url
stringlengths
52
124
post_id
stringlengths
17
17
title
stringlengths
2
248
author
stringlengths
2
49
content
stringlengths
22
295k
date
stringclasses
376 values
https://www.lesswrong.com/posts/pxLhbyigKyaFQajW2/freiburg-im-breisgau-germany-acx-meetups-everywhere-fall
pxLhbyigKyaFQajW2
Freiburg im Breisgau Germany - ACX Meetups Everywhere Fall 2024
omar-2
This year's Fall ACX Meetup everywhere in Freiburg im Breisgau. Location: Haus des Engagements, Rehlingstraße 9, 79100 Freiburg – https://plus.codes/8FV9XRQQ+QQ9 Group Link: https://www.rationality-freiburg.de/ If possible read one of the articles listed here: https://www.rationality-freiburg.de/events/2024-10-11-acx-m...
2024-08-29
https://www.lesswrong.com/posts/S3YcFWTpKGyYujJGn/cologne-germany-acx-meetups-everywhere-fall-2024
S3YcFWTpKGyYujJGn
Cologne Germany - ACX Meetups Everywhere Fall 2024
marcel müller
This year's Fall ACX Meetup everywhere in Cologne. Location: Marienweg 43, 50858 Köln – https://plus.codes/9F28WRMX+97 Group Link: https://www.lesswrong.com/groups/2QwpKyXvwiZ53G4HP Contact: marcel_mueller@mail.de
2024-08-29
https://www.lesswrong.com/posts/95hkJvs4jcT4wcZeJ/bremen-germany-acx-meetups-everywhere-fall-2024
95hkJvs4jcT4wcZeJ
Bremen Germany - ACX Meetups Everywhere Fall 2024
JohannWolfgang
This year's Fall ACX Meetup everywhere in Bremen. Location: We meet outside at Café Weserterrassen, near the playground or inside if the weather is really bad. I'll be carrying a Perplexus Epic Ball Labyrinth. – https://plus.codes/9F5C3R9J+8W9 Feel free to bring kids. Contact: ad.fontes@aol.com
2024-08-29
https://www.lesswrong.com/posts/Ksbcudo9uPocMD339/aachen-germany-acx-meetups-everywhere-fall-2024
Ksbcudo9uPocMD339
Aachen Germany - ACX Meetups Everywhere Fall 2024
martin schmidt
This year's Fall ACX Meetup everywhere in Aachen. Location: Cafe Papillon, probably near the entrance, will bring ACX sign – https://plus.codes/9F28Q3JH+8G Group Link: https://t.me/+IiFfbpWDWm1kOGQ6 Contact: acx@enc0.com
2024-08-29
https://www.lesswrong.com/posts/jfF2t5GoJXS4JuMrL/tbilisi-georgia-acx-meetups-everywhere-fall-2024
jfF2t5GoJXS4JuMrL
Tbilisi Georgia - ACX Meetups Everywhere Fall 2024
dmitrii
This year's Fall ACX Meetup everywhere in Tbilisi. Location: BNKR coffee (https://maps.app.goo.gl/VjMviRv9yymSpA1p7) – https://plus.codes/8HH6PQ4J+7H Contact: overfull_jailbird656@simplelogin.com
2024-08-29
https://www.lesswrong.com/posts/oCDjWLZ8HAeMt3e2y/toulouse-france-acx-meetups-everywhere-fall-2024
oCDjWLZ8HAeMt3e2y
Toulouse France - ACX Meetups Everywhere Fall 2024
alfonso
This year's Fall ACX Meetup everywhere in Toulouse. Location: Pizzeria La Pastasciutta (35Bis Rue Gabriel Péri, 31000 Toulouse). We'll meet at the door. – https://plus.codes/8FM3JF43+GW Group Link: https://www.meetup.com/the-friendly-debate/ Please, RSVP by email Contact: barsom.maelwys@gmail.com
2024-08-29
https://www.lesswrong.com/posts/BPXkLi8eEnxyBwprc/paris-france-acx-meetups-everywhere-fall-2024
BPXkLi8eEnxyBwprc
Paris France - ACX Meetups Everywhere Fall 2024
augustin
This year's Fall ACX Meetup everywhere in Paris. Location: In the Carrousel Garden (next to the Tuileries Gardens). We’ll be sitting on the grass near the Museum of Decorative Arts, which is located at the end of the north wing of the Louvre building complex. I’ll bring an ACX sign, and I’ll be wearing a bowtie. – http...
2024-08-29
https://www.lesswrong.com/posts/k9ugieJmWgD3Jmd5v/genoble-france-acx-meetups-everywhere-fall-2024
k9ugieJmWgD3Jmd5v
Genoble France - ACX Meetups Everywhere Fall 2024
Fantin
This year's Fall ACX Meetup everywhere in Genoble. Location: We'll be in the Jardin de Ville, on the lawn near the cable car, with a small ACX Meetup sign. – https://plus.codes/8FQ75PVG+3H Please RSVP on LessWrong so I know how many we are. We can go to a bar or somewhere else afterwards. Contact: fantin.seguin@live.f...
2024-08-29
https://www.lesswrong.com/posts/HEP4noRNnjtcBco2z/bordeaux-france-acx-meetups-everywhere-fall-2024
HEP4noRNnjtcBco2z
Bordeaux France - ACX Meetups Everywhere Fall 2024
trth
This year's Fall ACX Meetup everywhere in Bordeaux. Location: Under the trees, on the waterfront, opposite Quinconces – https://plus.codes/8CPXRCWH+6W Group Link: https://discord.gg/2NBRvz5JbC Please join the Discord server before attending, the exact location might change depending on the weather Contact: tom@rethalle...
