~www_lesswrong_com | Bookmarks (706)

Published on April 19, 2025 6:37 PM GMTThis post summarizes some of the research I have been doing for Bootstrap Bio AKA kman and Genesmith TL;DR We currently don’t have a list of all imprinted genes that are important in human development, but further long-read sequencing in adults and in the human placenta is going to get us close to that goal. Measuring DNA...

Published on April 19, 2025 12:47 AM GMTWe don’t always know what we’re looking for until we stop looking for what we are told to want.When I worked as a relationship coach, most people came to me with a list. A neat, itemised checklist of traits their future partner must have. Tall. Intelligent. Ambitious. Spiritual. Funny but not flippant. Driven but not workaholic. Family-oriented...

Published on April 19, 2025 3:37 PM GMTIn the face of any hard problem—reversing climate change, curing cancer, or starting a great novel—modern LLMs can generate thousands of possible solutions relatively cheaply.Most solutions from most prompts are bad: they’re not new relative to the state of the art, not feasible, or not significant enough.But for every thousand ideas an LLM has about how to...

Published on April 19, 2025 2:47 PM GMTThough, given my doomerism, I think the natsec framing of the AGI race is likely wrongheaded, let me accept the Dario/Leopold/Altman frame that AGI will be aligned with the national interest of a great power. These people seem to take as an axiom that a USG AGI will be better in some way than a CCP AGI....

Published on April 19, 2025 2:09 PM GMTI aim to cover a lot of ground, but only briefly. Click through the links for more detailed explanations.Several of the techniques here see general use outside of interpretability. My definitions/references lean towards how they specifically apply to Mechanistic Interpretability Sparse Dictionary Learning describes any ML technique that aims to find a set of “atoms” that can be...

Published on April 19, 2025 11:40 AM GMT Cross-posted from my NAO Notebook. This is an internal strategy note I wrote in November 2024 that I'm making public with some light editing. In my work at the NAO I've been thinking about what I expect to see as LLMs continue to become more capable and get closer to where they can significantly accelerate their...

Published on April 19, 2025 9:12 AM GMTThe ambulance screeched to a halt with the flair of a rock opera outside an apartment block whose hallway smelled like dry leaves, soggy cardboard, and… was that melted cheese? Best not to investigate. Within seconds, my partner—a guy who had tragedy for breakfast with his coffee—confirmed the inevitable: the mother, lifeless, sprawled in the kitchen next...

Published on April 19, 2025 4:29 AM GMTThis is a living document. Crosspost below may not be updated. Click link for the latest version. 2025-04-19 tldr SecureDrop provides less source privacy than journalist privacy, even though it is the source not the journalist who is more likely to be punished for their actions. SecureDrop opsec guide may be overkill for the median whistleblower but...

Published on April 18, 2025 9:20 PM GMTOpenAI has finally introduced us to the full o3 along with o4-mini. Greg Brockman (OpenAI): Just released o3 and o4-mini! These models feel incredibly smart. We’ve heard from top scientists that they produce useful novel ideas. Excited to see their positive impact on people’s daily lives and humanity’s hardest problems! Sam Altman: we expect to release o3-pro...

Published on April 18, 2025 9:15 PM GMTAI Control is a subfield of AI Safety research focused on ensuring the safety of powerful AI systems, particularly under the assumption that they might be misaligned or could become intentionally subversive (A Brief Explanation of AI Control).Unlike AI Alignment, which seeks to build inherently aligned systems, AI Control develops mechanisms to monitor, evaluate, constrain, verify, and...

Published on April 17, 2025 5:12 PM GMTLast fall the Roots of Progress Institute hosted the first annual Progress Conference. 200 people excited about human progress gathered for two days in Berkeley, California, to share ideas in deep conversation, catalyze new projects, and get energized and inspired. Several attendees even said it was the best conference they had ever attended. We shared more about...

Published on April 17, 2025 3:10 PM GMT I do a lot of work on EC2, where I ssh into a few instances I use for specific purposes. Each time I did this I'd get a prompt like: $ ssh_ec2nf The authenticity of host 'ec2-54-224-39-217.compute-1.amazonaws.com (54.224.39.217)' can't be established. ED25519 key fingerprint is SHA256:... This host key is known by the following other names/addresses:...

