🖼️00Frontier AI safety tests may be creating the very risks they're meant to stoptheregister·Carly Page·21 days ago#Q51VArnA#x2f#aisafety#aiml#cybersecurity#rusi#access+6 more🧰Tag tools✨Add tagThink tank warns outsider access to powerful models is governed by patchy controls and a hope nobody dangerous gets in15s0Read later0Read More
