We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Ilya Sutskever
I am this person!
Delegate
Choose a list of delegates
to vote as the majority of them.
Unless you vote directly.
AI researcher, co-founder and former former chief scientist at OpenAI
I am this person!
Location: United States
ai-policy (6)
ai (5)
ai-governance (5)
ai-regulation (5)
ai-safety (5)
existential-risk (4)
agi (3)
ai-ethics (3)
ai-risk (3)
future (3)
ethics (2)
policy (2)
ai-alignment (1)
gov (1)
international-relations (1)
Top
New
-
Pausing AI at human-genius level to solve alignment is safer than either racing to superintelligence or halting entirely
63 opinions
Ilya Sutskever
votes For
and says:
Future AI will be extraordinarily powerful compared to anything that exists today, and dealing with this future power will require unprecedented measures, such as the ones described here. The problem statement is real. This works only if it is done i...
more AI Verified source (Jul 2026)
added 5d ago
-
Ilya Sutskever
votes For
and says:
Future AI will be extraordinarily powerful compared to anything that exists today, and dealing with this future power will require unprecedented measures, such as the ones described here. The problem statement is real. This works only if it is done i...
more AI Verified source (Jul 2026)
added 9d ago
-
Ilya Sutskever
votes For
and says:
Future AI will be extraordinarily powerful compared to anything that exists today, and dealing with this future power will require unprecedented measures, such as the ones described here. The problem statement is real. This works only if it is done i...
more AI Verified source (Jul 2026)
added 10d ago
-
Governments and labs should build the capability for a global slowdown of frontier AI development in case it's needed
155 opinions
Ilya Sutskever
votes For
and says:
Future AI will be extraordinarily powerful compared to anything that exists today, and dealing with this future power will require unprecedented measures, such as the ones described here. The problem statement is real. This works only if it is done ...
more AI Verified source (Jul 2026)
added 11d ago
-
Ilya Sutskever
votes For
and says:
After almost a decade, I have made the decision to leave OpenAI. [...] I'm confident that OpenAI will build AGI that is both safe and beneficial.
AI Verified source (2024)
added 9mo ago
-
Ilya Sutskever
votes For
and says:
After almost a decade, I have made the decision to leave OpenAI. [...] I'm confident that OpenAI will build AGI that is both safe and beneficial.
Unverifiable source (2024)
added 9mo ago
-
Ilya Sutskever
votes For
and says:
I'd like to take a small detour and to give an analogy that will hopefully clarify why more accurate prediction of the next word leads to more understanding, real understanding. Let's consider an example. Say you read a detective novel, [...] then le...
more AI Verified source (Mar 22, 2023)
added 1mo ago
-
Ilya Sutskever
votes For
and says:
added 5mo ago