2024-08-29
https://www.lesswrong.com/posts/7buezjEFpnepn6mHE/helsinki-finland-acx-meetups-everywhere-fall-2024
7buezjEFpnepn6mHE
Helsinki Finland - ACX Meetups Everywhere Fall 2024
joe nash
This year's Fall ACX Meetup everywhere in Helsinki. Location: Oluthuone Kaisla, Vilhonkatu 4, 00100 Helsinki. I will have a notebook that says "ACX" on the table. – https://plus.codes/9GG65WCW+PW Group Link: https://www.meetup.com/helsinki-slate-star-codex-readers-meetup/ Contact: sschelsinkimeetup@gmail.com
2024-08-29
https://www.lesswrong.com/posts/FEwpwShF6xLFtgFH7/tallinn-estonia-acx-meetups-everywhere-fall-2024
FEwpwShF6xLFtgFH7
Tallinn Estonia - ACX Meetups Everywhere Fall 2024
andrew w
This year's Fall ACX Meetup everywhere in Tallinn. Location: Kohvik Must Puudel – https://plus.codes/9GF6CPPW+J4 Contact: andrew_n_west@yahoo.co.uk
2024-08-29
https://www.lesswrong.com/posts/iQbC4TYQMko6mvPWn/copenhagen-denmark-acx-meetups-everywhere-fall-2024
iQbC4TYQMko6mvPWn
Copenhagen Denmark - ACX Meetups Everywhere Fall 2024
SoerenE
This year's Fall ACX Meetup everywhere in Copenhagen. Location: Rundholtsvej 10, 2300 Copenhagen S – https://plus.codes/9F7JMH38+GFJ Group Link: https://www.lesswrong.com/events/xsAqbxvT8PD8kCgcr/astralcodexten-lesswrong-meetup-5jau RSVP on LessWrong Contact: soeren.elverlin@gmail.com
2024-08-29
https://www.lesswrong.com/posts/PWfY96jf2EWYnaWjs/prague-czech-republic-acx-meetups-everywhere-fall-2024
PWfY96jf2EWYnaWjs
Prague Czech Republic - ACX Meetups Everywhere Fall 2024
jiri-nadvornik
This year's Fall ACX Meetup everywhere in Prague. Location: Dharmasala Teahouse – https://plus.codes/9F2P3CRW+FQ Group Link: https://www.facebook.com/groups/835029216562521/ Contact: nadvornik.jiri@gmail.com
2024-08-29
https://www.lesswrong.com/posts/dCW5gkfY8b7iw2vqs/brno-czech-republic-acx-meetups-everywhere-fall-2024
dCW5gkfY8b7iw2vqs
Brno Czech Republic - ACX Meetups Everywhere Fall 2024
michal-keda
This year's Fall ACX Meetup everywhere in Brno. Location: Skautský institut Brno, 2nd floor, shared office (not ground level main hall) – https://plus.codes/8FXR5JX4+R8 Group Link: https://www.efektivni-altruismus.cz/kalendar-akci/ Contact: adekcz@gmail.com
2024-08-29
https://www.lesswrong.com/posts/niLhSeqa3iusFbRJr/zagreb-croatia-acx-meetups-everywhere-fall-2024
niLhSeqa3iusFbRJr
Zagreb Croatia - ACX Meetups Everywhere Fall 2024
Dominik Tujmer
This year's Fall ACX Meetup everywhere in Zagreb. Location: A Most Unusual Garden (Hendrick's Gin Garden), Horvaćanska cesta 3, Zagreb – https://plus.codes/8FQQQXP3+W55 Group Link: https://t.me/+A8_-NHQnSkhmY2Fk Contact: dominik.tujmer@gmail.com
2024-08-29
https://www.lesswrong.com/posts/ir8GrCEEeDwXmzdMo/sofia-bulgaria-acx-meetups-everywhere-fall-2024
ir8GrCEEeDwXmzdMo
Sofia Bulgaria - ACX Meetups Everywhere Fall 2024
Daniel Bensen
This year's Fall ACX Meetup everywhere in Sofia. Location: Borisova Gradina, Sofia, Bulgaria – https://plus.codes/8GJ5M8GW+P4 Group Link: https://www.lesswrong.com/groups/HGaSdqwqG4SogWfTi Contact: bensen.daniel@gmail.com
2024-08-29
https://www.lesswrong.com/posts/27ivCX6rkRbzM6CeS/ho-chi-minh-city-vietnam-acx-meetups-everywhere-fall-2024
27ivCX6rkRbzM6CeS
Ho Chi Minh City Vietnam - ACX Meetups Everywhere Fall 2024
cygnus
This year's Fall ACX Meetup everywhere in Ho Chi Minh City. Location: Trung Nguyen Legend Coffee at 603 Tran Hung Dao St. – https://plus.codes/7P28QM4P+H5 Group Link: https://www.lesswrong.com/groups/nSoF5ntooah7f4qzj Contact: hiepbq14408@gmail.com
2024-08-29
https://www.lesswrong.com/posts/MANyWjCLk5nL3FoeD/hanoi-vietnam-acx-meetups-everywhere-fall-2024
MANyWjCLk5nL3FoeD
Hanoi Vietnam - ACX Meetups Everywhere Fall 2024
jordine
This year's Fall ACX Meetup everywhere in Hanoi. Location: Ciao Bella Coffee, Alley 132 Vo Chi Cong, Xuan La, Tay Ho, Hanoi – https://plus.codes/7PH73R34+835 Please RSVP on Lesswrong / email me in case of any changes Contact: jordnguyen43@gmail.com
2024-08-29
https://www.lesswrong.com/posts/bq4cF5dNwnBPWXfa7/da-nang-vietnam-acx-meetups-everywhere-fall-2024
bq4cF5dNwnBPWXfa7
Da Nang Vietnam - ACX Meetups Everywhere Fall 2024
egor
This year's Fall ACX Meetup everywhere in Da Nang. Location: Me Coffee Roastery, 2nd floor. 91 Chương D., Bắc Mỹ Phú, Ngũ Hành Sơn, Đà Nẵng 550000, Vietnam – https://plus.codes/7P8C26WP+Q27 If you are planning to come, please contact me on Telegram @Zmaznevegor. https://t.me/Zmaznevegor Contact: zmaznevegor@gmail.com
2024-08-29
https://www.lesswrong.com/posts/wfGa3FXBrih4hNaRo/bankok-thailand-acx-meetups-everywhere-fall-2024
wfGa3FXBrih4hNaRo
Bankok Thailand - ACX Meetups Everywhere Fall 2024
steven_shonts
This year's Fall ACX Meetup everywhere in Bankok. Location: Too Fast To Sleep (Siam) สยาม - 222,222/1-7,224 ซอย Siam Square Soi 1, Pathum Wan, Bangkok 10330 – https://plus.codes/7P52PGVJ+XJ Contact: steven.shonts@gmail.com
2024-08-29
https://www.lesswrong.com/posts/gHXZzbvhZetcBfqYs/taipei-taiwan-acx-meetups-everywhere-fall-2024
gHXZzbvhZetcBfqYs
Taipei Taiwan - ACX Meetups Everywhere Fall 2024
jake and brandon
This year's Fall ACX Meetup everywhere in Taipei. Location: Daan Park - northeast field next to the basketball courts (backup: Learn Bar if it's raining) – https://plus.codes/7QQ32GJP+PG3 Backup location coordinates of Learn Bar: https://plus.codes/7QQ32GMJ+GHR Contact: jakessolo+acxmeetup@gmail.com
2024-08-29
https://www.lesswrong.com/posts/LAzggw5mQTtHtnQzL/singapore-singapore-acx-meetups-everywhere-fall-2024
LAzggw5mQTtHtnQzL
Singapore Singapore - ACX Meetups Everywhere Fall 2024
andrew-8
This year's Fall ACX Meetup everywhere in Singapore. Location: Maxwell (will send more details in email) – https://plus.codes/6PH57RJV+5W Group Link: https://rentry.co/AC6PH57RJV5W. Please send your RSVP email as early as you can because it would be immensely helpful. Feel free to send an email about topic sentences th...
