They keep switching the rabbits running before the dogs on the AGI track. Now the doomers are worried not about one model reaching AGI but about agents from multiple models getting superintelligent.
Distributional AGI Safety
https://arxiv.org/pdf/2512.16856
Discussion
Loading...
@jeffjarvis
Bingo! Way to go! 🤡
If we focus on speculative issues about something we don't have ( #AGI ) it looks like our unsolved problems today ( #ai #injections , #agents , #aisafety ) are actually solved. 👏
Anyone interested in research about predicability of solutions of the #travelingsalesmanproblem in context of #multidimension #timetravel ? 🤔
@jeffjarvis
Bingo! Way to go! 🤡
If we focus on speculative issues about something we don't have ( #AGI ) it looks like our unsolved problems today ( #ai #injections , #agents , #aisafety ) are actually solved. 👏