~www_lesswrong_com | Bookmarks (692)
-
Mask and Respirator Intelligibility Comparison — LessWrong
Published on December 7, 2024 3:20 AM GMT One of the downsides of wearing a mask...
-
Purging Corrupted Capabilities across Language Models — LessWrong
Published on December 6, 2024 10:56 PM GMTby Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Amirali Abdullah This...
-
Gradient Routing: Masking Gradients to Localize Computation in Neural Networks — LessWrong
Published on December 6, 2024 10:19 PM GMTWe present gradient routing, a way of controlling where...
-
Understanding Shapley Values with Venn Diagrams — LessWrong
Published on December 6, 2024 9:56 PM GMTDiscuss
-
Model Integrity — LessWrong
Published on December 6, 2024 9:28 PM GMTHi! My collaborators at the Meaning Alignment Institute put...
-
Can AI improve the current state of molecular simulation? — LessWrong
Published on December 6, 2024 8:22 PM GMTHey LW! I recently filmed a two-hour long scientific...
-
Experiments are in the territory, results are in the map — LessWrong
Published on December 6, 2024 3:44 PM GMTI recently read Thomas Kuhn's book The Structure of...
-
A car journey with conservative evangelicals - Understanding some British political-religious beliefs — LessWrong
Published on December 6, 2024 11:22 AM GMTI’m heading home from a family wedding this weekend....
-
Frontier Models are Capable of In-context Scheming — LessWrong
Published on December 5, 2024 10:11 PM GMTThis is a brief summary of what we believe...
-
Expevolu, a laissez-faire approach to country creation — LessWrong
Published on December 5, 2024 7:29 PM GMTI write this post to present expevolu[1], a system...
-
Should you be worried about H5N1? — LessWrong
Published on December 5, 2024 9:11 PM GMTEpistemic status: a few people without any particular expertise...
-
Are SAE features from the Base Model still meaningful to LLaVA? — LessWrong
Published on December 5, 2024 7:24 PM GMTShan Chen, Jack Gallifant, Kuleen Sasse, Danielle Bitterman[1]Please read...
-
Are SAE features from the Base Model still meaningful to LLaVA? — LessWrong
Published on December 5, 2024 8:21 PM GMTShan Chen, Jack Gallifant, Kuleen Sasse, Danielle Bitterman[1]Please read...
-
o1 tried to avoid being shut down — LessWrong
Published on December 5, 2024 7:52 PM GMTOpenAI released the o1 system card today, announcing that...
-
More Growth, Melancholy, and MindCraft @3QD [revised and updated] — LessWrong
Published on December 5, 2024 7:36 PM GMTThis is cross-posted from New Savanna.I’ve got a new...
-
OpenAI o1 + ChatGPT Pro release — LessWrong
Published on December 5, 2024 7:13 PM GMT As AI becomes more advanced, it will solve...
-
Announcement: AI for Math Fund — LessWrong
Published on December 5, 2024 6:33 PM GMTRenaissance Philanthropy and XTX Markets today announced the launch...
-
Detection of Asymptomatically Spreading Pathogens — LessWrong
Published on December 5, 2024 6:20 PM GMT Cross-posted from my NAO Notebook. This is an...
-
Countdown — LessWrong
Published on December 5, 2024 5:49 PM GMTTo the survivors, Earth-born and Zentradi alike, who chose...
-
Sam Harris’s Argument For Objective Morality — LessWrong
Published on December 5, 2024 10:19 AM GMTApparently, the following is an argument made by Sam...
-
Model Integrity: MAI on Value Alignment — LessWrong
Published on December 5, 2024 5:11 PM GMTEVERYONE, CALM DOWN!Meaning Alignment Institute just dropped their first...
-
Why muscle tension can be unsexy — LessWrong
Published on December 5, 2024 4:11 PM GMThttps://twitter.com/ChrisChipMonk/status/1864380405690061270Why do we often experience feelings as in the...
-
Higher and lower pleasures — LessWrong
Published on December 5, 2024 1:13 PM GMTI used to think that talk about more sophisticated...
-
Morality as Cooperation Part III: Failure Modes — LessWrong
Published on December 5, 2024 9:39 AM GMTThis is a Part III of a long essay....