Welcome to the Robustly Beneficial Wiki - Revision history

Lê Nguyên Hoang: /* How to solve AI ethics (hopefully) */

2020-03-02T09:37:25Z

How to solve AI ethics (hopefully)

Lê Nguyên Hoang: /* Why AI safety and ethics is harder than meets the eye */

2020-02-22T22:33:14Z

Why AI safety and ethics is harder than meets the eye

Lê Nguyên Hoang: /* Why AI ethics is becoming critical */

2020-02-13T07:27:23Z

Why AI ethics is becoming critical

Lê Nguyên Hoang: /* How today's (and probably tomorrow's) AIs work */

2020-02-03T12:07:35Z

How today's (and probably tomorrow's) AIs work

Lê Nguyên Hoang: /* How to solve AI ethics (hopefully) */

2020-02-03T06:18:14Z

How to solve AI ethics (hopefully)

Lê Nguyên Hoang: /* About the authors */

2020-02-02T07:46:10Z

About the authors

Lê Nguyên Hoang at 11:38, 1 February 2020

2020-02-01T11:38:13Z

Lê Nguyên Hoang at 06:50, 30 January 2020

2020-01-30T06:50:45Z

Lê Nguyên Hoang: /* Why AI safety and ethics is harder than meets the eye */

2020-01-28T13:51:24Z

Why AI safety and ethics is harder than meets the eye

Lê Nguyên Hoang: /* How today's (and probably tomorrow's) AIs work */

2020-01-27T13:08:55Z

How today's (and probably tomorrow's) AIs work

@@ Line 35: / Line 35: @@
 === How to solve AI ethics (hopefully) ===
-To solve AI ethics, [http://ceur-ws.org/Vol-2301/paper_1.pdf Hoang][https://dblp.org/rec/bibtex/conf/aaai/Hoang19 19a] proposed the [[ABCDE roadmap]], which decomposes the [[alignment]] problem into numerous (hopefully) orthogonal and complementary subproblems. Such subproblems include [[data certification]], perhaps through [[Blockchain]], [[world model inference]] through [[Bayesianism]] and/or [[representational learning]], [[volition]] learning perhaps from [[Preference learning from comparisons|comparisons]] and [[social choice]] solutions, [[corrigibility]] and safe [[reinforcement learning]].
+To solve AI ethics, [http://ceur-ws.org/Vol-2301/paper_1.pdf Hoang][https://dblp.org/rec/bibtex/conf/aaai/Hoang19 19a] proposed the [[ABCDE roadmap]], which decomposes the [[alignment]] problem into numerous (hopefully) orthogonal and complementary subproblems. Such subproblems include [[data certification]], perhaps through [[Blockchain]], [[world model inference]] of [[knowledge representation]] through [[Bayesianism]] and/or [[representational learning]], [[volition]] learning perhaps from [[Preference learning from comparisons|comparisons]] and [[social choice]] solutions, [[corrigibility]] and safe [[reinforcement learning]].
 The fabulous endeavor to make AIs robustly beneficial can seem overwhelming, given how extraordinarily interdisciplinary it is. While it is worthwhile to have an overview of the problem, we believe it is also useful for aspiring contributors to identify more precise problems they can contribute to. In this wiki, we propose targeted research directions for different expertises and research interests. Please check the following pages that may be of interest to you.

