Linkpost for https://arxiv.org/html/2611.14454v1
Our PIBBSS fellow Damini Kusum wrote an excellent paper on prediction with reflective oracle Solomonoff Induction (rOSI).
Reflec...
Want to know the latest news and articles posted on AI Alignment Forum?
Then subscribe to their feed now! You can receive their updates by email, via mobile or on your personal news page on this website.
See what they recently published below.
Website title: Vercel Security Checkpoint
Is this your feed? Claim it!
Linkpost for https://arxiv.org/html/2611.14454v1
Our PIBBSS fellow Damini Kusum wrote an excellent paper on prediction with reflective oracle Solomonoff Induction (rOSI).
Reflec...
I used to think of "automating alignment" as a natural category. But when I tried to think through the strategic implications, I realised that it depends a lot on the type of work. I'm now thinking of it in three buckets:
Empirical alignment research: design and execution of alignment-relevant experiments (for a given notion of what we’re aiming for)Conceptual al...This post reflects my own takes, and not that of my employer's.
This is a simple idea: before a new model can be deployed internally, you must first test it for a minimum, fixed period.
You can adjust various axes of this proposal:
Duration of the wait: in calendar time, or until you fulfill some condition.What it blocks: external deployment, internal d...METR recently estimated that Anthropic is now making AI progress about twice as fast as its historical rate (they would not be surprised by anything from 1.3x to 3x), and guessed that “perhaps ≈80%” of the <...
METR recently released a report estimating that Anthropic is getting an overall 1.7x acceleration in AI capability progress as a result of AI accelerating their work. As many have noted (see e.g. Ajeya’s post), this 1.7x acceleration implies that...