The AISafety.com Reading Group meets bi-weekly, usually Thursdays at 19:45 UTC. To join, add “soeren.elverlin” on Skype.
Usually, we start with small-talk and a presentation round, then the host gives a summary of the paper for roughly 20 minutes. The summary of the article is uploaded on the Youtube Channel. This is followed by discussion (both on the article and in general) and finally we decide on a paper to read the following week.
Join us by Skype, by adding ‘soeren.elverlin’. Also check out our Facebook Group.
| TITLE | AUTHOR | DATE | SLIDES | PRESENTATION |
|---|---|---|---|---|
| Let’s think about slowing down AI 1 | Katja Grace | 2023-02-09 | https://www.dropbox.com/s/9chis2lupmzcezj/Lets_Think_About_Slowing_Down_AI_1.pptx?dl=0 | https://youtu.be/tY-55ho0W68 |
| Discovering Language Model Behaviors with Model-Written Evaluations | Ethan Perez et al. | 2023-01-19 | https://www.dropbox.com/s/8667fndseo1uerg/Discovering_Language_Model_Behaviors.pptx?dl=0 | https://youtu.be/K332ragiUD8 |
| Our Approach to Alignment Research | Jan Leike et al. | 2023-01-05 | https://www.dropbox.com/s/b3nft68m8rap3z1/Our_Approach_To_Alignment_Research.pptx?dl=0 | https://youtu.be/sPpFiwYqvq4 |
| Counterarguments to the basic AI x-risk case 2 | Katja Grace | 2022-12-15 | https://www.dropbox.com/s/iv91de3iu4d3hxy/Counterarguments_to_the_basic_AI_x_risk_case_2%20-%20Copy.pptx?dl=0 | https://youtu.be/sVkudHH3n34 |
| Counterarguments to the basic AI x-risk case 1 | Katja Grace | 2022-12-01 | https://www.dropbox.com/s/bgzpobga8ih8kpf/Counterarguments_to_the_basic_AI_x_risk_case.pptx?dl=0 | https://youtu.be/hQr08RjkKv4 |
| Is Power-Seeking AI an Existential Risk? | Joseph Carlsmith | 2022-11-17 | https://www.dropbox.com/s/u25x4mn3k3gnmda/Is_Power-Seeking_AI_an_Existential_Threat.pptx?dl=0 | https://youtu.be/RBRb_-CzNow |
| How might we align transformative AI if it’s developed very soon? 3 | Holden Karnofsky | 2022-11-03 | https://www.dropbox.com/s/scju38qywxz33v4/How_Might_We_Align_Transformative_AI_3.pptx?dl=0 | https://youtu.be/8M-6xuLjb94 |
| How might we align transformative AI if it’s developed very soon? 2 | Holden Karnofsky | 2022-10-20 | https://www.dropbox.com/s/odcnybd826jmh6n/How_Might_We_Align_Transformative_AI_2.pptx?dl=0 | https://youtu.be/OfSWc7ByYYA |
| How might we align transformative AI if it’s developed very soon? 1 | Holden Karnofsky | 2022-10-06 | https://www.dropbox.com/s/ywp43o78otn8n22/How_Might_We_Align_Transformative_AI_1.pptx?dl=0 | https://youtu.be/93JuWY_TpWg |
| Where I agree and disagree with Eliezer 3 | Paul Christiano | 2022-09-22 | https://www.dropbox.com/s/y65v7itfoikca5j/Where_I_Agree_And_Disagree_With_Eliezer_3.pptx?dl=0 | https://youtu.be/8XWbPDvKgM0 |
| Where I agree and disagree with Eliezer 2 | Paul Christiano | 2022-09-08 | https://www.dropbox.com/s/7u5864sh2e2zd0z/Where_I_Agree_And_Disagree_With_Eliezer_2.pptx?dl=0 | https://youtu.be/a2qTNuD1Sn8 |
| Where I agree and disagree with Eliezer 1 | Paul Christiano | 2022-08-25 | https://www.dropbox.com/s/84573371ryib5o9/Where_I_Agree_And_Disagree_With_Eliezer_1.pptx?dl=0 | https://youtu.be/V8R0s8tesM0 |
| 20 comments on Corrigibility | Eliezer Yudkowsky et al. | 2022-08-11 | https://www.dropbox.com/s/dwcw4gnp6veg7lo/20_Tags_on_Corrigibility.pptx?dl=0 | https://youtu.be/A7dlTO33qd8 |
| Propositions Concerning Digital Minds and Society 2 | Nick Bostrom et al. | 2022-07-14 | https://www.dropbox.com/s/204z643q49c9y4h/Propositions%20Concerning%20Digital%20Minds%20and%20Society%202.pptx?dl=0 | https://youtu.be/r3aLmfsv9Aw |
| Propositions Concerning Digital Minds and Society 1 | Nick Bostrom et al. | 2022-06-30 | https://www.dropbox.com/s/6eozittckmhejxt/Propositions%20Concerning%20Digital%20Minds%20and%20Society%201.pptx?dl=0 | https://youtu.be/4WopVD9p4wg |
| A Generalist Agent 2 | Scott Reed et al. | 2022-06-16 | https://www.dropbox.com/s/r1sxot1srh6wdcj/A_Generalist_Agent%202.pptx?dl=0 | https://youtu.be/Z0PoEeHvewk |
| A Generalist Agent 1 | Scott Reed et al. | 2022-06-02 | https://www.dropbox.com/s/1obul9kz7m05l6o/A_Generalist_Agent.pptx?dl=0 | https://youtu.be/_DbyjSbczQw |
| MIRI announces new ‘Death With Dignity’ strategy | Eliezer Yudkowsky | 2022-05-19 | https://www.dropbox.com/s/n960rhxupuyj93o/MIRI_Announces_New_Strategy.pptx?dl=0 | https://youtu.be/u6ppY0OF6HE |
| Eliciting Latent Knowledge 2 | Paul Christiano et al. | 2022-05-05 | https://www.dropbox.com/s/bzw04mi70fnpcvj/Eliciting_Latent_Knowledge_2.pptx?dl=0 | https://youtu.be/hAKMMdapqWc |
| Eliciting Latent Knowledge 1 | Paul Christiano | 2022-04-21 | https://www.dropbox.com/s/vu6hwnp2xi64l2i/Eliciting_Latent_Knowledge_1.pptx?dl=0 | https://youtu.be/jhJ0_nLGyiw |
| Democratising Risk: In Search of a Methodology to Study Existential Risk 3/3 | Carla Zoe Cremer et al. | 2022-03-31 | https://www.dropbox.com/s/i4qrerhi9na2r8h/Democratizing_Risk_3.pptx?dl=0 | https://youtu.be/whL0OXPkvWo |
| Democratising Risk: In Search of a Methodology to Study Existential Risk 2/3 | Carla Zoe Cremer et al. | 2022-03-17 | https://www.dropbox.com/s/k2luzy62n0c692h/Democratizing_Risk_2.pptx?dl=0 | https://youtu.be/_K02aeKNx3Q |
| Democratising Risk: In Search of a Methodology to Study Existential Risk 1/3 | Carla Zoe Cremer et al. | 2022-03-03 | https://www.dropbox.com/s/6obocbagbv3fqd4/Democratizing_Risk_1.pptx?dl=0 | https://youtu.be/VqXulKAcjDk |
| A General Language Assistant as a Laboratory for Alignment | Jared Kaplan et al. | 2022-02-17 | https://www.dropbox.com/s/ebbwwknrss8e1bx/A_General_Language_Assistant_as_a_Laboratory_for_Alignment_Research.pptx?dl=0 | https://youtu.be/hAxGLNUYaG8 |
| Digital People Would Be An Even Bigger Deal | Holden Karnofsky | 2022-02-03 | https://www.dropbox.com/s/bgldqb7xixftpxb/Question.pptx?dl=0 | https://youtu.be/SOSULGb1ff0 |