@@ Line 31: / Line 31: @@
 We want to get algorithms to do what we would really want them to do. But this turns out to raise numerous highly nontrivial problems, like [[Goodhart's law]], [[overfitting]], [[robust statistics]], [[confounding variables]], [[adversarial attacks]], [[algorithmic bias]], [[cognitive bias]], [[backfire effect]], [[distributional shift]], [[privacy]], [[human liabilities]], [[interpretability]], [[reward hacking]], [[wireheading]] and [[instrumental convergence]]. Because of all such problems, it seems crucial that algorithms be able to reason about their ignorance, using [[Bayesianism|Bayesian]] principles, [[moral uncertainty]] and [[second opinion querying]]. Algorithms must be [[robustly beneficial]].
-AI ethics also demands that we solve thorny philosophical dilemmas, like the [[repugnant conclusion]], [[Newcomb's paradox]] and [[moral realism]]. Unfortunately, we have numerous [[cognitive bias|cognitive biases]], which seem critical to understand to solve AI ethics. Results about [[counterfactual]], [[von Neumann-Morgenstern theorem]] and [[Dutch book]] also seem useful to consider.
+AI ethics also demands that we solve thorny philosophical dilemmas, like the [[repugnant conclusion]], [[Newcomb's paradox]] and [[moral realism]]. Unfortunately, we have numerous [[cognitive bias|cognitive biases]], which seem critical to understand to solve AI ethics. Results about [[counterfactual]], [[von Neumann-Morgenstern preferences]] and [[Dutch book]] also seem useful to consider.
 === How to solve AI ethics (hopefully) ===

@@ Line 11: / Line 11: @@
 === Why AI ethics is becoming critical ===
-If you are new to AI ethics, you should probably start with the [[AI risks]] page. You could then go into arguably today's most important case of AI ethics, namely [[YouTube]]. Note that algorithms also offer formidable [[AI opportunities]] that are definitely worth considering. Find out more by reading about [[online polarization]], [[misinformation]], [[addiction]], [[mental health]] or [[hate]].
+If you are new to AI ethics, you should probably start with the [[AI risks]] page. You could then go into arguably today's most important case of AI ethics, namely [[YouTube]]. Note that algorithms also offer formidable [[AI opportunities]] that are definitely worth considering. Find out more by reading about [[online polarization]], [[misinformation]], [[addiction]], [[mental health]] or [[hate]]. And as an example of an urgent AI ethics dilemma, check [https://twitter.com/le_science4all/status/1227690739104174080 this Twitter thread] on responses to a "is climate change a hoax?" search.
 And if you know little about the current state of algorithmic research, you might want to check the latest [[impressive advances in AI]]. Or you could check some [[funny applications of AI]]. You can also read Lê's [https://www.lesswrong.com/posts/bwqDrSZvhEDKxRf6z/a-rant-against-robots rant against robots].

@@ Line 19: / Line 19: @@
 The most important principle of today's AI is surely [[machine learning]]. Today, it mostly relies on [[stochastic gradient descent]] for (deep) [[neural networks]], which allow [[representational learning]] (see [[convolutional neural network]], [[residual network]], [[transformer]]). See also [[Turing 1950]], [[convexity]], [[generative adversarial network]], [[specialized hardware]] and [[linear systems]].
-[[Bayesianism]] has been argued to be the ideal form of supervised and unsupervised learning, if we had infinite computational power (see [[Solomonoff's demon]]). It has numerous desirable properties, like [[statistical admissibility]], [[Bayesian agreement]] or the [[Bayesian brain]] hypothesis. See also [[Bayesian examination]] and [[conjugate priors]].
+[[Bayesianism]] has been argued to be the ideal form of supervised and unsupervised learning, if we had infinite computational power (see [[Solomonoff's demon]], [[Laplace 1814]]). It has numerous desirable properties, like [[statistical admissibility]], [[Bayesian agreement]] or the [[Bayesian brain]] hypothesis. See also [[Bayesian examination]] and [[conjugate priors]].
 A branch of learning called [[reinforcement learning]], which relies on [[Q-learning]] or [[policy learning]], seems likely to become the core framework of today's and tomorrow's AIs. [[AIXI]] achieves the upper-bound for [[Legg-Hutter intelligence]], which aims to measure [[artificial general intelligence|general intelligence]].