2024-08-29
https://www.lesswrong.com/posts/fLsekQkn5d7NKddCk/auckland-new-zealand-acx-meetups-everywhere-fall-2024
fLsekQkn5d7NKddCk
Auckland New Zealand - ACX Meetups Everywhere Fall 2024
mark-gilmour
This year's Fall ACX Meetup everywhere in Auckland. Location: Cornwall Park Band Rotunda – https://plus.codes/4VMP4Q3Q+RR Bring kids if relevant, feel free to bring some nibbles. Contact: markgilmour@gmail.com
2024-08-29
https://www.lesswrong.com/posts/RgGYH4yj4H3sxLMZz/tokyo-japan-acx-meetups-everywhere-fall-2024
RgGYH4yj4H3sxLMZz
Tokyo (日本語) Japan - ACX Meetups Everywhere Fall 2024
emi-2
This year's Fall ACX Meetup everywhere in Tokyo (日本語). Location: Nakameguro – https://plus.codes/8Q7XJPR4+63 (こちらは日本語の東京ミートアップです)/ This is a Tokyo Meetup in Japanese Contact: gouritekinakai@proton.me
2024-08-29
https://www.lesswrong.com/posts/YktL7xphsHNPB5Dtg/tokyo-english-japan-acx-meetups-everywhere-fall-2024
YktL7xphsHNPB5Dtg
Tokyo (English) Japan - ACX Meetups Everywhere Fall 2024
harold-2
This year's Fall ACX Meetup everywhere in Tokyo (English). Location: Get in touch for the details! – Get in touch for the details! Group Link: https://www.meetup.com/acx-tokyo/ Get in touch for the details! Contact: rationalitysalon@gmail.com
2024-08-29
https://www.lesswrong.com/posts/N5RzecbWEQap7PjBt/ubud-indonesia-acx-meetups-everywhere-fall-2024
N5RzecbWEQap7PjBt
Ubud Indonesia - ACX Meetups Everywhere Fall 2024
river-2
This year's Fall ACX Meetup everywhere in Ubud. Location: Kafe Upstairs – https://plus.codes/6P3QF7P7+CM Group Link: https://chat.whatsapp.com/HydwIF3u7Ve0nfpbc9EtnS Contact: acx.k55uc@passinbox.com
2024-08-29
https://www.lesswrong.com/posts/Z9wa8QhNyeKHmCuuh/jakarta-indonesia-acx-meetups-everywhere-fall-2024
Z9wa8QhNyeKHmCuuh
Jakarta Indonesia - ACX Meetups Everywhere Fall 2024
aud
This year's Fall ACX Meetup everywhere in Jakarta. Location: First Crack Coffee Jl. Bumi https://maps.app.goo.gl/1VBV9GmM51HxLEnL7 – https://plus.codes/6P58QQ7R+42 Please RSVP to my email so I know how many people to expect. Thanks! Contact: helloaud2000@gmail.com
2024-08-29
https://www.lesswrong.com/posts/v5kLN3gobBtyLubye/mumbai-india-acx-meetups-everywhere-fall-2024
v5kLN3gobBtyLubye
Mumbai India - ACX Meetups Everywhere Fall 2024
chetan-kharbanda
This year's Fall ACX Meetup everywhere in Mumbai. Location: Doolally Taproom - Andheri. https://maps.app.goo.gl/gf8U9AgUtbe892678?g_st=com.google.maps.preview.copy – https://plus.codes/7JFJ4RPM+C6 Group Link: https://www.lesswrong.com/groups/MsTdZ4KpJmHFmLrt4 Please RSVP so I know how many people to expect for the seat...
2024-08-29
https://www.lesswrong.com/posts/HSQS8DXFfntGRFuWe/hyderabad-india-acx-meetups-everywhere-fall-2024
HSQS8DXFfntGRFuWe
Hyderabad India - ACX Meetups Everywhere Fall 2024
vatsal
This year's Fall ACX Meetup everywhere in Hyderabad. Location: Yellolife Cafe, 1335h, Road No. 45, Nandagiri Hills, Jubilee Hills, Hyderabad, Telangana 500033, India – https://plus.codes/7J9WCCF5+RH Please RSVP on LessWrong Contact: vmehra@pm.me
2024-08-29
https://www.lesswrong.com/posts/zD2HzeKJuKoszhxy5/chennai-india-acx-meetups-everywhere-fall-2024
zD2HzeKJuKoszhxy5
Chennai India - ACX Meetups Everywhere Fall 2024
sathish-1
This year's Fall ACX Meetup everywhere in Chennai. Location: Besant Nagar Beach – https://plus.codes/7M42X7XC+GP Contact: sathish9289@gmail.com
2024-08-29
https://www.lesswrong.com/posts/LhWcwzcsxWZjFkrnR/bengaluru-india-acx-meetups-everywhere-fall-2024
LhWcwzcsxWZjFkrnR
Bengaluru India - ACX Meetups Everywhere Fall 2024
nihal m
This year's Fall ACX Meetup everywhere in Bengaluru. Location: Matteo coffea, church street – https://plus.codes/7J4VXJF4+PR Group Link: https://www.lesswrong.com/groups/i5vLw9xnG9iwXNQZZ RSVP on the event for october Contact: propwash@duck.com
2024-08-29
https://www.lesswrong.com/posts/QHsefiBpYzXzcXjzk/hong-kong-hong-kong-acx-meetups-everywhere-fall-2024
QHsefiBpYzXzcXjzk
Hong Kong Hong Kong - ACX Meetups Everywhere Fall 2024
max bolingbroke
This year's Fall ACX Meetup everywhere in Hong Kong. Location: Private flat in The Oakhill, 28 Wood Road, Wan Chai – https://plus.codes/7PJP75GG+HP Email me to RSVP and I will let you know which flat number to come to & give you an invite link to the ACX Hong Kong WhatsApp group. For those who couldn't RSVP in time I w...
