FleetingBits
@fleetingbits.bsky.social
Are base models the dreams of an LLM?
feels like the Apollo Research review of o1 was a bit adversarial - just getting that vibe from the description in the system card
December 7, 2024 at 12:11 AM
feels like the Apollo Research review of o1 was a bit adversarial - just getting that vibe from the description in the system card
It's interesting how many disasters come from a collection of small failures - often because people are not sufficiently motivated to coordinate.
www.youtube.com/watch?v=zRM2...
www.youtube.com/watch?v=zRM2...
The Wild Story of the Taum Sauk Dam Failure
YouTube video by Practical Engineering
www.youtube.com
December 6, 2024 at 1:09 AM
It's interesting how many disasters come from a collection of small failures - often because people are not sufficiently motivated to coordinate.
www.youtube.com/watch?v=zRM2...
www.youtube.com/watch?v=zRM2...
Interesting thread on what social media rewards in academic articles. I think overbroad claims but, you know, you take what you can get.
x.com/0xredJ/statu...
x.com/0xredJ/statu...
x.com
x.com
December 5, 2024 at 5:02 AM
Interesting thread on what social media rewards in academic articles. I think overbroad claims but, you know, you take what you can get.
x.com/0xredJ/statu...
x.com/0xredJ/statu...
Another interesting video - I think the idea that providers should have to stop deployment of their models if the models attempt to escape is reasonable.
Probably the starting point is actually a set of reporting requirements, but I digress...
Probably the starting point is actually a set of reporting requirements, but I digress...
Buck Shlegeris - AI Control [Alignment Workshop]
YouTube video by FAR․AI
www.youtube.com
December 4, 2024 at 12:55 AM
Another interesting video - I think the idea that providers should have to stop deployment of their models if the models attempt to escape is reasonable.
Probably the starting point is actually a set of reporting requirements, but I digress...
Probably the starting point is actually a set of reporting requirements, but I digress...
claimed - AI misuse risk and AI misalignment risk are the same thing form a policy and technical perspective
Richard Ngo – Reframing AGI Threat Models [Alignment Workshop]
YouTube video by FAR․AI
www.youtube.com
December 3, 2024 at 12:28 AM
claimed - AI misuse risk and AI misalignment risk are the same thing form a policy and technical perspective
the most frustrating thing of a lot of papers on safety topics is the refusal to give illustrative real life examples - and often when examples are given, they don't hold up to scrutiny or only weakly make the point that they are supposed to support
December 2, 2024 at 4:42 AM
the most frustrating thing of a lot of papers on safety topics is the refusal to give illustrative real life examples - and often when examples are given, they don't hold up to scrutiny or only weakly make the point that they are supposed to support
I'm starting to really wonder if the issue at OpenAI with safety is that the safety advocates don't understand what it's like to work in a "control function" at a company.
It's pretty brutal work.
It's pretty brutal work.
November 14, 2024 at 9:36 AM
I'm starting to really wonder if the issue at OpenAI with safety is that the safety advocates don't understand what it's like to work in a "control function" at a company.
It's pretty brutal work.
It's pretty brutal work.
I would be interested to see if anyone wants to talk about how a safety organization at a major lab should be designed. I don't hear much discussion of this.
November 14, 2024 at 9:30 AM
I would be interested to see if anyone wants to talk about how a safety organization at a major lab should be designed. I don't hear much discussion of this.
