~www_lesswrong_com | Bookmarks (667)

Published on July 30, 2024 5:36 AM GMTAfter consuming new information, it can be considered:Trivia if I intended to use it solely as entertainment value.Mental Masturbation[1] because while perhaps I enjoyed learning it, I failed to learn something useful that produced a tangible effect.Effective Information which I define as something that had a measurable effect on me.While stimulating myself with new information all day long...

Published on July 30, 2024 12:00 AM GMT A few weeks ago Julia wrote about how we approach kids climbing: The basics: Spot the child if they're doing something where a fall is likely. Don't encourage or help the child to climb something that's beyond their ability to do on their own. If they don't know how to get down, give advice rather than...

Published on July 29, 2024 5:50 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.Listen to the AI Safety Newsletter for free on Spotify or Apple Podcasts.Implications of a Trump administration for AI policyTrump named Ohio Senator J.D. Vance—an AI regulation skeptic—as his pick for vice president. This choice...

Published on July 29, 2024 2:50 PM GMTThis is an informal note on an interpretability illusion I've personally encountered, twice, in two different settingsCausal AnalysisLet's say we have a function f.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none;...

Published on July 29, 2024 10:28 AM GMTI was thinking about how prompt differs from training data in terms of tokenization. If i am to prompt with "solution:" as opposed to "solution: " it seems like it can influence the result, as in training data last token contain some information about next token. If there is token ": T" but my prompt ended in...

Published on July 29, 2024 9:36 AM GMTThis is an informal research note. It is the result of a few-day exploration into positional SAE features conducted as part of Neel Nanda’s training phase of the ML Alignment & Theory Scholars Program - Summer 2024 cohort.Thanks to Andy Arditi, Arthur Conmy and Stefan Heimersheim for helpful feedback. Thanks to Joseph Bloom for training this SAE.SummaryFigure...

Published on July 28, 2024 5:59 PM GMT"Making Beliefs Pay Rent (in Anticipated Experiences)" is one of the most used lessons from Yudkowsky's Sequences.* First, we're going to go over the essay itself. Second, we're going to suggest beliefs we hold. Third, we're going to be specific about what experiences those believes cause us to anticipate.Suggested reading: Making beliefs pay rent: https://www.lesswrong.com/s/7gRSERQZbqTuLX5re/p/a7n8GdKiAZRX86T5ABelief in Belief:...

Published on July 28, 2024 5:13 PM GMTCross-posted from Substack.I.And the sky opened, and from the celestial firmament descended a cube of ivory the size of a skyscraper, lifted by ten thousand cherubim and seraphim. And the cube slowly landed among the children of men, crushing the frail metal beams of the Golden Gate Bridge under its supernatural weight. On its surface were inscribed...

Published on July 28, 2024 12:23 PM GMTI refer to these posts:https://optimists.ai/2023/11/28/ai-is-easy-to-control/https://www.lesswrong.com/posts/hvz9qjWyv8cLX9JJR/evolution-provides-no-evidence-for-the-sharp-left-turnhttps://www.lesswrong.com/posts/CoZhXrhpQxpy9xw9y/where-i-agree-and-disagree-with-eliezerMy (poor, maybe mis-) understanding is that the argument is that as SGD optimizes for "predicting the next token" and we select for systems with very low loss by modifying every single parameter in the neural network (which basically defines the network itself), it seems quite unlikely that we'll have a "sharp left...

Published on July 28, 2024 7:05 AM GMTThe PDF version can be read here.The audio version can be listened to here:Humans have the capacity to form different types of relationships, which are mediated by emotions. We can divide these relationships into two categories: family and social. They create two types of structure: family and society. The family is held together by the pair bond...

Published on July 28, 2024 3:30 AM GMTYouTube link How can we figure out if AIs are capable enough to pose a threat to humans? When should we make a big effort to mitigate risks of catastrophic AI misbehaviour? In this episode, I chat with Beth Barnes, founder of and head of research at METR, about these questions and more. Topics we discuss: What...

Published on July 27, 2024 7:36 PM GMTi. The problem with psychology Psychology and economics are both attempts to study human behavior. While the precise focus may differ, we want to be able to make precise and accurate predictions about how humans respond to stimuli. We can use reasoning to make theoretical predictions about what will occur, and use empirical results to confirm or disconfirm...

Published on July 28, 2024 12:59 AM GMTMelanie Mitchell called the article "excellent". It also got a bit of discussion on HN.(This is an FYI. I don't necessarily approve or endorse the links I post.)Discuss

Published on July 27, 2024 10:32 PM GMTIf you're familiar with SB 1047, I recommend reading the letter in full; it's only 7 pages.I'll go through their list of suggested changes and briefly analyze them, and then make a couple high-level points.  (I am not a lawyer and nothing written here is legal advice.)Major ChangesGreatly narrow the scope of pre-harm enforcement to focus solely...

Published on July 27, 2024 3:28 PM GMTI've listened to some of his videos, and he strikes me as at least rationalist-adjacent.https://www.bryanjohnson.com/I was wondering what people think of him and his ideas, and whether they'd tried out any of his system.I respect that he offers his research for free, and I don't see a problem with him charging for personal consultation.I don't expect all...

Published on July 26, 2024 4:32 PM GMTThe Bay Area rationalist community has an entry problem! Lots of listed groups are dead, the last centralized index disappeared, communication moved to private discord and slacks. This is bad, so we're making a new index, hopefully up to date and as complete as we can!CommunicationDiscord: Bay Area Rationalists: https://discord.gg/EpG4xUVKtfEmail Group: BayAreaLessWrong: https://groups.google.com/g/bayarealesswrongLocal Meetup GroupsTaco Tuesday: by...

Published on July 26, 2024 2:08 PM GMTOn 75 percent or more of the residential land in most major American cities it is illegal to build anything other than a detached single-family home. 95.8 percent of total residential land area in California is zoned as single-family-only, which is 30 percent of all land in the state. Restrictive zoning regulations such as these probably lower...

Published on July 26, 2024 11:18 AM GMT“You should practise acceptance.”“What do you mean?”“You’re being too hard on yourself, you should accept yourself more.”“Sounds reasonable. I think I get the “vibe” of acceptance, but I still feel confused. How do I practise acceptance?”“Mmm I haven’t thought hard about this before. I’m guessing it’s about loving every part of you, even your weaknesses and failures....