2024-08-29
https://www.lesswrong.com/posts/3WZKvfT6NDKKYo58x/sydney-australia-acx-meetups-everywhere-fall-2024
3WZKvfT6NDKKYo58x
Sydney Australia - ACX Meetups Everywhere Fall 2024
eliot
This year's Fall ACX Meetup everywhere in Sydney. Location: Lvl 2, 565 George St, Sydney NSW – https://plus.codes/4RRH46F4+98 Group Link: https://meetu.ps/e/.qqqqlrygcmbzb/sqK6x/i Bring a friend! Everyone welcome! Contact: Redeliot@gmail.com
2024-08-29
https://www.lesswrong.com/posts/krgGQXHQuW2oNuu7h/perth-australia-acx-meetups-everywhere-fall-2024
krgGQXHQuW2oNuu7h
Perth Australia - ACX Meetups Everywhere Fall 2024
bianca peterek
This year's Fall ACX Meetup everywhere in Perth. Location: Dôme Café Bassendean (Located in Hawaiian's) West Rd, Bassendean WA 6054 – https://plus.codes/4PWQ3XW3+9G Please find the table with the "ACX meet-up" sign. I'm totally blind, so you'll have to find me and be verbal! Contact: bianca.czatyrko@gmail.com
2024-08-29
https://www.lesswrong.com/posts/5WH7L9nHmtgZyZbY6/melbourne-australia-acx-meetups-everywhere-fall-2024
5WH7L9nHmtgZyZbY6
Melbourne Australia - ACX Meetups Everywhere Fall 2024
allan
This year's Fall ACX Meetup everywhere in Melbourne. Location: Wolf Cafe and Eatery, 21 Lobelia Dr, Altona North VIC 3025. We will have a sign saying "AXC Meetup" written on it – https://plus.codes/4RJ65R4R+3V Group Link: https://www.facebook.com/groups/lesswrongmelbourne/ Contact: winnings_gesture485@simplelogin.com
2024-08-29
https://www.lesswrong.com/posts/ircdrjiRoiAHyPfmd/canberra-australia-acx-meetups-everywhere-fall-2024
ircdrjiRoiAHyPfmd
Canberra Australia - ACX Meetups Everywhere Fall 2024
declan
This year's Fall ACX Meetup everywhere in Canberra. Location: Grease Monkey Braddon – https://plus.codes/4RPFP4GM+R3 Please RSVP by previous Friday for table booking. Contact: declan_t@hotmail.com
2024-08-29
https://www.lesswrong.com/posts/jgxKfCbfgt69umsao/brisbane-australia-acx-meetups-everywhere-fall-2024
jgxKfCbfgt69umsao
Brisbane Australia - ACX Meetups Everywhere Fall 2024
laura-2
This year's Fall ACX Meetup everywhere in Brisbane. Location: The Burrow, West End. We might be either upstairs or downstairs. I will have a sign that says ACX meetup. – https://plus.codes/5R4MG2C7+44M Contact: laura.leighton94@gmail.com
2024-08-29
https://www.lesswrong.com/posts/7gfKZeC5aa6jZudxs/albury-australia-acx-meetups-everywhere-fall-2024
7gfKZeC5aa6jZudxs
Albury Australia - ACX Meetups Everywhere Fall 2024
bk-1
This year's Fall ACX Meetup everywhere in Albury. Location: Mitta Mitta Canoe Club building in Noreuil Park – https://plus.codes/4RM8WW73+2P7 Alcohol free venue, please bring snacks Contact: podcastaffix@gmail.com
2024-08-29
https://www.lesswrong.com/posts/KvrubaeTrYLAtC4B2/istanbul-turkey-acx-meetups-everywhere-fall-2024
KvrubaeTrYLAtC4B2
Istanbul Turkey - ACX Meetups Everywhere Fall 2024
ozge
This year's Fall ACX Meetup everywhere in Istanbul. Location: Kadikoy, Rıhtım, Yeni Iskele Upstairs, Istanbul Kitapcisi Kahve Dunyasi – https://plus.codes/8GGFX2VF+4F This time we organize this meeting together with AI Safety Istanbul Group. Everybody warmly welcomed. Contact: ozgeco@yahoo.com
2024-08-29
https://www.lesswrong.com/posts/eTMPshgDPutbcrS6n/antalya-turkey-acx-meetups-everywhere-fall-2024
eTMPshgDPutbcrS6n
Antalya Turkey - ACX Meetups Everywhere Fall 2024
annalise-tarhan
This year's Fall ACX Meetup everywhere in Antalya. Location: We'll be meeting at the Shakespeare in Beach Park, on the patio. Look for a propped up notebook with ACX in big letters. – https://plus.codes/8G8GVMMC+4VR Contact: annalisetarhan@gmail.com
2024-08-29
https://www.lesswrong.com/posts/wR4shGCwBQiSLX55b/cape-town-south-africa-acx-meetups-everywhere-fall-2024
wR4shGCwBQiSLX55b
Cape Town South Africa - ACX Meetups Everywhere Fall 2024
moyamo
This year's Fall ACX Meetup everywhere in Cape Town. Location: Truth Coffee Roasting, 36 Buitenkant St, Cape Town City Centre - we'll put a sign on the table – https://plus.codes/4FRW3CCF+P3 Please RSVP using LessWrong or email or WhatsApp (+27 79 813 5144), so book I big enough table. Contact: yaseen@mowzer.co.za
2024-08-29
https://www.lesswrong.com/posts/nkMLjsFaNgcCTbiXR/kaduna-state-nigeria-acx-meetups-everywhere-fall-2024
nkMLjsFaNgcCTbiXR
Kaduna State Nigeria - ACX Meetups Everywhere Fall 2024
abdul malik
This year's Fall ACX Meetup everywhere in Kaduna State. Location: Cafe one, Uptown Mall, Zaire Rd – https://plus.codes/7F29FCCJ+8X Contact: maleekcherry510@gmail.com
2024-08-29
https://www.lesswrong.com/posts/hdqEXuhPyLMphhGHd/tel-aviv-israel-acx-meetups-everywhere-fall-2024
hdqEXuhPyLMphhGHd
Tel Aviv Israel - ACX Meetups Everywhere Fall 2024
MissMarble
This year's Fall ACX Meetup everywhere in Tel Aviv. Location: Sarona park, grass area next to Benedict restaurant. I'll have an ACX MEETUP sign and some balloons. – https://plus.codes/8G4P3QCP+MPH Group Link: https://www.facebook.com/groups/5389163051129361 There is a secure location (מרחב מוגן) very close to where we'...
2024-08-29
https://www.lesswrong.com/posts/XLQbeEgufPKG9dt33/haifa-israel-acx-meetups-everywhere-fall-2024
XLQbeEgufPKG9dt33
Haifa Israel - ACX Meetups Everywhere Fall 2024
shai
This year's Fall ACX Meetup everywhere in Haifa. Location: The Goldmund book store located at the talpiot market on ekron 6 street – https://plus.codes/8G4QR262+39 Group Link: https://chat.whatsapp.com/FSclSIRSpdSJ6T5VJT2QAD Looking forward to seeing ya'll at our meetup! Feel free to bring along anyone/anything if you'...
2024-08-29
https://www.lesswrong.com/posts/BWxo4QJah2tGorS4T/baghdad-iraq-acx-meetups-everywhere-fall-2024
BWxo4QJah2tGorS4T
Baghdad Iraq - ACX Meetups Everywhere Fall 2024
mustafa-1
This year's Fall ACX Meetup everywhere in Baghdad. Location: In the Grinders, Zayona. I will sit with a brown – https://plus.codes/8H568FG6+839 please join the group or notify me in any way, I hosted 3 meet ups so far and no attended, so I would not go if no other person at least notified me. If you can't attend, but ...
2024-08-29
https://www.lesswrong.com/posts/oPnFzfZtaoWrqTP4H/solving-adversarial-attacks-in-computer-vision-as-a-baby
oPnFzfZtaoWrqTP4H
Solving adversarial attacks in computer vision as a baby version of general AI alignment
stanislavfort
I spent the last few months trying to tackle the problem of adversarial attacks in computer vision from the ground up. The results of this effort are written up in our new paper Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness (explainer on X/Twitter). Taking inspiration from biology, ...
