Hjalmar_Wijk

Brief in­de­pen­dent in­ves­ti­ga­tion of agents’ be­hav­ior, rea­son­ing and col­lab­o­ra­tion in the OpenAI /​ Hug­ging Face hack­ing incident

Hjal­mar_Wijk’s Shortform

Au­tonomous repli­ca­tion and adap­ta­tion: an at­tempt at a con­crete dan­ger threshold

Ta­boo­ing ‘Agent’ for Pro­saic Alignment