@@ Line 35: / Line 35: @@
 === How to solve AI ethics (hopefully) ===
-To solve AI ethics, [http://ceur-ws.org/Vol-2301/paper_1.pdf Hoang][https://dblp.org/rec/bibtex/conf/aaai/Hoang19 19a] proposed the [[ABCDE roadmap]], which decomposes the [[alignment]] problem into numerous (hopefully) orthogonal and complementary subproblems. Such subproblems include [[data certification]], perhaps through [[Blockchain]], [[world model inference]] through [[Bayesianism]] and/or [[representational learning]], [[volition]] learning and [[social choice]] solutions, [[corrigibility]] and safe [[reinforcement learning]].
+To solve AI ethics, [http://ceur-ws.org/Vol-2301/paper_1.pdf Hoang][https://dblp.org/rec/bibtex/conf/aaai/Hoang19 19a] proposed the [[ABCDE roadmap]], which decomposes the [[alignment]] problem into numerous (hopefully) orthogonal and complementary subproblems. Such subproblems include [[data certification]], perhaps through [[Blockchain]], [[world model inference]] through [[Bayesianism]] and/or [[representational learning]], [[volition]] learning perhaps from [[Preference learning from comparisons|comparisons]] and [[social choice]] solutions, [[corrigibility]] and safe [[reinforcement learning]].
 The fabulous endeavor to make AIs robustly beneficial can seem overwhelming, given how extraordinarily interdisciplinary it is. While it is worthwhile to have an overview of the problem, we believe it is also useful for aspiring contributors to identify more precise problems they can contribute to. In this wiki, we propose targeted research directions for different expertises and research interests. Please check the following pages that may be of interest to you.

@@ Line 58: / Line 58: @@
 == About the authors ==
-This wiki is written and edited mostly by members of the [https://groups.google.com/forum/#!forum/lausannealignment Robustly Beneficial group], which regularly meets at EPFL, in Lausanne, Switzerland. Please feel free to [https://groups.google.com/forum/#!forum/lausannealignment ask to join]. So far, the main authors are [[User:Lê_Nguyên_Hoang|Lê Nguyên Hoang]], [[User:El_Mahdi_El_Mhamdi|El Mahdi El Mhamdi]] and [[User:Louis_Faucon|Louis Faucon]].
+This wiki is written and edited mostly by members of the [[Robustly Beneficial group]], which regularly meets at EPFL, in Lausanne, Switzerland. Please feel free to [https://groups.google.com/forum/#!forum/lausannealignment ask to join]. So far, the main authors are [[User:Lê_Nguyên_Hoang|Lê Nguyên Hoang]], [[User:El_Mahdi_El_Mhamdi|El Mahdi El Mhamdi]] and [[User:Louis_Faucon|Louis Faucon]].
 Lê and Mahdi recently co-wrote the book <em>The Fabulous Endeavor: Make Artificial Intelligence Robustly Beneficial</em> [https://laboutique.edpsciences.fr/produit/1107/9782759824304/Le%20fabuleux%20chantier HoangElmhamdi][https://scholar.google.ch/scholar?hl=en&as_sdt=0%2C5&q=Le+fabuleux+chantier%3A+Rendre+l%27intelligence+artificielle+robustement+b%C3%A9n%C3%A9fique&btnG= 19<sup>FR</sup>] (the English version is pending).