| Finetuned Language Models are Zero-Shot Learners | Jason Wei et al. | 2022-01-13 | https://www.dropbox.com/s/ux4gl0kvpy0aw9b/Finetuned_Language_Models_are_Zero_Shot_Learners.pptx?dl=0 | https://youtu.be/3HcVqQdmpu8 |
| Treacherous Turns from Deep Learning | Søren Elverlin | 2021-12-30 | https://www.dropbox.com/s/l3uyrek0nl97epm/Treacherous_Turns_From_Deep_Learning_Truncated.pdf?dl=0 | https://youtu.be/zC8qNrz1TXw |
| Soares, Tallinn, and Yudkowsky discuss AGI cognition | Eliezer Yudkowsky et al. | 2021-12-16 | https://www.dropbox.com/s/5m5owhtzvdmxsai/Soares_Tallinn_and_Yudkowsky_discuss.pptx?dl=0 | https://youtu.be/kpZeUPsq_bY |
| Beyond fire alarms: freeing the groupstruck | Katja Grace | 2021-12-02 | https://www.dropbox.com/s/ypvddpaktye7wju/Beyond_FIre_Alarms.pptx?dl=0 | https://youtu.be/9PyEBLDtQ9k |
| Distinguishing AI takeover scenarios | Sam Clarke and Sammy Martin | 2021-11-18 | https://www.dropbox.com/s/niczx6p49v3zn5r/Distinguishing_AI_takeover_scenarios.pptx?dl=0 | https://youtu.be/OyeQj-aSwzY |
| A Theoretical Computer Science Perspective on Consciousness | Manuel and Lenore Blum. | 2021-10-28 | ||
| Recursively Summarizing Books with Human Feedback | Paul Christiano et al. | 2021-10-14 | https://www.dropbox.com/s/sns7l1f6rexlz03/Recursively_Summarizing_Books.pptx?dl=0 | https://youtu.be/mZ59IImWwkg |
| “A brief review of the reasons multi-objective RL could be important in AI Safety Research | Ben Smith et al. | 2021-09-30 | https://www.dropbox.com/s/2ig2l4sq4g5dthw/Multi_Objective_Reinforcement_learning_for_AI_Safety.pptx?dl=0 | https://youtu.be/W0x1NKBA2k0 |
| AISafety.com | Søren Elverlin | 2021-09-16 | https://www.dropbox.com/s/tffk3jx3hpv8y6w/AISafetycom.pptx?dl=0 | https://youtu.be/07oW7PsRyiA |
| Learning to summarize from human feedback | Paul Christiano et al. | 2021-09-01 | https://www.dropbox.com/s/slhudqy7tbop530/Learning_to_summarize_%20from%20human_feedback.pptx?dl=0 | https://youtu.be/68CrM_HFhi4 |
| What does GPT-3 understand? Symbol grounding and Chinese rooms | Stuart Armstrong | 2021-08-19 | https://www.dropbox.com/s/cif6eu7lu86tsab/What_Does_GPT3_Understand.pptx?dl=0 | https://youtu.be/SoDotLxRsGY |
| MIRI comments on Cotra’s ‘Case for Aligning Narrowly Superhuman Models | Eliezer Yudkowsky and Evan Hubinger | 2021-08-05 | https://www.dropbox.com/s/llnfar7k339255q/MIRI_Comments_on_Cotras_Aligning_Narrowly_Superhuman_Models.pptx?dl=0 | https://youtu.be/wW7_b0yO1HU |
| The case for aligning narrowly superhuman models | Ajeya Cotra | 2021-07-22 | https://www.dropbox.com/s/enu29q9tadg0s25/The_Case_For_Aligning_Narrowly_Superhuman_Models.pptx?dl=0 | https://youtu.be/ISxu8lvR8Yw |
| Another (outer) alignment failure story | Paul Christiano | 021-07-08 | https://www.dropbox.com/s/odaxoc7ukl4l7tp/Anothe_outer_alignment_failure_story.pptx?dl=0 | https://youtu.be/hYL8UMDIDFM |
| AI Risk Skepticism 2/2 | Roman Yampolskiy | 2021-06-24 | https://www.dropbox.com/s/vpcjzbp8h88t55l/AI_Risk_Skepticism_2.pptx?dl=0 | https://youtu.be/usKTc0ntZv8 |
| Is AI Safety a Progressive Science? | John Fox | 2021-06-17 | https://youtu.be/5D8zELMw_8k | |
| AI Risk Skepticism 1/2 | Roman Yampolskiy | 2021-06-10 | https://www.dropbox.com/s/b18n8uxw4q8px60/AI_Risk_Skepticism.pptx?dl=0 | https://youtu.be/qjmy0LKGq5s |
| Intelligence and Unambitiousness Using Algorithmic Information Theory | Michael Cohen | 2021-05-27 | https://youtu.be/PLCaPMBnsLc | |
| Conversation with Ernie Davis | Robert Long | 2021-05-20 | https://www.dropbox.com/s/kn05w1vgomha0lm/Conversation_With_Ernie_Davis.pptx?dl=0 | https://youtu.be/5ErMITZinhA |
| Conversation with Rohin Shah | Asya Bergal et al. | 2021-05-06 | https://www.dropbox.com/s/bwgyv8s54jnu9xi/Conversation_With_Rohin_Shah.pptx?dl=0 | https://youtu.be/8AR4WMXaUdk |
| Draft Report on AI Timelines | Ajeya Cotra | 2021-04-22 | https://www.dropbox.com/s/t161zr3n99tjijx/Draft_report_on_ai_timelines.pptx?dl=0 | https://youtu.be/NR7flenPnkQ |
| Metaethical.AI | June Ku | 2021-04-08 | https://youtu.be/2afdrE81yvg | |
| Misconceptions about continuous takeoff | Matthew Barnett | 2021-03-25 | https://www.dropbox.com/s/vxp55n83skynwdp/Misconceptions_About_Continuous_Takeoff.pptx?dl=0 | https://youtu.be/ojyYX4sX_w8 |
| Extrapolating GPT-N performance | Lukas Finnveden | 2021-03-04 | https://www.dropbox.com/s/xz5ljdxcnd2aq5d/Extrapolating_GPT_N_Performance.pptx?dl=0 | https://youtu.be/s2zKUe35Zsk |
| Eight Claims about Multi-AGI safety | Richard Ngo | 2021-02-11 | https://www.dropbox.com/s/rkjjh60v9knywe8/Eight_Claims_About_AGI_Safety.pptx?dl=0 | https://youtu.be/-o6eFCW6SrM |
| Functionally Effective Conscious AI Without Suffering | A. Agarwal and S. Edelman | 2021-02-04 | https://www.dropbox.com/s/9lxxk1m51o31tnk/Functionally_Effective_Conscious_AI_Without_Suffering.pptx?dl=0 | https://youtu.be/MgS5CwtKSxo |
| Consequences of Misaligned AI | Simon Zhuang and Dylan Hadfield-Menell | 2021-01-28 | https://youtu.be/Z46LIAcZ-vg | |
| AI Alignment, Philosophical Pluralism, and the Relevance of Non-Western Philosophy | Tan Zhi Xuan | 2021-01-21 | https://www.dropbox.com/s/wqjmaathnrf6qgo/Relevance_of_Non_Western_Philosophy.pptx?dl=0 | https://youtu.be/MrjCpAAM_Tc |
| An AGI Modifying Its Utility Function in Violation of the Strong Orthogonality Thesis | James D. Miller et al. | 2021-01-07 | https://www.dropbox.com/s/xralucim6qx5lp7/An_AGI_Modifying_Its_Utility_Function.pptx?dl=0 | https://youtu.be/0zgw79EKL8M |
| On Classic Arguments for AI Discontinuities | Ben Garfinkel | 2020-12-17 | https://www.dropbox.com/s/rv9h79826y0xuvg/On_Classic_Arguments_For_AI_Discontinuities.pptx?dl=0 | https://youtu.be/R8vh5qkON58 |