2024-08-29
https://www.lesswrong.com/posts/6mTAFh8epLvydhTRp/can-ai-agents-learn-to-be-good
6mTAFh8epLvydhTRp
Can AI agents learn to be good?
ram@rachum.com
Hi everyone! My name is Ram Rachum and I'm working on AI Safety research. I want to elicit social behavior in RL agents and use it to achieve AI Safety goals such as alignment, interpretability and corrigibility. I made a guest post on the Future of Life Institute's blog: https://futureoflife.org/ai-research/can-ai-age...
2024-08-29
https://www.lesswrong.com/posts/zPmhxAmEYwKyy29TN/things-i-learned-talking-to-the-new-breed-of-scientific
zPmhxAmEYwKyy29TN
Things I learned talking to the new breed of scientific institution
abhishaike-mahajan
Note: this article is sponsored by and cross-posted to the Good Science Project. They also write a fair bit, and their articles were essential reading for writing this essay! Also, this article would not be possible without the hours of discussion/editing help I’ve had with several people from these institutions, and a...
2024-08-29
https://www.lesswrong.com/posts/K8R3Cpj3szcX7z6Xo/ai-79-ready-for-some-football
K8R3Cpj3szcX7z6Xo
AI #79: Ready for Some Football
Zvi
I have never been more ready for Some Football. Have I learned all about the teams and players in detail? No, I have been rather busy, and have not had the opportunity to do that, although I eagerly await Seth Burn’s Football Preview. I’ll have to do that part on the fly. But oh my would a change of pace and chance to ...
2024-08-29
https://www.lesswrong.com/posts/4TnCJSBYH4fvCkABY/speculations-on-sleep-in-an-age-of-machines
4TnCJSBYH4fvCkABY
Speculations on Sleep in an Age of Machines
cleanwhiteroom
One-liner: Must androids dream of electric sheep? Three-liner: In a thinking network, a vast web of microstates underpin system macrostates. These microstates are expensive to maintain. Processes that locally reduce or collapse informational entropy may be important for thinking things to learn and function. Entropy in...
2024-08-29
https://www.lesswrong.com/posts/zi63ygtsfKrCztuYN/navigating-the-ethical-and-alignment-challenges-of
zi63ygtsfKrCztuYN
Navigating the Ethical and Alignment Challenges of Developing Open-Source AI for Landscape Architecture in a Big Tech-Dominated World
SimonLOLAland
Hello everyone, As part of a collaborative initiative involving designers, researchers, and journalists, we are delving into the potential of AI within landscape architecture, particularly for fields that prioritize sustainability, ecological balance, and community-driven values. One of the pressing concerns we face is...
2024-08-29
https://www.lesswrong.com/posts/Pd3DS7Xx55a9oJsmC/how-to-build-open-source-ai-models-for-landscape-1
Pd3DS7Xx55a9oJsmC
How to build open source AI models for landscape architecture?
SimonLOLAland
Hello everyone, Together with a group of designers, researchers and journalists we are working in a publication on the Application of AI for Planning and Climate Adaptation (SCAPE magazine). While diving into the topic, we have started wondering: how will less profitable and more activist fields like landscape architec...
2024-08-29
https://www.lesswrong.com/posts/rpPpeoBhxKusgcagt/agi-fermi-paradox
rpPpeoBhxKusgcagt
AGI Fermi Paradox
nerd_gatherer
Enrico Fermi originally asked in 1950, "Where are the aliens? Now, in 2024, it is becoming more of a question of: "Where are the AGIs?" Essentially, we have the computing power (the 2011 Watson computer could certainly have trained LaMDA and other large language models; the worlds most powerful supercomputer could alm...
2024-10-27
https://www.lesswrong.com/posts/ogQwinK7njrXA8B35/approval-seeking-playful-evaluation
ogQwinK7njrXA8B35
Approval-Seeking ⇒ Playful Evaluation
JonathanMoregard
For a long time, I related to flirting as a challenge. At stake was my social worth — with the woman holding the power of social approval.1 My role was to perform my part, impress and showcase my best sides. Holding this view meant relinquishing my power. This way of relating has an undercurrent of scarcity — focusing ...
2024-08-28
https://www.lesswrong.com/posts/WYCF3fuK89QBBwqWv/why-do-firms-choose-to-be-inefficient
WYCF3fuK89QBBwqWv
Why do firms choose to be inefficient?
nicholas-d
Firms choose inefficient production technologies for seemingly bizarre reasons. I examine the evidence, and show that this genuinely is worse for everyone, not merely the result of unobserved constraints. I think this can be explained by a model where information is cheap to attain locally but costly to acquire from af...
2024-08-28
https://www.lesswrong.com/posts/uBZcQLmBPiiSyXsc9/automating-llm-auditing-with-developmental-interpretability
uBZcQLmBPiiSyXsc9
Automating LLM Auditing with Developmental Interpretability
htlou
Produced as part of the ML Alignment & Theory Scholars Program - Summer 2024 Cohort, supervised by Evan Hubinger TL: DR We proved that the SAE features related to the finetuning target will change more than other features in the semantic space.We developed an automated model audit method based on this finding.We invest...
2024-09-04
https://www.lesswrong.com/posts/yRjLY3z3GQBJaDuoY/things-that-confuse-me-about-the-current-ai-market
yRjLY3z3GQBJaDuoY
things that confuse me about the current AI market.
DMMF
Paging Gwern or anyone else who can shed light on the current state of the AI market—I have several questions. Since the release of ChatGPT, at least 17 companies, according to the LMSYS Chatbot Arena Leaderboard, have developed AI models that outperform it. These companies include Anthropic, NexusFlow, Microsoft, Mist...
2024-08-28
https://www.lesswrong.com/posts/yP48zaJt7YwFwmLxB/universal-dimensions-of-visual-representation
yP48zaJt7YwFwmLxB
Universal dimensions of visual representation
bogdan-ionut-cirstea
Authors: Zirui Chen, Michael F. Bonner. Quick take: this seems among the strongest evidence yet for the Natural Abstration Hypothesis. Abstract: Do neural network models of vision learn brain-aligned representations because they share architectural constraints and task objectives with biological vision or because they ...
2024-08-28
https://www.lesswrong.com/posts/rtftr6xccNeMfCK4T/leverage-points-for-a-pause
rtftr6xccNeMfCK4T
Leverage points for a pause
remmelt-ellen
What are ways to prevent development of dangerous AI? When I started on this question two years ago, I expected that passing laws to ban dangerous architectures was the way to go. Then I learned about many new ways from other concerned communities. It was overwhelming. Here’s a four-level framework I found helpful for ...