@@ Line 1: / Line 1: @@
 Welcome to the [[Robustly beneficial|Robustly Beneficial]] wiki!!
-This wiki aims to better grasp the scope and the limits of current AI ethics research. It lists references, key ideas and relevant open questions to make algorithms robustly beneficial. Please check also our [https://www.youtube.com/watch?v=WWbw4cla2jw&list=PLgqL_7nXb23FKk_rUfs7vnvyrPshYPfA8 Robustly Beneficial Podcast] (iTunes, RSS), our [https://www.youtube.com/playlist?list=PLgqL_7nXb23HvhToBb9FwFxj83navY6oq&playnext=1&index=1 Robustly Beneficial Talks] and our [https://twitter.com/robustlyb Twitter account].
+This wiki aims to better grasp the scope and the limits of current AI ethics research. It lists references, key ideas and relevant open questions to make algorithms robustly beneficial. Please check also our [https://www.youtube.com/watch?v=WWbw4cla2jw&list=PLgqL_7nXb23FKk_rUfs7vnvyrPshYPfA8 Robustly Beneficial Podcast] ([https://podcasts.apple.com/fr/podcast/robustly-beneficial-podcast/id1496159681 iTunes], [https://playlists.podmytube.com/UCgl_MmjatQif8juz3Lt6iPw/PLgqL_7nXb23FKk_rUfs7vnvyrPshYPfA8.xml RSS]), our [https://www.youtube.com/playlist?list=PLgqL_7nXb23HvhToBb9FwFxj83navY6oq&playnext=1&index=1 Robustly Beneficial Talks] and our [https://twitter.com/robustlyb Twitter account].
 The wiki has just been launched, so most pages are still being written. But they will never be finished — this is the whole point of a wiki!

@@ Line 29: / Line 29: @@
 === Why AI safety and ethics is harder than meets the eye ===
-We want to get algorithms to do what we would really want them to do. But this turns out to raise numerous highly nontrivial problems, like [[Goodhart's law]], [[overfitting]], [[robust statistics]], [[confounding variables]], [[adversarial attacks]], [[algorithmic bias]], [[cognitive bias]], [[backfire effect]], [[distributional shift]], [[privacy]], [[interpretability]], [[reward hacking]], [[wireheading]] and [[instrumental convergence]]. Because of all such problems, it seems crucial that algorithms be able to reason about their ignorance, using [[Bayesianism|Bayesian]] principles, [[moral uncertainty]] and [[second opinion querying]]. Algorithms must be [[robustly beneficial]].
+We want to get algorithms to do what we would really want them to do. But this turns out to raise numerous highly nontrivial problems, like [[Goodhart's law]], [[overfitting]], [[robust statistics]], [[confounding variables]], [[adversarial attacks]], [[algorithmic bias]], [[cognitive bias]], [[backfire effect]], [[distributional shift]], [[privacy]], [[human liabilities]], [[interpretability]], [[reward hacking]], [[wireheading]] and [[instrumental convergence]]. Because of all such problems, it seems crucial that algorithms be able to reason about their ignorance, using [[Bayesianism|Bayesian]] principles, [[moral uncertainty]] and [[second opinion querying]]. Algorithms must be [[robustly beneficial]].
 AI ethics also demands that we solve thorny philosophical dilemmas, like the [[repugnant conclusion]], [[Newcomb's paradox]] and [[moral realism]]. Unfortunately, we have numerous [[cognitive bias|cognitive biases]], which seem critical to understand to solve AI ethics. Results about [[counterfactual]], [[von Neumann-Morgenstern theorem]] and [[Dutch book]] also seem useful to consider.

@@ Line 17: / Line 17: @@
 === How today's (and probably tomorrow's) AIs work ===
-The most important principle of today's AI is surely [[machine learning]]. Today, it mostly relies on [[stochastic gradient descent]] for (deep) [[neural networks]], which allow [[representational learning]] (see [[convolutional neural network]], [[residual network]], [[transformer]]). See also [[Turing 1950]], [[convexity]], [[generative adversarial network]] and [[linear systems]].
+The most important principle of today's AI is surely [[machine learning]]. Today, it mostly relies on [[stochastic gradient descent]] for (deep) [[neural networks]], which allow [[representational learning]] (see [[convolutional neural network]], [[residual network]], [[transformer]]). See also [[Turing 1950]], [[convexity]], [[generative adversarial network]], [[specialized hardware]] and [[linear systems]].
 [[Bayesianism]] has been argued to be the ideal form of supervised and unsupervised learning, if we had infinite computational power (see [[Solomonoff's demon]]). It has numerous desirable properties, like [[statistical admissibility]], [[Bayesian agreement]] or the [[Bayesian brain]] hypothesis. See also [[Bayesian examination]] and [[conjugate priors]].