| Unpacking Classic AI Risk Arguments | Ben Garfinkel | 2020-11-26 | https://www.dropbox.com/s/7ckfytk4bnrasj7/Unpacking_Classic_AI_Risk_Arguments.pptx?dl=0 | https://youtu.be/A9TG9EfXhWs |
| The Human Condition | Hannah Arendt | 03-12-2020 | ||
| Unpacking Classic AI Risk Arguments | Ben Garfinkel | 26-11-2020 | https://www.dropbox.com/s/7ckfytk4bnrasj7/Unpacking_Classic_AI_Risk_Arguments.pptx?dl=0 | https://youtu.be/A9TG9EfXhWs |
| Sharing the world with digital minds 2/2 | Carl Shulman and Nick Bostrom | 19-11-2020 | https://www.dropbox.com/s/a4nf41udlmjgmof/Digital_Minds_2.pptx?dl=0 | https://youtu.be/gZTCJuhxF90 |
| Sharing the world with digital minds 1/2 | Carl Shulman and Nick Bostrom | 12-11-2020 | https://www.dropbox.com/s/m0re23cm7c5azrq/Digital_Minds_1.pptx?dl=0 | https://youtu.be/eJ2BLeoBbRk |
| On Scaling Laws | Jared Kaplan | 05-11-2020 | https://www.dropbox.com/s/7xh9jdmz1qr5ev4/Questions_for_Jared_Kaplan.pptx?dl=0 | https://youtu.be/I5mC4nDDp2I |
| An Empirical Model of Large Batch Training | Jared Kaplan et al. | 30-10-2020 | https://www.dropbox.com/s/925g6i9k79ugna5/Large-Batch_Training.pptx?dl=0 | https://youtu.be/JJCP0h_q-cs |
| Universal Intelligence | Shane Legg and Marcus Hutter | 22-10-2020 | https://youtu.be/1zroYiCkHiY | |
| Roadmap to a Roadmap | Matthijs Maas et al. | 15-10-2020 | https://www.dropbox.com/s/ms268vpm89t9a59/Roadmap_to_a_roadmap_Questions.pptx?dl=0 | https://youtu.be/1w9gYhhXzwI |
| On GPT-3 | Gwern Branwen | 08-10-2020 | https://www.dropbox.com/s/3qo2eyhnfyghpfg/On_GPT3.pptx?dl=0 | https://youtu.be/2d4dPclY1y8 |
| Corrigibility | Ali | 01-10-2020 | https://youtu.be/xmFSRmJAsto | |
| Language Models are Few Shot Learners 2/2 | Tom B. Brown et al. | 24-09-2020 | https://www.dropbox.com/s/kg5ekfg5st0jgml/Language_Models_are_Few_Shot_Learners_2.pptx?dl=0 | https://youtu.be/ypvz06StqvM |
| How close are we to creating Artificial General Intelligence? | David Deutsch | 17-09-2020 | https://youtu.be/wjq-PHQGIug | |
| Language Models are Few Shot Learners 1/2 | Tom B. Brown et al. | 10-09-2020 | https://www.dropbox.com/s/oeyawox7sys039y/Language_Models_are_Few_Shot_Learners_1.pptx?dl=0 | https://youtu.be/jOxtiqszL4s |
| Scrutinizing Classic AI Risk Arguments 2/2 | Ben Garfinkel | 27-08-2020 | https://www.dropbox.com/s/qujdwgog90ijyyn/Scrutinizing_Classical_AI_Risk_Arguments_2.pptx?dl=0 | https://youtu.be/j-_FvJ-XbWA |
| Scrutinizing classical AI risk arguments 1/2 | Ben Garfinkel | 13-08-2020 | https://www.dropbox.com/s/vus0iugix955z1e/Scrutinizing_Classical_AI_Risk_Arguments_1.pptx?dl=0 | https://youtu.be/_kNvExbheNA |
| ‘Indifference’ methods for managing agent rewards | Stuart Armstrong and Xavier O’Rourke | 06-08-2020 | https://youtu.be/KDLYS2hPKBA | |
| AI Research Considerations for Human Existential Safety (ARCHES) | Andrew Critch and David Krueger | 30-07-2020 | https://www.dropbox.com/s/e8h1t4f0u1l3vt1/Arches.pptx?dl=0 | https://youtu.be/4b4VlwUeCWY |
| Risks from learned optimization | Evan Hubinger et al. | 23-07-2020 | ||
| Problem of fully updated deference | Eliezer Yudkowsky | 16-07-2020 | https://www.dropbox.com/s/d3bgw6pjwdwa2ul/Updated_Deference.pptx?dl=0 | https://youtu.be/QWd72bHpRLM |
| Pessimism About Unknown Unknowns Inspires Conservatism | Michael K. Cohen and Marcus Hutter | 09-07-2020 | https://youtu.be/55AMF2z5dJU | |
| Steven Pinker on the Possible Existential Threat of AI | Steven Pinker | 02-07-2020 | https://www.dropbox.com/s/xulk2lozpvtvu2g/steven_pinker_on_the%20possible_existential_threat_of_ai.pptx?dl=0 | https://youtu.be/nrCjVhp4wuo |
| The Off-Switch Game | Dylan Hadfield-Menell et al. | 25-06-2020 | https://youtu.be/wEoAZWmsCJk | |
| Formal Metaethics and Metasemantics for AI Alignment | June Ku | 18-06-2020 | https://www.dropbox.com/s/f5ddi96eblvurwm/formal_metaethics_and_metasemantics_for_ai_alignment.pptx?dl=0 | https://youtu.be/FJdnU9P5QlM |
| Discussion: If I were a well-intentioned AI | Stuart Armstrong, Scott Garrabrant | 10-06-2020 | https://youtu.be/JVVj9Dui9es | |
| Measuring the Algorithmic Efficiency of Neural Networks | Danny Hernandez et al. | 28-05-2020 | https://www.dropbox.com/s/tx648kfvbtjnon2/measuring_the_algorithmic_efficiency_of_neural_networks.pptx?dl=0 | https://youtu.be/-7rYPH-8f3w |
| If I were a well-intentioned AI 3+4/4 | Stuart Armstrong | 21-05-2020 | https://youtu.be/qPKrTap4gPE | |
| Conversation with Adam Gleave | Adam Gleave | 15-05-2020 | https://www.dropbox.com/s/m0611n0flebpaqz/conversation_with_adam_gleave.pptx?dl=0 | https://youtu.be/pVzvW_rI8Q0 |
| If I were a well-intentioned AI 2/4 | Stuart Armstrong | 07-05-2020 | https://youtu.be/HW7kfKrbLSg | |
| The Offence-Defence Balance of Scientific Knowledge | Toby Shevlane et al. | 01-05-2020 | https://youtu.be/HW7kfKrbLSg | |
| Conversation with Paul Christiano | Paul Christiano et al. | 22-04-2020 | https://www.dropbox.com/s/mjqkp4xv4s6rf1l/conversation_with_paul_christiano.pptx?dl=0 | https://youtu.be/etwwBAneIGY |
| If I were a well-intentioned AI 1/4 | Stuart Armstrong | 15-04-2020 | https://youtu.be/hWb09uq6Zlk | |
| The Role of Cooperation in Responsible AI Development | Gillian Hadfield et al. | 08-04-2020 | https://www.dropbox.com/s/jcspqnl8b3r3tbk/role_of_cooperation.pptx?dl=0 | https://youtu.be/212ih2NaK9Q |
| Q & A with Stuart Russell | Stuart Russell | 08-01-2020 | https://www.dropbox.com/s/r0wvq3ofddectoc/Stuart_Russell_Questions.pptx?dl=0 | https://youtu.be/BztgYBqXi0Q |
| Raging robots, hapless humans: the AI dystopia | David Leslie | 17-12-2019 | https://www.dropbox.com/s/1yp0lixp3k1ztif/Raging_Robots.pptx?dl=0 | https://youtu.be/fbhop4ErrUA |
| Human Compatible (9-10) | Stuart Russell | 11-12-2019 | https://www.dropbox.com/s/c0z4qie7mgvmcdj/Human_Compatible_3.pptx?dl=0 | https://youtu.be/up9OQL2SXCI |
