderbilt University Office of Diversity deans suspended after controversy over using ChatGPT to write email to students about deadly mass shooting at Michigan State
Villains for using ChatGPT?
Heroes for confirming that condolence messages from big organizations are always fake nonsense and reducing DEI?
Villains for using ChatGPT?
Heroes for confirming that condolence messages from big organizations are always fake nonsense and reducing DEI?
😁9👍4🤣4❤1👏1