Published on April 17, 2025 3:10 PM GMTOpenAI has upgraded its entire suite of models. By all reports, they are back in the game for more than images. GPT-4.1 and especially GPT-4.1-mini are their new API non-reasoning models. All reports are that GPT-4.1-mini especially is very good. o3 is the new top of the line ChatGPT reasoning model, with o3-pro coming in a few...

Published on April 17, 2025 2:14 PM GMTThe US is experiencing a great decline in trust. According to the US General Social Survey, people who agreed with the statement "most people can be trusted" went from 49% to 25% between 1984 and 2022. Trust in institutions is also falling. Over that same period trust in the government fell from 42% to 20%. For civil services it...

Published on April 17, 2025 12:31 PM GMTIt seems to me the question of consciousness of LLMs is a bit of a red herring. Instead the salient point is that they are sequence learning systems similar to our cortex (+ hippocampus). Therefore we should expect them to be able to learn sequences. What we should not expect is that they feel pain. In humans that is...

Published on April 17, 2025 11:36 AM GMTWhat is this about?With some parameters we have thus defined probabilistic skills, one can formulate questions for special moments in life to help organize events, routines, and tasks. This approach approaches the atomic model where, even if we cannot precisely pinpoint an electron’s layer, through specific questions we can predict which area our focus lies in.It also...

Published on April 17, 2025 11:04 AM GMTWhat is this about?We often experience complex things (like learning) that can’t be understood just by looking at their pieces. This framework uses ideas from information theory (how systems handle uncertainty) to give us five simple questions for examining our own thinking and behavior.1. The Mega Vector: Information EfficiencyThe “Mega Vector”: Humans as information machines. We organize, transform,...

Published on April 17, 2025 1:04 AM GMTCrossposting from my substack.Note for LW: This post is about the apathy and nonchalance I've been seeing in many peers regarding AGI. There seems to be massive cognitive dissonance (and it isn't straightforward to overcome) – how can we on the one hand talk about things like AIs becoming smarter than humans across all domains, and on...

Published on April 16, 2025 9:47 PM GMTSUMMARY:  ALLFED is making an emergency appeal here due to a serious funding shortfall. Without new support, ALLFED will be forced to cut half our budget in the coming months, drastically reducing our capacity to help build global food system resilience for catastrophic scenarios like nuclear winter, a severe pandemic, or infrastructure breakdown. ALLFED is seeking $800,000 over...

Published on April 16, 2025 9:30 PM GMTMidjourneyThanks to Renaissance Philanthropy for their support of my research on this topic.Why Prodromes?A lot of chronic diseases, particularly autoimmune and neurodegenerative disorders, develop over the course of years, as the patient transitions from “healthy” to “sick”. This may involve the loss of neurons (as in neurodegenerative diseases like Alzheimer’s or Parkinson’s) or the loss of other...

Published on April 15, 2025 6:14 PM GMTOne key hope for mitigating risk from misalignment is inspecting the AI's behavior, noticing that it did something egregiously bad, converting this into legible evidence the AI is seriously misaligned, and then this triggering some strong and useful response (like spending relatively more resources on safety or undeploying this misaligned AI). You might hope that (fancy) internals-based...

Published on April 15, 2025 4:01 PM GMTWelcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.In this newsletter, we cover the launch of AI Frontiers, a new forum for expert commentary on the future of AI. We also discuss AI 2027, a detailed scenario describing how artificial superintelligence might...

Published on April 15, 2025 3:56 PM GMTIntroductionWriting this post puts me in a weird epistemic position. I simultaneously believe that:The reasoning failures that I'll discuss are strong evidence that current LLM- or, more generally, transformer-based approaches won't get us AGIAs soon as major AI labs read about the specific reasoning failures described here, they might fix themBut future versions of GPT, Claude etc....

Published on April 15, 2025 3:30 PM GMTThree big OpenAI news items this week were the FT article describing the cutting of corners on safety testing, the OpenAI former employee amicus brief, and Altman’s very good TED Interview. The FT detailed OpenAI’s recent dramatic cutting back on the time and resources allocated to safety testing of its models. In the interview, Chris Anderson made...