| Human Compatible (7-8) | Stuart Russell | 05-12-2019 | https://www.dropbox.com/s/c0z4qie7mgvmcdj/Human_Compatible_2.pptx?dl=0 | https://youtu.be/q278iRzQhrY |
| Human Compatible (1-6) | Stuart Russell | 28-11-2019 | https://www.dropbox.com/s/c0z4qie7mgvmcdj/Human_Compatible_3.pptx?dl=0 | https://youtu.be/VBKUGy3IDZw |
| Why AI Doomsayers are like Sceptical Theists | John Danaher | 20-11-2019 | https://www.dropbox.com/s/but73z6sr875r6s/Doomsayers_are_like_Sceptical_Theists.pptx?dl=0 | https://youtu.be/GzV3_AgR8xU |
| Policy Desiderata for Superintelligent AI 2/2 | Nick Bostrom | 12-11-2019 | https://www.dropbox.com/s/arq597osl2gmh8y/Policy_Desiderata_For_Superintelligent_AI_2.pptx?dl=0 | https://youtu.be/VkjOzcSAFAs |
| Policy Desiderata for Superintelligent AI 1/2 | Nick Bostrom | 06-11-2019 | https://www.dropbox.com/s/zz1gs581m32ct4i/Policy_Desiderata_For_Superintelligent_AI.pptx?dl=0 | https://youtu.be/rdNwJpGWO5Y |
| AI safety via debate 2/2 | Paul Christiano et al. | 30-10-2019 | https://www.dropbox.com/s/2ecnw0zlx1noczi/ai_safety_via_debate_2.pptx?dl=0 | https://youtu.be/TmM1pNop37M |
| AI safety via debate 1/2 | Paul Christiano et al. | 22-10-2019 | https://www.dropbox.com/s/2ecnw0zlx1noczi/ai_safety_via_debate_1.pptx?dl=0 | https://youtu.be/pFvRDrVzEZ0 |
| AI Insights Dataset Analysis | Colleen McKenzie et al. | 15-10-2019 | https://www.dropbox.com/s/51abhbpxvyaympi/ai_insights_dataset_analysis.pptx?dl=0 | https://youtu.be/y3sTUD002wM |
| A Tutorial on Machine Learning and Data Science Tools | Andreas Holzinger | 09-10-2019 | https://www.dropbox.com/s/jbg9qsprcwa8agq/machine_learning_tutorial.pptx?dl=0 | https://youtu.be/QCd8yXqgR_s |
| Superintelligence Skepticism as a Political Tool | Seth Baum | 02-10-2019 | https://www.dropbox.com/s/1ilw590x5ukkw5m/Superintelligence_Skepticism_as_a_Political_Tool.pptx?dl=0 | https://youtu.be/-phnH6dGhqk |
| Computing Machinery and Intelligence 2 | A. M. Turing | 26-09-2019 | https://www.dropbox.com/s/7zv8gy2ktmrvpw4/computing_machinery_and_intelligence_2.pptx?dl=0 | https://youtu.be/cmfxk8wWMLU |
| Computing Machinery and Intelligence 1 | A. M. Turing | 17-09-2019 | https://www.dropbox.com/s/7zv8gy2ktmrvpw4/computing_machinery_and_intelligence_1.pptx?dl=0 | https://youtu.be/1DAankZL_Sw |
| A shift in arguments for AI Risk 2 | Tom Sittler | 11-09-2019 | https://www.dropbox.com/s/fpteb5oxi5d82pm/a_shift_in_arguments_2.pptx?dl=0 | https://youtu.be/l1LJ40Jf6gg |
| A shift in arguments for AI Risk 1 | Tom Sittler | 04-09-2019 | https://www.dropbox.com/s/t414yxk7dbqzcdc/a_shift_in_arguments_1.pptx?dl=0 | https://youtu.be/qVzcRvLCKqc |
| TAISU report and retrospective | Søren Elverlin | 28-08-2019 | https://www.dropbox.com/s/hkpv90h9jm1y0d3/taisu_retrospective.pptx?dl=0 | https://youtu.be/kha2TgGcoUM |
| Jeff Hawkins on neuromorphic AGI within 20 years | Steve Byrne | 20-08-2019 | https://www.dropbox.com/s/vzxk89tyiuahuoj/Neuromorphic_AGI.pptx?dl=0 | https://youtu.be/B8c6dA1p0Vw |
| Stuart Armstrong presents “Synthesising…” | Stuart Armstrong | 14-08-2019 | https://www.dropbox.com/s/jlcek8z742bynrq/synthesising_questions.pptx?dl=0 | https://youtu.be/N-u8c3Q3RM0 |
| Synthesising a human’s preferences into a utility function 4/4 | Stuart Armstrong | 08-08-2019 | https://www.dropbox.com/s/ajyb8bl3cl9bdpc/Synthesizing_into_Utility_4.pptx?dl=0 | https://youtu.be/y1tiz9xOO0o |
| Synthesising a human’s preferences into a utility function 3/4 | Stuart Armstrong | 01-08-2019 | https://www.dropbox.com/s/ajyb8bl3cl9bdpc/Synthesizing_into_Utility_3.pptx?dl=0 | https://youtu.be/gSKpm8jnhvo |
| Synthesising a human’s preferences into a utility function 2/4 | Stuart Armstrong | 24-07-2019 | https://www.dropbox.com/s/ajyb8bl3cl9bdpc/Synthesizing_into_Utility_2.pptx?dl=0 | https://youtu.be/sN1BOubfcrk |
| Synthesising a human’s preferences into a utility function 1/4 | Stuart Armstrong | 17-07-2019 | https://www.dropbox.com/s/ajyb8bl3cl9bdpc/Synthesizing_into_Utility_1.pptx?dl=0 | https://youtu.be/9ync2XKx-W0 |
| Reframing Superintelligence Q&A | Eric Drexler | 09-07-2019 | https://www.dropbox.com/s/i5oqix83wsfv1u5/Comprehensive_AI_Services_Q_A.pptx?dl=0 | |
| Reframing Superintelligence 3 | Eric Drexler | 03-07-2019 | https://www.dropbox.com/s/6dpnwrl8yfxsm9p/Comprehensive_AI_Services_3.pptx?dl=0 | https://youtu.be/6zgjbKtpGAM |
| Reframing Superintelligence 2 | Eric Drexler | 27-06-2019 | https://www.dropbox.com/s/6dpnwrl8yfxsm9p/Comprehensive_AI_Services_2.pptx?dl=0 | https://youtu.be/uZfzX9amdqI |
| Reframing Superintelligence 1 | Eric Drexler | 12-06-2019 | https://www.dropbox.com/s/6dpnwrl8yfxsm9p/Comprehensive_AI_Services_1.pptx?dl=0 | https://youtu.be/J6T9YuDT1mU |
| Ethics Guidelines for Trustworthy AI | Pekka Ala-Pietilä et al | 06-06-2019 | https://www.dropbox.com/s/9u7pcxquz0utyqs/Ethics_Guidelines_For_Trustworthy_AI.pptx?dl=0 | https://youtu.be/BQDtN_4M3F4 |
| Likelihood of discontinuous progress around the development of AGI 2 | Katja Grace | 29-05-2019 | https://www.dropbox.com/s/dc7moqf28vzxl8o/Discontinuous_Progress_2.pptx?dl=0 | https://youtu.be/j8GnMy-Bckk |
| Likelihood of discontinuous progress around the development of AGI 1 | Katja Grace | 23-05-2019 | https://www.dropbox.com/s/dc7moqf28vzxl8o/Discontinuous_Progress_1.pptx?dl=0 | https://youtu.be/KiYoYVpfXFo |
| Value Learning Q/A | Rohin Shah | 15-05-2019 | https://www.dropbox.com/s/nw33obe8h7y3hsx/Value_Learning_Questions.pptx?dl=0 | https://youtu.be/Xvql4fGBoBA |
| Value Learning Comments | Rohin Shah et al. | 08-05-2019 | https://www.dropbox.com/s/4yd579xlnnzc8uu/Value_Learning_Comments.pptx?dl=0 | https://youtu.be/EGpT3fR2HSo |
| Value Learning 6/6 | Rohin Shah | 30-04-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_6.pptx?dl=0 | https://youtu.be/CjO08ooLfLc |
