LESSWRONG
LW

mushroomsoup
14430
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Instrumental Goals Are A Different And Friendlier Kind Of Thing Than Terminal Goals
mushroomsoup7mo*30

This comment raises some good points, but even "there will be a natural pressure for [subprocesses] to resemble a corrigible agent" seem to be debatable. Again consider the restaurant setting. It is sometime necessary for restaurants to close temporarily for renovation to increase the seating capacity, upgrade equipment, etc. The head chef who decided to renovate will be making the instrumental goals of all the other chefs (make a good food, earn money to stay alive) untenable while they are furloughed. More generally, progress towards terminal goals is not monotonic and thus only focusing on the local topology of the optimization landscape might be insufficient to predict long-horizon trends. 

Reply
Orienting to 3 year AGI timelines
mushroomsoup8mo10

Thanks! The linked article is exactly what I was looking for. Assuming "nationalization" means something like "soft nationalization" does make the timeline seem a lot more plausible. 

Reply
Orienting to 3 year AGI timelines
mushroomsoup9mo60

According to the timeline of the post, AGI will take place during the Trump presidency and much of the nationalization efforts will need to be lead by his administration. However, that seems antithetical to the administrations general ethos of deregulation (at least in the banking and energy sectors). Would it be possible to explain which avenues would lead Trump to nationalize, for example, OpenAI or Antropic?

Reply
3[Translation] The Realities of AI Start-ups in 2025
1d
0
3[Translation] In the Age of AI don't Look for Unicorns
7mo
0
3[Translation] AI Generated Fake News is Taking Over my Family Group Chat
7mo
0
4How are Those AI Participants Doing Anyway?
7mo
0