Comment by Review Bot on FHI (Future of Humanity Institute) has shut down (2005–2024) · 2024-05-09T23:04:29.165Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Cohabitive Games so Far · 2024-05-09T16:57:54.357Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on 6 non-obvious mental health issues specific to AI safety · 2024-05-09T06:51:44.081Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Why I'm doing PauseAI · 2024-05-09T01:49:06.833Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Reconsider the anti-cavity bacteria if you are Asian · 2024-05-08T21:04:53.642Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on What convincing warning shot could help prevent extinction from AI? · 2024-05-07T22:02:22.392Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on My simple AGI investment & insurance strategy · 2024-05-07T19:35:43.022Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on My Objections to "We’re All Gonna Die with Eliezer Yudkowsky" · 2024-05-06T23:28:55.727Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Which skincare products are evidence-based? · 2024-05-06T06:46:19.680Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on What I mean by "alignment is in large part about making cognition aimable at all" · 2024-05-05T10:16:10.484Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Don't Dismiss Simple Alignment Approaches · 2024-05-05T05:49:56.167Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Killing Socrates · 2024-05-05T01:28:30.851Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on My hour of memoryless lucidity · 2024-05-04T13:44:35.158Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Shutting down AI is not enough. We need to destroy all technology. · 2024-05-03T06:23:56.238Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on the QACI alignment plan: table of contents · 2024-05-02T21:48:30.992Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on The "public debate" about AI is confusing for the general public and for policymakers because it is a three-sided debate · 2024-05-02T15:03:32.025Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Why was the AI Alignment community so unprepared for this moment? · 2024-05-02T14:39:49.462Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Ability to solve long-horizon tasks correlates with wanting things in the behaviorist sense · 2024-05-02T09:21:22.592Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on POC || GTFO culture as partial antidote to alignment wordcelism · 2024-05-02T01:27:44.385Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Transformers Represent Belief State Geometry in their Residual Stream · 2024-05-01T17:50:59.273Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on On Not Pulling The Ladder Up Behind You · 2024-05-01T16:58:39.422Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Why Would Belief-States Have A Fractal Structure, And Why Would That Matter For Interpretability? An Explainer · 2024-05-01T16:30:14.710Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Mechanistically Eliciting Latent Behaviors in Language Models · 2024-05-01T13:24:33.420Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Refusal in LLMs is mediated by a single direction · 2024-05-01T02:30:13.547Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Ironing Out the Squiggles · 2024-04-30T23:37:28.656Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Thoughts on seed oil · 2024-04-30T21:23:59.289Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Paul Christiano named as US AI Safety Institute Head of AI Safety · 2024-04-30T20:45:23.270Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Express interest in an "FHI of the West" · 2024-04-30T19:59:53.585Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight · 2024-04-30T19:12:32.949Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Introducing AI Lab Watch · 2024-04-30T19:08:49.526Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on My experience using financial commitments to overcome akrasia · 2024-04-30T18:29:33.331Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Examples of Highly Counterfactual Discoveries? · 2024-04-28T08:06:22.526Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Funny Anecdote of Eliezer From His Sister · 2024-04-24T06:29:48.753Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Pausing AI Developments Isn't Enough. We Need to Shut it All Down · 2024-04-10T21:21:02.874Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on A stylized dialogue on John Wentworth's claims about markets and optimization · 2024-04-09T13:22:18.498Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Parasitic Language Games: maintaining ambiguity to hide conflict while burning the commons · 2024-04-09T12:58:53.202Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on AGI and the EMH: markets are not expecting aligned or unaligned AI in the next 30 years · 2024-04-08T13:55:28.937Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on The Learning-Theoretic Agenda: Status 2023 · 2024-04-08T09:11:34.097Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Algorithmic Improvement Is Probably Faster Than Scaling Now · 2024-04-07T02:47:25.638Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Towards Monosemanticity: Decomposing Language Models With Dictionary Learning · 2024-04-06T09:18:14.560Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Please don't throw your mind away · 2024-04-05T21:54:03.664Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on LLMs for Alignment Research: a safety priority? · 2024-04-05T15:10:42.361Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Recursive Middle Manager Hell · 2024-04-05T15:05:32.508Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on The Translucent Thoughts Hypotheses and Their Implications · 2024-04-05T14:36:10.852Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Discussion with Nate Soares on a key alignment difficulty · 2024-04-05T13:40:17.778Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Against LLM Reductionism · 2024-04-05T11:04:19.862Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on LeCun’s “A Path Towards Autonomous Machine Intelligence” has an unsolved technical alignment problem · 2024-04-05T10:25:14.136Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Attitudes about Applied Rationality · 2024-04-05T01:55:33.665Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on Gradient hacking is extremely difficult · 2024-04-04T18:21:06.284Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

Comment by Review Bot on AI as a science, and three obstacles to alignment strategies · 2024-04-04T09:28:21.337Z · LW · GW

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?