| Value Learning 5/6 | Rohin Shah | 25-04-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_5.pptx?dl=0 | |
| Value Learning 4/6 | Rohin Shah | 10-04-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_4.pptx?dl=0 | https://youtu.be/vP9yuEz2AZU |
| Value Learning 3/6 | Rohin Shah | 02-04-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_3.pptx?dl=0 | https://youtu.be/mbb5HhkkUAw |
| Thoughts on Human Models | Ramana Kumar and Scott Garrabrantrant | 26-03-2019 | https://www.dropbox.com/s/nwr0sgs5d32vgg9/Thoughts_on_Human_Models.pptx?dl=0 | https://youtu.be/UnC7xaQEpC8 |
| Value Learning 2/6 | Rohin Shah | 19-03-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_2.pptx?dl=0 | https://youtu.be/1OuBHDsbyHo |
| Value Learning 1/6 | Rohin Shah | 12-03-2019 | https://www.dropbox.com/s/x2ert6pxoc1trm2/Value_Learning_1.pptx?dl=0 | https://youtu.be/Rs8-JRmp9c0 |
| Critique of Superintelligence (2/2) | Fods12 | 05-03-2019 | https://www.dropbox.com/s/a9y84opvh2pt5qj/Critique_of_Superintelligence_2.pptx?dl=0 | https://youtu.be/lCKc_eDXebM |
| How Viable is Arms Control For Military AI? (2/2) | Matthijs Maas | 26-02-2019 | https://www.dropbox.com/s/oonhfxtul129jqq/Arms_Control_For_Military_AI_2.pptx?dl=0 | https://youtu.be/SO9eqaM0rEE |
| How Viable is Arms Control For Military AI? (1/2) | Matthijs Maas | 19-02-2019 | https://www.dropbox.com/s/k8mzphincxl178h/Arms_Control_For_Military_AI.pptx?dl=0 | https://youtu.be/yIiurUItNGw |
| Superintelligence: Paths, Dangers, Strategies | Fods12 | 12-02-2019 | https://www.dropbox.com/s/js7z8fpedjcdhus/Long%20term%20AI%20Safety.pptx?dl=0 | |
| Critique of Superintelligence (1/2) | Fods12 | 07-02-201 | https://www.dropbox.com/s/cvvlpcy4mjndbp5/Critique_of_Superintelligence_1.pptx?dl=0 | https://youtu.be/Xl5SMS9eKD4 |
| Embedded Agency Q & A | Scott Garrabrant | 30-01-2019 | https://www.dropbox.com/s/t723ektqch6o6ok/Embedded_Agency_Questions.pptx?dl=0 | https://youtu.be/btc-4vYyOSs |
| Embedded Agency (4/4) | Abram Demski and Scott Garrabrant | 24-01-2019 | https://www.dropbox.com/s/gocajy754deiscr/Embedded_Agency_4.pptx?dl=0 | https://youtu.be/ITK3j6yng8E |
| Embedded Agency (3/4) | Abram Demski and Scott Garrabrant | 16-01-2019 | https://www.dropbox.com/s/qzq0nu6of280yhg/Embedded_Agency_3.pptx?dl=0 | https://youtu.be/GZM0qLF9ZZA |
| Embedded Agency (2/4) | Abram Demski and Scott Garrabrant | 10-01-201 | https://www.dropbox.com/s/s50supg8new80mi/Embedded_Agency_2.pptx?dl=0 | https://youtu.be/wiQ7GDOIi1o |
| Embedded Agency (1/4) | Abram Demski and Scott Garrabrant | 02-01-201 | https://www.dropbox.com/s/ftdkvvtg3tb1405/Embedded_Agency_1.pptx?dl=0 | https://youtu.be/AiTbB5tyICA |
| The Vulnerable World Hypothesis 2/2 | Nick Bostrom | 12-12-2018 | https://www.dropbox.com/s/ci3z0ji1vst83a3/Vulnerable_World_2.pptx?dl=0 | https://youtu.be/pxM_F3F1eiI |
| The Vulnerable World Hypothesis 1/2 | Nick Bostrom | 04-12-2018 | https://www.dropbox.com/s/zs4iwt0z6hacz1z/Vulnerable_World_1.pptx?dl=0 | https://youtu.be/7nGP00193Ig |
| Foom Justifies AI Risk Efforts Now | Robin Hanson | 28-11-2018 | https://youtu.be/QbHzxHsnAtk | |
| Why Altruists Should Perhaps Not Prioritize AI 2/2 | Magnus Vinding | 20-11-2018 | https://www.dropbox.com/s/82y15dir9lm38k7/A_Lengthy_Critique_2.pptx?dl=0 | |
| Building Safer AGI by introducing Artificial Stupidity | Roman Yampolskiy et al. | 15-11-2018 | https://youtu.be/AiqgacILGcQ | |
| Why Altruists Should Perhaps Not Prioritize AI | Magnus Vinding | 07-11-2018 | https://www.dropbox.com/s/gw6jrozrr6ld2lh/A_Lengthy_Critique.pptx?dl=0 | https://youtu.be/G3lV2_slkSA |
| Are we Approaching an Economic Singularity? (2/2) | William D. Nordhaus | 30-10-2018 | https://www.dropbox.com/s/oqhvkh9kl8upveg/Economic_Singularity_2.pptx?dl=0 | https://youtu.be/ifBTeeLNdRo |
| Are we Approaching an Economic Singularity? | William D. Nordhaus | 23-10-2018 | https://www.dropbox.com/s/cr20fl468q94ew0/Economic_Singularity.pptx?dl=0 | https://youtu.be/TU5ZKZGCTC8 |
| The Rocket Alignment Problem | Eliezer Yudkowsky | 17-10-2018 | https://www.dropbox.com/s/qdevdaymx0ol7rg/Rocket_Alignment.pptx?dl=0 | https://youtu.be/DVmWDkIond4 |
| Technology Roulette | Richard Danzig | 10-10-2018 | https://www.dropbox.com/s/5f60dck5qk5w8d4/Technology_Roulette.pptx?dl=0 | https://youtu.be/hEgY76o5Myg |
| Towards a new Impact Measure | Alex Turner | 03-10-2018 | https://www.dropbox.com/s/6e2cgdfit5cnvqq/Towards_a_New_Impact_Measure.pptx?dl=0 | https://youtu.be/X46L5gNsjPY |
| Incomplete Contracting and AI Alignment | Dylan Hadfield-Menell et al. | 19-09-2018 | https://www.dropbox.com/s/kpv4rs2lp4ard6w/Incomplete_Contracting.pptx?dl=0 | https://youtu.be/h9ijCo1iE0I |
| Open Ended Intelligence | David Weinbaum et al. | 12-09-2018 | https://www.dropbox.com/s/zh1pz6mkq470mcp/Open_Ended_Intelligence.pptx?dl=0 | https://youtu.be/0n0f8_AqwLw |
| Strategic Implications of Openness in AI Development | Nick Bostrom | 05-09-2018 | https://www.dropbox.com/s/fg6i1tp26huzb6x/Strategic_Implications_of_Openness.pptx?dl=0 | https://youtu.be/Dw7jo-DBo9o |
| A Survey of Artificial General Intelligence Projects | Seth Baum | 29-08-2018 | https://www.dropbox.com/s/d5o35v2pn2i6bde/Survey_of_AGI_projects.pptx?dl=0 | https://youtu.be/5aFzEkOy0PI |
| MIRI’s Strategic Background | Malo Bourgon | 22-08-2018 | https://www.dropbox.com/s/5fz7qr0yd0nxg3q/Strategic_Background.pptx?dl=0 | https://youtu.be/uB79g2uxEOM |
| The Malicious use of AI | Miles Brundage et al. | 15-08-2018 | https://www.dropbox.com/s/6hwln45lcl5ea1e/Malicous_Use_of_AI.pptx?dl=0 | https://youtu.be/jv3zzw_jouM |
