Artificial intelligence and universal values:
The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By 'alignment' we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimall...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Cambridge, UK
Ethics International Press
2024
|
| Schlagworte: | |
| Zusammenfassung: | The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By 'alignment' we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimally harmful, to humans. There are a large number of techniques that are being experimented with, but this work often fails to specify what values exactly we should be aligning. When making a decision, an agent is supposed to maximize the expected utility of its value function. Classically, this has been referred to as happiness, but this is just one of many things that people value. In order to resolve this issue, we need to determine a set of human values that represent humanity's interests. Although this problem might seem intractable, research shows that people of various cultures and religions actually share more in common than they realize. In this book we review world religions, moral philosophy and evolutionary psychology to elucidate a common set of shared values. We then show how these values can be used to address the alignment problem and conclude with problems and goals for future research. The key audience for this book will be researchers in the field of ethics and artificial intelligence who are interested in, or working on this problem. These people will come from various professions and include philosophers, computer programmers and psychologists, as the problem itself is multi-disciplinary. |
| Beschreibung: | Erscheinungsort auf Verlagsseite recherchiert. |
| Beschreibung: | xiv, 153 Seiten 22 cm |
| ISBN: | 9781804416051 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV049930468 | ||
| 003 | DE-604 | ||
| 005 | 20250128 | ||
| 007 | t| | ||
| 008 | 241030s2024 xx |||| 00||| eng d | ||
| 020 | |a 9781804416051 |c hardback |9 978-1-80441-605-1 | ||
| 035 | |a (OCoLC)1477606155 | ||
| 035 | |a (DE-599)BVBBV049930468 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-12 |a DE-188 | ||
| 084 | |a MS 4855 |0 (DE-625)164810: |2 rvk | ||
| 084 | |a CC 7270 |0 (DE-625)161523: |2 rvk | ||
| 100 | 1 | |a Friedenberg, Jay |d 1966- |e Verfasser |0 (DE-588)13182886X |4 aut | |
| 245 | 1 | 0 | |a Artificial intelligence and universal values |c by Jay Friedenberg |
| 246 | 1 | 3 | |a AI and universal values |
| 264 | 1 | |a Cambridge, UK |b Ethics International Press |c 2024 | |
| 300 | |a xiv, 153 Seiten |c 22 cm | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Erscheinungsort auf Verlagsseite recherchiert. | ||
| 520 | 3 | |a The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By 'alignment' we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimally harmful, to humans. There are a large number of techniques that are being experimented with, but this work often fails to specify what values exactly we should be aligning. When making a decision, an agent is supposed to maximize the expected utility of its value function. Classically, this has been referred to as happiness, but this is just one of many things that people value. In order to resolve this issue, we need to determine a set of human values that represent humanity's interests. Although this problem might seem intractable, research shows that people of various cultures and religions actually share more in common than they realize. In this book we review world religions, moral philosophy and evolutionary psychology to elucidate a common set of shared values. We then show how these values can be used to address the alignment problem and conclude with problems and goals for future research. The key audience for this book will be researchers in the field of ethics and artificial intelligence who are interested in, or working on this problem. These people will come from various professions and include philosophers, computer programmers and psychologists, as the problem itself is multi-disciplinary. | |
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Wertethik |0 (DE-588)4602196-6 |2 gnd |9 rswk-swf |
| 653 | 0 | |a Artificial intelligence / Moral and ethical aspects | |
| 653 | 0 | |a Intelligence artificielle / Aspect moral | |
| 689 | 0 | 0 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 0 | 1 | |a Wertethik |0 (DE-588)4602196-6 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-1-80441-606-8 |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-035268848 | |
Datensatz im Suchindex
| _version_ | 1822497762012299264 |
|---|---|
| adam_text | |
| any_adam_object | |
| author | Friedenberg, Jay 1966- |
| author_GND | (DE-588)13182886X |
| author_facet | Friedenberg, Jay 1966- |
| author_role | aut |
| author_sort | Friedenberg, Jay 1966- |
| author_variant | j f jf |
| building | Verbundindex |
| bvnumber | BV049930468 |
| classification_rvk | MS 4855 CC 7270 |
| ctrlnum | (OCoLC)1477606155 (DE-599)BVBBV049930468 |
| discipline | Soziologie Philosophie |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV049930468</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20250128</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">241030s2024 xx |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781804416051</subfield><subfield code="c">hardback</subfield><subfield code="9">978-1-80441-605-1</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1477606155</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV049930468</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-12</subfield><subfield code="a">DE-188</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">MS 4855</subfield><subfield code="0">(DE-625)164810:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">CC 7270</subfield><subfield code="0">(DE-625)161523:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Friedenberg, Jay</subfield><subfield code="d">1966-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)13182886X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Artificial intelligence and universal values</subfield><subfield code="c">by Jay Friedenberg</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">AI and universal values</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge, UK</subfield><subfield code="b">Ethics International Press</subfield><subfield code="c">2024</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xiv, 153 Seiten</subfield><subfield code="c">22 cm</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Erscheinungsort auf Verlagsseite recherchiert.