2024-08-28
https://www.lesswrong.com/posts/zgM92GFsgDi5XaSda/deception-and-jailbreak-sequence-2-iterative-refinement
zgM92GFsgDi5XaSda
Deception and Jailbreak Sequence: 2. Iterative Refinement Stages of Jailbreaks in LLM
winnie-yang
Content Warning: This blog post contains examples of harmful language generated by LLM. Note: This blog post summarizes very preliminary results after a "weekend hackathon", inspired by the work by Ball et al. (2024). Motivation and Background Approaches to "jailbreaking" AI models—making them perform harmful actions d...
2024-08-28
https://www.lesswrong.com/posts/3AZkXwcCJZc5CAFQN/how-to-hire-somebody-better-than-yourself
3AZkXwcCJZc5CAFQN
How to hire somebody better than yourself
lcmgcd
I'm no expert but I've made some recommendations that turned out pretty well -- maybe like 5 ever. This post would probably be better if I waited 10 years to write it. Nonetheless, I think my method is far better than what most orgs/corps do. If you have had mad hiring success (judging by what your org accomplished) th...
2024-08-28
https://www.lesswrong.com/posts/fLzbjZLpuEWuX8Z2h/on-agentic-generalist-models-we-re-essentially-using
fLzbjZLpuEWuX8Z2h
On agentic generalist models: we're essentially using existing technology the weakest and worst way you can use it
Yuli_Ban
The bottom of the coffee table is not the ceiling Not long ago, Andrew Ng posted one of the most fascinating tweets I've read in quite some time. It's a longer post, but the main introduction is worthy jumping off from, as it inadvertently answers a question many current AI-skeptics raise about the nature of LLMs. http...
2024-08-28
https://www.lesswrong.com/posts/zXk9Rwy4oFaex7bdd/benefits-of-psyllium-dietary-fiber-in-particular
zXk9Rwy4oFaex7bdd
Benefits of Psyllium Dietary Fiber in Particular
korin43
Psyllium husk is a non-fermenting (no gas or bloating) soluble dietary fiber that improves both constipation and diarrhea (such as with IBS), normalizes blood sugar, reduces LDL ("bad") cholesterol, and can help with weight loss. Each type of dietary fiber has different effects, and a "high fiber" diet in general won't...
2024-08-28
https://www.lesswrong.com/posts/WECqiLtQiisqWvhim/free-will-and-dodging-anvils-aixi-off-policy
WECqiLtQiisqWvhim
Free Will and Dodging Anvils: AIXI Off-Policy
Amyr
This post depends on a basic understanding of history-based reinforcement learning and the AIXI model. I am grateful to Marcus Hutter and the lesswrong team for early feedback, though any remaining errors are mine. The universal agent AIXI treats the environment it interacts with like a video game it is playing; the ac...
2024-08-29
https://www.lesswrong.com/posts/8oX4FTRa8MJodArhj/the-information-openai-shows-strawberry-to-feds-races-to
8oX4FTRa8MJodArhj
The Information: OpenAI shows 'Strawberry' to feds, races to launch it
martinsq
Two new The Information articles with insider information on OpenAI's next models and moves. They are paywalled, but here are the new bits of information: Strawberry is more expensive and slow at inference time, but can solve complex problems on the first try without hallucinations. It seems to be an application or ext...
2024-08-27
https://www.lesswrong.com/posts/RaKWcwhygqpMnFZCp/sb-1047-final-takes-and-also-ab-3211
RaKWcwhygqpMnFZCp
SB 1047: Final Takes and Also AB 3211
Zvi
This is the endgame. Very soon the session will end, and various bills either will or won’t head to Newsom’s desk. Some will then get signed and become law. Time is rapidly running out to have your voice impact that decision. Since my last weekly, we got a variety of people coming in to stand for or against the final v...
2024-08-27
https://www.lesswrong.com/posts/SuNa5usgxRrvAtbyH/lesswrong-email-subscriptions
SuNa5usgxRrvAtbyH
LessWrong email subscriptions?
Raemon
Right now, LessWrong has a fair amount of email subscription options, but they're given in a giant list in your user profile that's kind of annoying to look at.[1] I have a sense that some people – especially newer users, or users who just don't have a habit of coming to LessWrong all the time – might benefit from havi...
2024-08-27
https://www.lesswrong.com/posts/Xmqnuq5eo9inywS7T/am-i-confused-about-the-malign-universal-prior-argument
Xmqnuq5eo9inywS7T
Am I confused about the "malign universal prior" argument?
nostalgebraist
In a 2016 blog post, Paul Christiano argued that the universal prior (hereafter "UP") may be "malign."  His argument has received a lot of follow-up discussion, e.g. in Mark Xu's The Solomonoff Prior is MalignCharlie Steiner's The Solomonoff prior is malign. It's not a big deal. among other posts. This argument never m...
2024-08-27
https://www.lesswrong.com/posts/hsqKp56whpPEQns3Z/why-large-bureaucratic-organizations
hsqKp56whpPEQns3Z
Why Large Bureaucratic Organizations?
johnswentworth
Large bureaucratic organizations have long seemed… strange to me, on an intuitive level. Why do they exist? Like, in a world where the median person is John Wentworth (“Wentworld”), I’m pretty sure there just aren’t large organizations of the sort our world has. Nobody would ever build such an organization, because the...
2024-08-27
https://www.lesswrong.com/posts/CtMX3wNx4PQgK3xPJ/in-defense-of-technological-unemployment-as-the-main-ai
CtMX3wNx4PQgK3xPJ
In defense of technological unemployment as the main AI concern
tailcalled
It seems to me that when normal people are concerned about AI destroying their life, they are mostly worried about technological unemployment, whereas rationalists think that it is a bigger risk that the AI might murder us all, and that automation gives humans more wealth and free time and is therefore good. I'm not en...
2024-08-27
https://www.lesswrong.com/posts/H65uLxFGPuBDLoTso/what-depression-is-like
H65uLxFGPuBDLoTso
What Depression Is Like
Sable
I was thinking to myself about the difficulties I have explaining depression to people, when I thought of a relatively good metaphor for it. Bear with me. Sudoku For anyone unaware, Sudoku is a puzzle where one tries to fill in a 9x9 grid of numbers according to certain rules: Each row, column, and 3x3 square must have...
2024-08-27
https://www.lesswrong.com/posts/SJESBW9ezhT663Sjd/unit-economics-of-llm-apis
SJESBW9ezhT663Sjd
Unit economics of LLM APIs
dschwarz
Disclaimer 1: Our calculations are rough in places; information is sparse, guesstimates abound. Disclaimer 2: This post draws from public info on FutureSearch as well as a paywalled report. If you want the paywalled numbers, email dan@futuresearch.ai with your LW account name and we’ll send you the report for free. Her...
2024-08-27
https://www.lesswrong.com/posts/wrBxEPGE8B2CRYyAn/i-m-doing-yolov8-model-training-but-the-accuracy-rate-is-70
wrBxEPGE8B2CRYyAn
I'm doing Yolov8 model training but the accuracy rate is 70%
sezer-karatas
I'm currently working on training a YOLOv8 model for my project. The goal is to train this model to recognize the product's stock code from a photo sent to a chatbot. I have 1,522 stock codes, with about 10-15 photos for each stock code. Although the number of photos is a bit low, our customers typically send us the sa...
