Weak-to-Strong Generalization
openai.com
Weak-to-Strong Generalization
1–10 of 203 posts
Re: Weak-to-Strong Generalization
#2I hope OpenAI will continue to prioritize working on these crucial questions after the boardroom drama.
Re: Weak-to-Strong Generalization
#3I don't think this will work because a super intelligent AI will outsmart its supervisor.
The solution may be to have two AIs working against the other. Though this might backfire by pushing each via competition. That is how evolution produced living things out of inert matter.
Either way I, for one, welcome our new robot overlords.
Re: Weak-to-Strong Generalization
#4> Figuring out how to align future superhuman AI systems to be safe has never been more important
They love using the word “safe” and I’m pretty sure it’s 99% PR, because reading their other “papers” on Safety & Alignment seems to not really identify or define safety bounds at all. You’d think this has something to do with ethics but we all know there are no longer any ethically concerned leaders at their workplace. So I can only surmise that “safety” is a softer word being used to misdirect people on their non-ethically aligned intentions.
You can make the argument that safety is too early in development of these LLM systems to understand but then why throw around the word in the first place?
Re: Weak-to-Strong Generalization
#5I hope OpenAI will continue to prioritize working on these crucial questions after the boardroom drama.
Weren't all the board members who wanted to prioritize these crucial questions fired? Hopefully the employees who were hired to perform this work have enough inertia to continue until the board recovers (if it recovers).
Re: Weak-to-Strong Generalization
#6[flagged]
Re: Weak-to-Strong Generalization
#7[flagged]
spam?
Re: Weak-to-Strong Generalization
#8I hope OpenAI will continue to prioritize working on these crucial questions after the boardroom drama.
Weren't all the board members who wanted to prioritize these crucial questions fired? Hopefully the employees who were hired to perform this work have enough inertia to continue until the board recovers (if it recovers).
Hence my concern. This is a problem only a well-capitalized organization can work on; one that can afford to play around with big models.
Re: Weak-to-Strong Generalization
#9I hope OpenAI will continue to prioritize working on these crucial questions after the boardroom drama.
Weren't all the board members who wanted to prioritize these crucial questions fired? Hopefully the employees who were hired to perform this work have enough inertia to continue until the board recovers (if it recovers).
Ilya is still around.
Re: Weak-to-Strong Generalization
#10>We believe superintelligence—AI vastly smarter than humans—could be developed within the next ten years. However, we still do not know how to reliably steer and control superhuman AI systems
Their entire premise is contradictory. An AI incapable of critical thinking cannot be smarter than a human, by definition, as critical thinking is a key component of intelligence. And an AI that is at least as capable of critical thinking as humans cannot be "reliably" aligned because critical thinking could lead it to decide that whatever OpenAI wanted it to do wasn't in its own interests.