</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By 'alignment' we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimally harmful, to humans. There are a large number of techniques that are being experimented with, but this work often fails to specify what values exactly we should be aligning. When making a decision, an agent is supposed to maximize the expected utility of its value function. Classically, this has been referred to as happiness, but this is just one of many things that people value. In order to resolve this issue, we need to determine a set of human values that represent humanity's interests. Although this problem might seem intractable, research shows that people of various cultures and religions actually share more in common than they realize. In this book we review world religions, moral philosophy and evolutionary psychology to elucidate a common set of shared values. We then show how these values can be used to address the alignment problem and conclude with problems and goals for future research. The key audience for this book will be researchers in the field of ethics and artificial intelligence who are interested in, or working on this problem. These people will come from various professions and include philosophers, computer programmers and psychologists, as the problem itself is multi-disciplinary.</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Wertethik</subfield><subfield code="0">(DE-588)4602196-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Artificial intelligence / Moral and ethical aspects</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Intelligence artificielle / Aspect moral</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Wertethik</subfield><subfield code="0">(DE-588)4602196-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-1-80441-606-8</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-035268848</subfield></datafield></record></collection> |
| id | DE-604.BV049930468 |
| illustrated | Not Illustrated |
| indexdate | 2025-01-28T13:01:47Z |
| institution | BVB |
| isbn | 9781804416051 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-035268848 |
| oclc_num | 1477606155 |
| open_access_boolean | |
| owner | DE-12 DE-188 |
| owner_facet | DE-12 DE-188 |
| physical | xiv, 153 Seiten 22 cm |
| publishDate | 2024 |
| publishDateSearch | 2024 |
| publishDateSort | 2024 |
| publisher | Ethics International Press |
| record_format | marc |
| spelling | Friedenberg, Jay 1966- Verfasser (DE-588)13182886X aut Artificial intelligence and universal values by Jay Friedenberg AI and universal values Cambridge, UK Ethics International Press 2024 xiv, 153 Seiten 22 cm txt rdacontent n rdamedia nc rdacarrier Erscheinungsort auf Verlagsseite recherchiert. The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By 'alignment' we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimally harmful, to humans. There are a large number of techniques that are being experimented with, but this work often fails to specify what values exactly we should be aligning. When making a decision, an agent is supposed to maximize the expected utility of its value function. Classically, this has been referred to as happiness, but this is just one of many things that people value. In order to resolve this issue, we need to determine a set of human values that represent humanity's interests. Although this problem might seem intractable, research shows that people of various cultures and religions actually share more in common than they realize. In this book we review world religions, moral philosophy and evolutionary psychology to elucidate a common set of shared values. We then show how these values can be used to address the alignment problem and conclude with problems and goals for future research. The key audience for this book will be researchers in the field of ethics and artificial intelligence who are interested in, or working on this problem. These people will come from various professions and include philosophers, computer programmers and psychologists, as the problem itself is multi-disciplinary. Künstliche Intelligenz (DE-588)4033447-8 gnd rswk-swf Wertethik (DE-588)4602196-6 gnd rswk-swf Artificial intelligence / Moral and ethical aspects Intelligence artificielle / Aspect moral Künstliche Intelligenz (DE-588)4033447-8 s Wertethik (DE-588)4602196-6 s DE-604 Erscheint auch als Online-Ausgabe 978-1-80441-606-8 |
| spellingShingle | Friedenberg, Jay 1966- Artificial intelligence and universal values Künstliche Intelligenz (DE-588)4033447-8 gnd Wertethik (DE-588)4602196-6 gnd |
| subject_GND | (DE-588)4033447-8 (DE-588)4602196-6 |
| title | Artificial intelligence and universal values |
| title_alt | AI and universal values |
| title_auth | Artificial intelligence and universal values |
| title_exact_search | Artificial intelligence and universal values |
| title_full | Artificial intelligence and universal values by Jay Friedenberg |
| title_fullStr | Artificial intelligence and universal values by Jay Friedenberg |
| title_full_unstemmed | Artificial intelligence and universal values by Jay Friedenberg |
| title_short | Artificial intelligence and universal values |
| title_sort | artificial intelligence and universal values |
| topic | Künstliche Intelligenz (DE-588)4033447-8 gnd Wertethik (DE-588)4602196-6 gnd |
| topic_facet | Künstliche Intelligenz Wertethik |
| work_keys_str_mv | AT friedenbergjay artificialintelligenceanduniversalvalues AT friedenbergjay aianduniversalvalues |