2024-08-27
https://www.lesswrong.com/posts/AoNaKckQJxZcEPpcx/on-nothing
AoNaKckQJxZcEPpcx
On Nothing
Agent Smith
I can't seem to trace it but there's an interesting article on nothing on Wikipedia. The gist of the article is that people have deemed inquiring about nothing a fool's errand, bound to fail! By nothing I refer to that which the fundamental question of metaphysics, "Why is there something rather than nothing?", queries...
2024-08-27
https://www.lesswrong.com/posts/7q8xvwjJBcffQhMfg/real-summer
7q8xvwjJBcffQhMfg
"Real summer"?
duck_master
(epistemic status: personal/metaphysical rambling) Today - yes, that's August 26, 2024 - I took a really, really long nap. The first phase was from about 11:30am to 1pm; the second phase lasted from about 3pm to 4:30pm.[1] The dream itself was kind of incoherent and not worth retelling, except for one thing - bits and ...
2024-08-26
https://www.lesswrong.com/posts/BueeGgwJHt9D5bAsE/soft-nationalization-how-the-usg-will-control-ai-labs
BueeGgwJHt9D5bAsE
Soft Nationalization: how the USG will control AI labs
deric-cheng
Crossposted to the EA Forum. We have yet to see anyone describe a critical element of effective AI safety planning: a realistic model of the upcoming role the US government will play in controlling frontier AI. The rapid development of AI will lead to increasing national security concerns, which will in turn pressure t...
2024-08-27
https://www.lesswrong.com/posts/rhDmAHvoxWwBo2yHW/on-epistemic-autonomy
rhDmAHvoxWwBo2yHW
On epistemic autonomy
santeri-koivula
TL;DR: Epistemic autonomy refers to the degree to which you are able to change your mind without letting outside sources, such as social and financial pressure, affect it. To increase your epistemic autonomy, you can refrain from publishing your opinions, reduce your conflicts of interest, or change your environment, a...
2024-08-31
https://www.lesswrong.com/posts/ZfJwD5TATCKgefwyH/metaculus-s-minitaculus-experiments-collaborate-with-us
ZfJwD5TATCKgefwyH
Metaculus's 'Minitaculus' Experiments — Collaborate With Us
ChristianWilliams
null
2024-08-26
https://www.lesswrong.com/posts/DgKyDTKeGcisEGCnH/gpt-3-5-judges-can-supervise-gpt-4o-debaters-in-capability
DgKyDTKeGcisEGCnH
GPT-3.5 judges can supervise GPT-4o debaters in capability asymmetric debates
charlie-george
Introduction The AI safety debate agenda, proposed by Irving et al. (2018), explores using debates between AI agents to ensure truthful answers from advanced systems. Recently three key debate settings have been studied with LLMs: Information asymmetric debates: Debaters have access to information unavailable to the ju...
2024-08-27
https://www.lesswrong.com/posts/EBT3wxngiBfDFQx4s/my-apartment-art-commission-process
EBT3wxngiBfDFQx4s
My Apartment Art Commission Process
pixx
When I know that I’m going to be moving out from an apartment soon, I commission a digital artist to draw it for me. Then I print it out and I have a cool art piece. If you love your current place but you don’t think you’ll spend the rest of your life there, you should consider doing the same. Digital artists are much ...
2024-08-26
https://www.lesswrong.com/posts/YTZAmJKydD5hdRSeG/would-catching-your-ais-trying-to-escape-convince-ai
YTZAmJKydD5hdRSeG
Would catching your AIs trying to escape convince AI developers to slow down or undeploy?
Buck
I often talk to people who think that if frontier models were egregiously misaligned and powerful enough to pose an existential threat, you could get AI developers to slow down or undeploy models by producing evidence of their misalignment. I'm not so sure. As an extreme thought experiment, I’ll argue this could be har...
2024-08-26
https://www.lesswrong.com/posts/QsstSjDqa7tmjQfnq/wait-our-models-of-semantics-should-inform-fluid-mechanics
QsstSjDqa7tmjQfnq
... Wait, our models of semantics should inform fluid mechanics?!?
johnswentworth
This post is styled after conversations we’ve had in the course of our research, put together in a way that hopefully highlights a bunch of relatively recent and (ironically) hard-to-articulate ideas around natural abstractions. John: So we’ve been working a bit on semantics, and also separately on fluid mechanics. Our...
2024-08-26
https://www.lesswrong.com/posts/Wmnf9kfuxASeBcnbp/day-zero-antivirals-for-future-pandemics
Wmnf9kfuxASeBcnbp
Day Zero Antivirals for Future Pandemics
niko-2
By Brian Wang Ebola tore through Western Africa in 2014, killing an estimated 11,325 people in two years. After the outbreak ended, it took another three years for the first Ebola vaccine by Merck to be approved. When COVID-19 emerged in 2019, by contrast, mRNA vaccines developed by Pfizer and Moderna took just 326 day...
2024-08-26
https://www.lesswrong.com/posts/YxNnFCwq3xrqAwWDk/molecular-dynamics-data-will-be-essential-for-the-next
YxNnFCwq3xrqAwWDk
Molecular dynamics data will be essential for the next generation of ML protein models
abhishaike-mahajan
Introduction I’ve been pondering the thesis behind this post for a few months now, figuring out how to approach it. In my head, it feels plainly obvious, of course we should use molecular dynamics (MD) to help further train proteomics models. But it’s a good exercise to motivate the whole thing from a first-ish-princip...
2024-08-26
https://www.lesswrong.com/posts/t3pCgKGb7KtNdArmk/my-lukewarm-take-on-glp-1-agonists
t3pCgKGb7KtNdArmk
My lukewarm take on GLP-1 agonists
George3d6
Motivation for posting: I read Scott's recent article: https://www.astralcodexten.com/p/why-does-ozempic-cure-all-diseases And it seems to me that scott isn't considering two points: GLP-1s might fix a lot of things because people are metabolically compromised (e.g. literally to the point of having mitochondria that ar...
2024-08-26
https://www.lesswrong.com/posts/BC7qxdosxeDFBddhQ/my-current-model-of-what-an-ai-governance-researcher-does
BC7qxdosxeDFBddhQ
My (current) model of what an AI governance researcher does
johan-de-kock-1
Purpose of this post: We need more people working as AI governance researchers. This post establishes a basic framework for thinking about what this career path entails, and how you might test your fit. I hope to receive feedback on this framework. Epistemic status and disclosure: I have thought about and researched th...
2024-08-26
https://www.lesswrong.com/posts/fQe7zPuGEkM5fZZyM/interview-with-robert-kralisch-on-simulators
fQe7zPuGEkM5fZZyM
Interview with Robert Kralisch on Simulators
WillPetillo
The following is a transcript of a video interview (edited for grammar and readability) with Robert Kralisch on simulator theory and its implications for AI safety. Introduction by Will Petillo: In February 2023, Microsoft launched Bing chat, an AI-powered chatbot based on the same large language model technology that ...
