TL;DRThis work replicates and extends the findings of Arditi et al. [1], who studied the refusal mechanism and found that a single direction, obtained through Difference-in-Means…
A ~month ago I left from Chicago to bike (and amtrak) to plzdontkillus in Berkeley. I've been street interviewing/conversing with a wide variety of people I…
Virtually every plan to avert AI-catastrophe assumes legal regulation will remain a reliable tool. Plan A in AI 2040; slowdown in AI 2027, and several other…
tl;dr: whether a model has one tracks modern pretraining, not parameter count, and not instruction-tuning.Here's the intuition almost everyone has about a "global workspace" in a…
Crosspost from: https://inputlogic.substack.com/p/woke-nonsense-in-competitive-debateI. ContextFor the last 2 weeks, I’ve been at a Lincoln-Douglas debate camp—mainly to learn more about philosophical arguments. The instructors and people there…
A corrigible agent "acts opposite the trope of 'be careful what you wish for' by cautiously reflecting on itself as a flawed tool and focusing on…
This replication was done as part of the Second Look Fellowship by Arav Dhoot and supervised by Yixiong Hao and Zephaniah Roe. I am grateful to…
AI is increasingly capable. Suppose we're lucky and the alignment problem gets solved, so AI reliably does what its operators want. But we’re not done yet:…
Epistemic status: a survey, not an argument. I am agnostic on whether any current system is conscious; the claim is only that the question is researchable.This…
Occam’s razor is both intuitive and counter-intuitive. It seems obvious that a simpler explanation is probably better; but it’s not clear why simplicity is raised to…