| The Learning-Theoretic AI Alignment Research Agenda | Vadim Kosoy | 09-08-2018 | https://www.dropbox.com/s/be03ndnr2qe0wnu/AI%20Alignment%20and%20Learning%20Theory.pptx?dl=0 | https://youtu.be/6MkmeADXcZg |
| No Basic AI Drives and A Rebuttal to Omohundro’s ‘Basic A.I. Drives’ | Alexander Kruel and Scott Jackish | 01-08-2018 | https://www.dropbox.com/s/t5vhg0lkqn46tnd/No_Basic_AI_Drives.pptx?dl=0 | https://youtu.be/l9g76TsWRIU |
| The Basic AI Drives | Stephen Omohundro | 24-07-2018 | https://www.dropbox.com/s/dn9tw9wzpoyjq4t/Basic_AI_Drives.pptx?dl=0 | https://youtu.be/d4pYgQ-1z6s |
| AI and compute / Interpreting AI Compute trends | Amodei et al., Ryan Carey | 18-07-2018 | https://www.dropbox.com/s/vhpl29bx9tmhcip/AI_and_Compute.pptx?dl=0 | https://youtu.be/3TE24oh6WHU |
| Learning which reward to maximise | Stuart Armstrong et al. | 11-07-2018 | https://www.dropbox.com/s/qzhcj4uaxwj41k3/Learning_Which_Reward.pptx?dl=0 | https://youtu.be/GoLIY894xYQ |
| AlphaGo Zero and the Foom Debate | Eliezer Yudkowsky | 04-07-2018 | https://www.dropbox.com/s/stgltpu588cwesm/Eliezer_Hanson_Foom_Debate3.pptx?dl=0 | https://youtu.be/mYy7slSq9Nw |
| The Hanson-Yudkowsky AI-Foom Debate (2/2) | Kaj Sotala | 28-06-2018 | https://www.dropbox.com/s/94s1nz9emda6yld/Eliezer_Hanson_Foom_Debate2.pptx?dl=0 | https://youtu.be/AFjFCKJA23c |
| The Hanson-Yudkowsky AI-Foom Debate (1/2) | Kaj Sotala | 20-06-2018 | https://www.dropbox.com/s/y4k27a11dw88pgt/Eliezer_Hanson_Foom_Debate.pptx?dl=0 | |
| Taking AI Risk Seriously | Andrew Critch | 14-06-2018 | https://www.dropbox.com/s/w8nttdob5pa8gg3/Taking_AI_Risk_Seriously.pptx?dl=0 | https://youtu.be/7tF3uW-MVFI |
| Current thoughts on Paul Christano’s research agenda | Jessica Taylor | 06-06-2018 | https://www.dropbox.com/s/s5eubox7wkoenyt/Thoughts_on_PCs_agenda.pptx?dl=0 | https://youtu.be/WtKA0DcXTTM |
| Challenges to Christiano’s capability amplification proposal | Eliezer Yudkowsky | 30-05-2018 | https://www.dropbox.com/s/039evo5u61c1ksb/Challengs_To_Christianos_IDA.pptx?dl=0 | https://youtu.be/bgAZ1NUUOfA |
| Long-term strategies for ending existential risk from fast takeoff | Daniel Dewey | 24-05-2018 | https://www.dropbox.com/s/ugsan767ffsd2mz/Long-term_strategies.pptx?dl=0 | https://youtu.be/69abTzH2GfI |
| Machines that Think | Toby Walsh | 16-05-2018 | https://www.dropbox.com/s/7mfguf4zn0kf6l1/Machines_that_Think.pptx?dl=0 | https://youtu.be/DcIGaLHD054 |
| Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm | David Silver et al. | 10-05-2018 | https://www.dropbox.com/s/c4jgfze5vvldudg/Mastering_Chess.pptx?dl=0 | https://youtu.be/2mh89MhYGeE |
| Iterated Distillation and Amplification | Ajeya Cotra | 02-05-2018 | https://www.dropbox.com/s/66cjpw44netl8n4/Iterated_Distillation.pptx?dl=0 | https://youtu.be/LD1sfZ3ebhc |
| Deciphering China’s AI Dream | Jeffrey Ding | 24-04-2018 | https://www.dropbox.com/s/hn0w3zdxuwq4i52/Deciphering_China.pptx?dl=0 | https://youtu.be/YuMsB51DxeI |
| Why the Singularity is not a Singularity | Edward Felten | 18-04-2018 | https://www.dropbox.com/s/kfcm3qvv7iouo0a/Why_the_Singularity.pptx?dl=0 | https://youtu.be/_kO2v0-t4ys |
| The Ethics of Artificial Intelligence | Yudkowsky and Bostrom | 22-03-2018 | https://www.dropbox.com/s/yc486dnvu08fi81/Ethics_of_AI.pptx?dl=0 | https://youtu.be/0rob3jNHfjQ |
| An Untrollable Mathematician | Abram Demski | 14-03-2018 | https://www.dropbox.com/s/e95ib00jruavei5/An%20Untrollable%20Mathematician.pdf?dl=0 | https://youtu.be/ql4Y0-jEKhw |
| Takeoff Speeds | Paul Christiano | 07-03-2018 | https://www.dropbox.com/s/t0k6wn4q90emwf2/Takeoff_Speeds.pptx?dl=0 | https://youtu.be/7ogJuXNmAIw |
| We’re told to fear robots. But why do we think they’ll turn on us? | Steven Pinker | 01-03-2018 | https://www.dropbox.com/s/xjfhto3dwzn8wzk/Robot_Uprising.pptx?dl=0 | https://youtu.be/kXg2NZCQZaQ |
| Cognitive Biases Potentially Affecting Judgment of Global Risks | Eliezer Yudkowsky | 21-02-2018 | https://www.dropbox.com/s/jrfcqwca4dxrvjq/Cognitive_biases.pptx?dl=0 | https://youtu.be/z0B5xVdNq1E |
| Goodhart Taxonomy | Scott Garrabrant | 13-02-2018 | https://www.dropbox.com/s/7bdeyrmrm8sccse/Goodhart%20Taxonomy.pptx?dl=0 | https://youtu.be/tzbMSObyp4o |
| An AI Race for Strategic Advantage: Rhetoric and Risks | Seán S ÓhÉigeartaigh et al. | 07-02-2018 | https://www.dropbox.com/s/vtxaak9ngppxyku/Rhetoric_and_Risks.pptx?dl=0 | https://youtu.be/7wGdkoPxOSQ |
| Reply to Bostrom’s arguments for a hard takeoff | Brian Tomasik | 31-01-2018 | https://www.dropbox.com/s/y8iltly2919zd3h/Reply_To_Bostrom.pptx?dl=0 | https://youtu.be/04nu87UnslI |
| Superintelligence as a Cause or Cure for Risks of Astronomical Suffering | Kaj Sotala et al. | 24-01-2018 | https://www.dropbox.com/s/1ekz8282oh207wy/Astronomical_Suffering.pptx?dl=0 | https://youtu.be/Onx24F7Hliw |
| Impossibility of deducing preferences and rationality from human policy | Stuart Armstrong et al. | 17-01-2018 | https://www.dropbox.com/s/3jhoj03vj8ph9du/2018-01-17-Stuart-Armstrong-You-cannot-learn-human-rationality-and-reward-together.pptx?dl=0 | https://youtu.be/H7b_2NCJk1E |
| On the Promotion of Safe and Socially Beneficial Artificial Intelligence | Seth Baum | 09-01-2018 | https://www.dropbox.com/s/c4b9cggo9ylc3jf/Beneficial_AI.pptx?dl=0 | https://youtu.be/QYkvsEHxHxI |
| Refuting Bostrom’s Superintelligence Argument | Sebastian Benthall | 03-01-2018 | https://www.dropbox.com/s/zcq5d0z6i66pu0j/Refuting%20Bostrom.pptx?dl=0 | https://youtu.be/DfZjVKsnjTk |
| Logical Induction (1+7) | Scott Garrabrant et al. | 27-12-2017 | https://www.dropbox.com/s/9jrm8whuswaytjb/Logical_Induction.pptx?dl=0 | https://youtu.be/jbZyfcDcaKE |
| Conceptual Confusions in Assessing AGI | Chris Cooper | 20-12-2017 | https://www.dropbox.com/s/ax49ckl3exhk9s0/Conceptual_Confusions.pptx?dl=0 | https://youtu.be/d4luYznO1ec |