2024-08-26
https://www.lesswrong.com/posts/McEkGKYCB4raWChwd/one-person-s-worth-of-mental-energy-for-ai-doom-aversion
McEkGKYCB4raWChwd
One person's worth of mental energy for AI doom aversion jobs. What should I do?
Lorec
Hi! I'm Lorec, AKA Mack. I made this post 3 years ago: Wanted: Foom-scared alignment research partner I met some great people, but we never got much of anywhere. Since then, technical alignment research in general also has not gotten much of anywhere [ counterexample; other strongish counterexamples I know of include t...
2024-08-26
https://www.lesswrong.com/posts/q3YmKemEzyrcphAeP/darwinian-traps-and-existential-risks
q3YmKemEzyrcphAeP
Darwinian Traps and Existential Risks
KristianRonn
This part 1 in a 3-part sequence summarizes my book, The Darwinian Trap (see part 2 here and part 3 here). The book aims to popularize the concept of multipolar traps and establish them as a broader cause area.  If you find this series intriguing contact me at kristian@kristianronn.com if you have any input or ideas. G...
2024-08-25
https://www.lesswrong.com/posts/JAd8NA8AkMsvTQkGu/diy-lesswrong-jewelry
JAd8NA8AkMsvTQkGu
DIY LessWrong Jewelry
Pear
[There are no affiliate links in this post and I haven't been paid by anyone; I just happened to have bought the charms from Shein. You can probably get similar things on Temu, Aliexpress or Amazon] I made a  cute LessWrong themed necklace/earring set for cheap, here's how. For the necklace, buy a pair of these earring...
2024-08-25
https://www.lesswrong.com/posts/okCHLnuSpJBkpjnQF/meta-on-viewing-the-latest-lw-posts
okCHLnuSpJBkpjnQF
Meta: On viewing the latest LW posts
quiet_NaN
To view all the latest posts on LW without the use of bookmarks or cookies, here are the steps I take: Go to lesswrong.comSwitch from Enriched to LatestClick on Advanced Sorting/FilteringClick on Sorted by Magic (New & Upvoted)Click on New in the column Sorted by This will then allow me to browse through all posts[1] i...
2024-08-25
https://www.lesswrong.com/posts/mu2iJxZWszkKSGgxf/visualizing-small-attention-only-transformers
mu2iJxZWszkKSGgxf
Visualizing small Attention-only Transformers
Wcargo
Visualizing small Attention-only Transformers Work done during an internship at MILES, Paris Dauphine University, under the supervision of Yann Chevaleyre. You can find the git page for the post here. Research has indicated that in large Transformers, facts are primarily stored in the MLP layer rather than the attentio...
2024-11-19
https://www.lesswrong.com/posts/FEc5SfjCbAyJgRkhR/you-should-probably-eat-oatmeal-sometimes
FEc5SfjCbAyJgRkhR
you should probably eat oatmeal sometimes
bhauth
Inspired by all the blog posts I've seen promoting unusual diets, nootropic drugs, unusual sleep cycles, and so on, I've decided to make my own post suggesting some radical lifestyle choice. My suggestion here is, as the title says: you should probably eat oatmeal sometimes. Yes, I know, oats are <2% of global grain pr...
2024-08-25
https://www.lesswrong.com/posts/CixJcx8yrjBQhBiks/referendum-mechanics-in-a-marketplace-of-ideas
CixJcx8yrjBQhBiks
Referendum Mechanics in a Marketplace of Ideas
sustrik
This is a cross post from https://250bpm.substack.com/p/referendum-mechanics-in-a-marketplace. In a referendum, people vote either for or against the proposal and that's it. Right? Wrong! One can definitely make referendums more complex by mixing in unrelated stuff, unnecessary restrictions, and complexities. But that'...
2024-08-25
https://www.lesswrong.com/posts/8YnHuN55XJTDwGPMr/a-gentle-introduction-to-sparse-autoencoders
8YnHuN55XJTDwGPMr
A gentle introduction to sparse autoencoders
nick-jiang
Sparse autoencoders (SAEs) are the current hot topic 🔥 in the interpretability world. In late May, Anthropic released a paper that shows how to use sparse autoencoders to effectively break down the internal reasoning of Claude 3 (Anthropic’s LLM) . Shortly after, OpenAI published a paper successfully applying a simila...
2024-09-02
https://www.lesswrong.com/posts/N9fQpF5hkkqGkrN5N/axrp-episode-35-peter-hase-on-llm-beliefs-and-easy-to-hard
N9fQpF5hkkqGkrN5N
AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization
DanielFilan
YouTube link How do we figure out what large language models believe? In fact, do they even have beliefs? Do those beliefs have locations, and if so, can we edit those locations to change the beliefs? Also, how are we going to get AI to perform tasks so hard that we can’t figure out if they succeeded at them? In this e...
2024-08-24
https://www.lesswrong.com/posts/AFdvSBNgN2EkAsZZA/what-is-it-to-solve-the-alignment-problem-1
AFdvSBNgN2EkAsZZA
What is it to solve the alignment problem? (Notes)
joekc
(I originally wrote this post as some rough notes on defining the alignment problem, with the intention of turning them into something more polished later. I've now started doing that, as part of a broader series introduced here. In particular, the first post in that series covers some of the same ground as section 1 o...
2024-08-24
https://www.lesswrong.com/posts/8344Fm4mjnoXjxXr5/looking-to-interview-ai-safety-researchers-for-a-book
8344Fm4mjnoXjxXr5
Looking to interview AI Safety researchers for a book
jeffreycaruso
If you are or have been employed as an AI Safety Researcher, I'd love to interview you as background for a novel that I'm writing. I'm interested in learning what a day in the life of an AI researcher typically looks like. I'd be happy to include you in the acknowledgments  or keep your participation completely confide...
2024-08-24
https://www.lesswrong.com/posts/CcJ2YWPqcMsWg8vGt/perplexity-wins-my-ai-race-1
CcJ2YWPqcMsWg8vGt
Perplexity wins my AI race
pktechgirl
Perplexity is the first generalized AI chatbot I’ve found useful enough to integrate into any part of my daily workflow, much less across multiple domains. It speeds me up enough that I’m planning an increase in my freelancing rate. Perplexity has three key advantages: It provides citations, cleanly, in context It has ...
2024-08-24
https://www.lesswrong.com/posts/c52pGAaKLDJ6ZAviQ/the-ap-distribution
c52pGAaKLDJ6ZAviQ
The Ap Distribution
criticalpoints
E.T. Jaynes introduces this really interesting concept called the Apdistribution in his book Probability Theory. Despite the book enjoying a cult following, the Ap distribution has failed to become widely-known among aspiring probability theorists. After finishing the relevant chapter in the book, I googled the phrase ...
2024-08-24