Cameron Holmes
@cameronholmes.bsky.social
AI Alignment Research Manager @MATS
Market participant, EA.
Market participant, EA.
I think it's pretty hard to disentangle them really, I was initially skeptical of the (very convenient) argument from the labs about them not being orthogonal, but I'm increasingly buying it.
January 1, 2025 at 9:30 AM
I think it's pretty hard to disentangle them really, I was initially skeptical of the (very convenient) argument from the labs about them not being orthogonal, but I'm increasingly buying it.
When will the first general AI system be devised, tested, and publicly announced?
www.metaculus.com
December 24, 2024 at 9:27 PM
Congratulations!
December 1, 2024 at 11:59 PM
Congratulations!
It would have been an all-too-convenient refrain for the "I don't believe in that sci-fi nonsense" AI Safety scepticism line
December 1, 2024 at 7:55 PM
It would have been an all-too-convenient refrain for the "I don't believe in that sci-fi nonsense" AI Safety scepticism line
Truly an excellent milestone.
Although concessions do follow in (incorrect) episode preferences. Sleepytime falling out of favour was crushing.
Although concessions do follow in (incorrect) episode preferences. Sleepytime falling out of favour was crushing.
November 23, 2024 at 11:54 PM
Truly an excellent milestone.
Although concessions do follow in (incorrect) episode preferences. Sleepytime falling out of favour was crushing.
Although concessions do follow in (incorrect) episode preferences. Sleepytime falling out of favour was crushing.
Yeah I try to follow a similar approach
November 23, 2024 at 6:56 PM
Yeah I try to follow a similar approach
The fora draw a clear distinction between upvotes / agreement votes so I think the culture of upvoting contributions stems from that maybe?
November 23, 2024 at 6:49 PM
The fora draw a clear distinction between upvotes / agreement votes so I think the culture of upvoting contributions stems from that maybe?
Bizarre that was included in the screenshot, doesn't seem like it belongs to the same class as the others at all.
November 23, 2024 at 1:33 PM
Bizarre that was included in the screenshot, doesn't seem like it belongs to the same class as the others at all.
Now grappling with whether I'd be in that group or not.
November 21, 2024 at 11:56 PM
Now grappling with whether I'd be in that group or not.
Not everyone, then we'd have to read them. If only those inclined to make one did then the mere existence of the doc would probably clarify 90% of scenarios.
"Oh they've got one of those docs, we are probably cool"
"Oh they've got one of those docs, we are probably cool"
November 21, 2024 at 11:52 PM
Not everyone, then we'd have to read them. If only those inclined to make one did then the mere existence of the doc would probably clarify 90% of scenarios.
"Oh they've got one of those docs, we are probably cool"
"Oh they've got one of those docs, we are probably cool"
The Settlers of Catan Problem
November 21, 2024 at 9:40 PM
The Settlers of Catan Problem
Hoping this generalizes into alignment research
November 17, 2024 at 7:40 PM
Hoping this generalizes into alignment research
Good idea, for more details that might help: forum.effectivealtruism.org/topics/draft...
Draft Amnesty Week - EA Forum
Draft Amnesty Week is an event running on the EA Forum between March 11th and 17th 2024, where Forum users can publish scrappy, draft-y, or incomplete posts with impunity.
This tag is to be used on ...
forum.effectivealtruism.org
November 13, 2024 at 9:35 AM
Good idea, for more details that might help: forum.effectivealtruism.org/topics/draft...
This is a Draft Amnesty Week #DAW draft. It may not be polished, up to my usual standards, fully thought through, or fully fact-checked.
November 13, 2024 at 6:12 AM
This is a Draft Amnesty Week #DAW draft. It may not be polished, up to my usual standards, fully thought through, or fully fact-checked.