Top postsTop post
TL;DR: We suggest a sanity check for proposed evaluation or AI oversight schemes: Imagine the AI was replaced by a competent, strategic human — someone who knows they might get evaluated and has their own agenda. Would the evaluation still work? When we apply this mental move broadly, to all...
[I was aiming for legibility to a limited extent only. This post got extracted from a bigger post I've been writing and is meant mostly as a reference, and thus it may make more sense in context than in isolation.] (Spiritually related: Yes, It's Subjective, But Why All The Crabs?[1])...
TL;DR: * We introduce a concept we call "entanglement": roughly, the amount of information that the AI has about its environment. * We distinguish between "actual" entanglement between a specific instance of an AI and its environment and "minimum" entanglement corresponding to some task, without which solving the task is...
A Day at AFFINE[1] > “AFFINE was the best month of intellectual exploration I have had the opportunity to engage in, ever. Usually opportunities like this are limited to a day or a weekend, which both limits depth, forces a sprint-type mindset, and generally is quite limiting. At AFFINE I...
TL;DR Evaluation awareness — an AI recognizing it's being evaluated — is a widely discussed concept in AI safety. But there is a closely related concept that we claim is more important: deployment awareness, the AI's ability to recognize when it is not being evaluated and when its actions matter....
We had an influx of applications for the in-person AFFINE Superintelligence Alignment Seminar so we’ve decided to open it up to remote applicants to join online, from anywhere. Key info: * Dates: From 28th April to 28th of May (same as in-person Seminar held in Czechia) * Location: Online (remote...
[A veridically metaphorical explanation of why you shouldn't naïvely cram your life with local optimizations (even for noble or altruistic reasons).] TL;DR: You need Slack to be an effective agent. Slack is fragile, and it is tempting to myopically sacrifice it, and myopic sacrifice makes future myopic sacrificing more likely....