| Disjunctive Scenarios of Catastrophic AI Risk (2/2) | Kaj Sotala | 06-12-2017 | https://www.dropbox.com/s/vaxifnfhqx5c3qk/Disjunctive_Scenarios2.pptx?dl=0 | https://youtu.be/PcT6L5YKN9A |
| Disjunctive Scenarios of Catastrophic AI Risk (1/2) | Kaj Sotala | 01-12-2017 | https://www.dropbox.com/s/wyw9ke0beapqglp/Disjunctive_Scenarios.ppsx?dl=0 | https://youtu.be/T85G-ah3ynE |
| Artificial Intelligence in Life Extension: from Deep Learning to Superintelligence | Alexey Turchin | 22-11-2017 | https://www.dropbox.com/s/p2e6ehi8gz27pk3/AI_in_Healthcare.pdf?dl=0 | https://youtu.be/ZRy7ET-0KPI |
| Good and safe uses of AI Oracles | Stuart Armstrong | 08-11-2017 | https://www.dropbox.com/s/xnl2t89z4nfbexr/Oracles.pdf?dl=0 | https://youtu.be/5R73YhldO_o |
| Positively shaping the development of artificial intelligence | Robert Wilbin | 01-11-2017 | https://www.dropbox.com/s/jk23r5xbmcrs37n/Positively_Shaping.pdf?dl=0 | https://youtu.be/j_YyAv0CUG8 |
| There is no Fire Alarm for Artificial General Intelligence | Eliezer Yudkowsky | 25-10-2017 | https://www.dropbox.com/s/oqwmybfjq5tjebp/No_Fire_Alarm.pdf?dl=0 | https://youtu.be/k86VzPd0wTQ |
| Fitting Values to Inconsistent Humans | Stuart Armstrong | 18-10-2017 | https://www.dropbox.com/s/u3n9s9nsp009z0p/Fitting_Values.pdf?dl=0 | https://youtu.be/w0H6Ws7xts8 |
| Age of Em (Intelligence Explosion) | Robin Hanson | 11-10-2017 | https://www.dropbox.com/s/o7se1q6996mc0ph/Age_of_Em_Intelligence_Explosion.pdf?dl=0 | https://youtu.be/qlH-gyvZL1g |
| Age of Em (Chapter 27) | Robin Hanson | 27-09-2017 | https://www.dropbox.com/s/i50zb7iswpivbgm/Age%20of%20Em.pdf?dl=0 | https://youtu.be/vufsTEVK7DM |
| Meditations on Moloch | Scott Alexander | 20-09-2017 | https://www.dropbox.com/s/nn0ep22szo2h9gs/Meditations_on_Moloch.pdf?dl=0 | https://youtu.be/YQ_2HFtXBDM |
| Incorrigibility in the CIRL Framework | Ryan Carey | 13-09-2017 | https://www.dropbox.com/s/yyryrngcs7qhsz5/Incorrigibility_In_CIRL.pdf?dl=0 | https://youtu.be/n2X1QKEUrt4 |
| OpenAI Makes Humanity Less Safe | Ben Hoffman | 06-09-2017 | https://www.dropbox.com/s/v8ugc4uo5ds533b/OpenAI_Makes_Humanity_Less_Safe.pdf?dl=0 | https://youtu.be/nwh9ZR3yO2M |
| Open Problems Regarding Counterfactuals: An Introduction For Beginners | Alex Appel | 30-08-2017 | https://www.dropbox.com/s/0ztr9lwd9z8md2l/Counterfactuals.pdf?dl=0 | https://youtu.be/JqtJXr9QHkM |
| A Game-Theoretic Analysis of the Off-Switch Game | Tobias Wängberg et al. | 23-08-2017 | https://www.dropbox.com/s/n4rx49hq49m5bxi/Off-Switch-Game.pdf?dl=0 | https://youtu.be/8w2_cb6cBY0 |
| Benevolent Artificial Anti-Natalism | Thomas Metzinger | 16-08-2017 | https://www.dropbox.com/s/6gfbt568tadnflo/Benevolent_Artificial_Anti-Natalism.pdf?dl=0 | https://youtu.be/Zjid5CgLaac |
| Where the Falling Einstein Meets the Rising Mouse | Scott Alexander | 09-08-2017 | https://www.dropbox.com/s/wu4pc3qc8zi13h0/Where_the_Falling_Einstein.pdf?dl=0 | https://youtu.be/oua1fMxYXvo |
| Superintelligence Risk Project | Jeff Kaufman | 03-08-2017 | https://www.dropbox.com/s/9jk00oohc912izx/Superintelligence_Risk_Project.pdf?dl=0 | https://youtu.be/vG8SuD66NLA |
| Staring into the Singularity | Eliezer Yudkowsky | 26-07-2017 | https://www.dropbox.com/s/f7g9mpcwk3qr9pk/Staring_Into_the_Singularity.pdf?dl=0 | https://youtu.be/qud4WvehRho |
| Artificial Intelligence and the Future of Defense | Matthijs Maas et al. | 19-07-2017 | https://www.dropbox.com/s/gxigsjyyd1thnb1/AI_and_the_Future_of_Defense.pdf?dl=0 | https://youtu.be/UO6Px7-AL4w |
| Prosaic AI Alignment | Paul Christiano | 12-07-2017 | https://www.dropbox.com/s/vlg3pb0pewx1w7r/Prosaic_AI_Alignment.pdf?dl=0 | https://youtu.be/YvBj620UPBg |
| A model of the Machine Intelligence Research Institute | Sindy Li | 05-07-2017 | https://www.dropbox.com/s/d2fxbnqyay104df/A_Model_of_MIRI.pdf?dl=0 | https://youtu.be/kNlU3kAB2ks |
| Deep Reinforcement Learning from Human Preferences | Paul Christiano et al. | 28-06-2017 | https://www.dropbox.com/s/ajajtd7fs3fhw8u/Deep_Reinforcement_Learning.pdf?dl=0 | https://youtu.be/3zK1kNremWA |
| –Holiday– | 21-06-2017 | |||
| The Singularity: A Philosophical Analysis (2/2) | David J. Chalmers | 14-06-2017 | https://www.dropbox.com/s/pan93bzvfroj58k/The_Singularity_2.pdf?dl=0 | |
| The Singularity: A Philosophical Analysis (1/2) | David J. Chalmers | 07-06-2017 | https://www.dropbox.com/s/lu4qk2205htlku2/The_Singularity.pdf?dl=0 | https://youtu.be/U-0ZD9Irfw |
| Why Tool AIs want to be Agent AIs | Gwern Branwen | 31-05-2017 | https://www.dropbox.com/s/i9jvrj43r7xvocl/Tool_AIs.pdf?dl=0 | https://youtu.be/Tnnn6LtZGiQ |
| A Map: AGI Failure Modes and Levels | Alexey Turchin | 24-05-2017 | https://www.dropbox.com/s/to6qowvhh14wfut/AGI_Failure_modes.pdf?dl=0 | https://youtu.be/kBTNrprdKiU |
| Neuralink and the Brain’s Magical Future | Tim Urban | 17-05-2017 | https://www.dropbox.com/s/e00gsu629zkzl4b/Neuralink.pdf?dl=0 | https://youtu.be/9NpNzlCptJI |
| The Myth of Superhuman AI | Kevin Kelly | 10-05-2017 | https://www.dropbox.com/s/00cnhpyndlo4jru/The_Myth_of_a_Superhuman_AI.pdf?dl=0 | https://youtu.be/WLSOmVXweSs |
| Merging our brains with machines won’t stop the rise of the robots | Michael Milford | 03-05-2017 | https://www.dropbox.com/s/og3pn5o7ofi101e/Humans_Merging_with_AI.pdf?dl=0 | https://youtu.be/Rgm6xMt54VA |
| Building Safe AI | Andrew Trask | 26-04-2017 | https://www.dropbox.com/s/3fnx251f9oiga8p/Building_Safe_AI.pdf?dl=0 | https://youtu.be/Ys-U-4vjRjw |
| AGI Safety Solutions Map | Alexey Turchin | 19-04-2017 | https://www.dropbox.com/s/ldyb7a32nd2089k/AGI_Safety_Solutions_Map.pdf?dl=0 | https://youtu.be/ZNSfUiXZwz0 |
| Strong AI Isn’t Here Yet | Sarah Constantin | 12-04-2017 | https://www.dropbox.com/s/297amvxrl58wgil/Strong_AI_Isnt_Here_Yet.pdf?dl=0 | https://youtu.be/GpuQlJ3IHBM |
| Robotics: Ethics of artificial intelligence | Stuart Russell et al. | 05-04-2017 | https://www.dropbox.com/s/8t5o990d1hf7ew6/Robotics_Ethics_of_artificial_intelligence.pdf?dl=0 | https://youtu.be/z_WhxqCWJ4s |
| Using machine learning to address AI risk | Jessica Taylor | 29-03-2017 | https://www.dropbox.com/s/52k4u10f95c6fvb/Using_Machine_Learning.pdf?dl=0 | https://youtu.be/vXNi4L5PH0A |
| Racing to the Precipice: a Model of Artificial Intelligence Development | Armstrong et al. | 22-03-2017 | https://www.dropbox.com/s/2zybpfb667vy9tl/Racing_To_The_Precipice.pdf?dl=0 | |
| Politics is Upstream of AI | Raymond Brannen | 15-03-2017 | https://www.dropbox.com/s/kvcyf4kwmqmlufx/Politics_Is_Upstreams_of_AI.pdf?dl=0 | |
| Coherent Extrapolated Volition | Eliezer Yudkowsky | 08-03-2017 | https://www.dropbox.com/s/2jldifzkpc82rmk/Coherent_Extrapolated_Volition.pdf?dl=0 | |
| –Cancelled due to illness– | 01-03-2017 | |||
| Towards Interactive Inverse Reinforcement Learning | Armstrong, Leike | 22-02-2017 | https://www.dropbox.com/s/ouom3qzx8aofulv/Towards_Interactive_Inverse_Reinforcement_Learning_.pdf?dl=0 | |
| Notes from the Asilomar Conference on Beneficial AI | Scott Alexander | 15-02-2017 | https://www.dropbox.com/s/4ohpo4fpewwdz7q/Notes_from_the_Asilomar_Conference_on_Beneficial_AI.pdf?dl=0 | |
| My current take on the Paul-MIRI disagreement on alignability of messy AI | Jessica Taylor | 08-02-2017 | https://www.dropbox.com/s/9jtu8njaloxucrv/My_Current_take_on_the_Paul_MIRI_disagreement.pdf?dl=0 | |
| How feasible is the rapid development of Artificial Superintelligence? | Kaj Sotala | 01-02-2017 | https://www.dropbox.com/s/5u79rex6czszt23/How_Feasible_is_the_Rapid_Development_of_Artificial_Superintelligence.pdf?dl=0 | |
| Response to Cegłowski on superintelligence | Matthew Graves | 25-01-2017 | https://www.dropbox.com/s/bzlw8mc7k1fs0ox/Response_to_Ceglowski.pdf?dl=0 | |
| Disjunctive AI scenarios: Individual or collective takeoff? | Kaj Sotala | 18-01-2017 | https://www.dropbox.com/s/sdsm2mpaiq892o3/Individual_or_collective_takeoff.pdf?dl=0 | |
| Policy Desiderata in the Development of Machine Superintelligence | Nick Bostrom | 11-01-2017 | https://www.dropbox.com/s/jt6w0fzli5b0vg1/Policy%20Desiderata.pdf?dl=0 | |
| Concrete Problems in AI Safety | Dario Amodei et al. | 04-01-2017 | https://www.dropbox.com/s/wthme4pnhlipz2q/Concrete.pdf?dl=0 | |
| –Holiday– | 28-12-2016 | |||
| A Wager on the Turing Test: Why I Think I Will Win | Ray Kurzweil | 21-12-2016 | https://www.dropbox.com/s/iurbqzyaq9tt69f/Kurzweil.pdf?dl=0 | |
| Responses to Catastrophic AGI Risk: A Survey | Sotala, Yampolskiy | 14-12-2016 | https://www.dropbox.com/s/iywy8znxx8yn1xt/Responses%20to%20AI.pdf?dl=0 | |
| Discussion of ‘Superintelligence: Paths, Dangers, Strategies’ | Neil Lawrence | 07-12-2016 | https://www.dropbox.com/s/pyhb55mz65bhe9m/Neil%20Lawrence%20-%20Future%20of%20AI.pdf?dl=0 | |
| Davis on AI capability and motivation | Rob Bensinger | 30-11-2016 | https://www.dropbox.com/s/eatjziiqsj5bmmg/Rob%20Bensinger%20Reply%20to%20Ernest%20Davis.pdf?dl=0 | |
| Ethical guidelines for a Superintelligence | Ernest Davis | 22-11-2016 | https://www.dropbox.com/s/7j14li21igzi5gx/Ethical%20Guidelines%20for%20a%20Superintelligence.pdf?dl=0 | |
| Superintelligence: Chapter 15 | Nick Bostrom | 15-11-2016 | https://www.dropbox.com/s/5jsusue656rdf2r/15%20Crunch%20Time.pdf?dl=0 | |
| Superintelligence: Chapter 14 | Nick Bostrom | 09-11-2016 | https://www.dropbox.com/s/l2myz5c7t3a6at9/14%20Science%20and%20Technology%20Strategy.pdf?dl=0 | |
| Superintelligence: Chapter 11 | Nick Bostrom | 01-11-2016 | https://www.dropbox.com/s/vj9j5saz39ese5i/11%20Multipolar%20Scenarios.pdf?dl=0 | |
| Superintelligence: Chapter 9 (2/2) | Nick Bostrom | 25-10-2016 | https://www.dropbox.com/s/ux66z2ujz9jgofe/9.%20Motivation%20Selection%20Methods.pdf?dl=0 | |
| Superintelligence: Chapter 9 (1/2) | Nick Bostrom | 18-10-2016 | https://www.dropbox.com/s/0mgnqcq075vehfv/Capability%20Control%20Methods.pdf?dl=0 | |
| Superintelligence: Chapter 8 | Nick Bostrom | 11-10-2016 | https://www.dropbox.com/s/ihj35vxbevfghal/Default%20doom.pdf?dl=0 | |
| Superintelligence: Chapter 7 | Nick Bostrom | 04-10-2016 | https://www.dropbox.com/s/pps6di0pza7wvab/The%20superintelligent%20Will.pdf?dl=0 | |
| Superintelligence: Chapter 6 | Nick Bostrom | 27-09-2016 | ||
| Superintelligence: Chapter 5 | Nick Bostrom | 20-09-2016 | ||
| Taxonomy of Pathways to Dangerous Artificial Intelligence | Roman V. Yampolskiy | 13-09-2016 | ||
| Unethical Research: How to Create a Malevolent Artificial Intelligence | Roman V. Yampolskiy | 06-09-2016 | ||
| Superintelligence: Chapter 4 | Nick Bostrom | 30-08-2016 | ||
| Superintelligence: Chapter 3 | Nick Bostrom | 23-08-2016 | ||
| Superintelligence: Chapter 1+2 | Nick Bostrom | 16-08-2016 | ||
| Why I am skeptical of risks from AI | Alexander Kruel | 09-08-2016 | ||
| –Break due to family extension– | 02-08-2016 | |||
| –Break due to family extension– | 26-07-2016 | |||
| Intelligence Explosion FAQ | Luke Muehlhauser | 19-07-2016 | ||
| A toy model of the treacherous turn | Stuart Armstrong | 12-07-2016 | ||
| The Fable of the Dragon Tyrant | Nick Bostrom | 05-07-2016 | ||
| The Fun Theory Sequence | Eliezer Yudkowsky | 28-06-2016 | ||
| Intelligence Explosion Microeconomics | Eliezer Yudkowsky | 21-06-2016 | ||
| Strategic Implications of Openness in AI Development | Nick Bostrom | 14-06-2016 | ||
| That Alien Message | Eliezer Yudkowsky | 07-06-2016 | ||
| The Value Learning Problem | Nate Soares | 31-05-2016 | ||
| Decisive Strategic Advantage without a Hard Takeoff | Kaj Sotala | 24-05-2016 |