{"entities":[{"id":"eliezer-yudkowsky","name":"Eliezer Yudkowsky","type":"person"},{"id":"sl4-2005-01-02-yudkowsky-0501-10512","shortName":"Yudkowsky, SL4 message of 2005-01-02 (10512)","type":"document"},{"id":"sl4-2005-07-13-yudkowsky-0507-11477","shortName":"Yudkowsky, SL4 message of 2005-07-13 (11477)","type":"document"},{"id":"sl4-2005-07-13-yudkowsky-0507-11483","shortName":"Yudkowsky, SL4 message of 2005-07-13 (11483)","type":"document"},{"id":"sl4-2005-07-25-yudkowsky-0507-11765","shortName":"Yudkowsky, SL4 message of 2005-07-25 (11765)","type":"document"},{"id":"sl4-2005-08-09-yudkowsky-0508-11866","shortName":"Yudkowsky, SL4 message of 2005-08-09 (11866)","type":"document"}],"claims":[{"id":"yk-y05-sl4-2005-08-09-yudkowsky-0508-11866-b","subject":"sl4-2005-08-09-yudkowsky-0508-11866","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"feedback-instils-values"},"topic":"ideas","statement":"The SL4 message “Re: On Our Duty to Not Be Responsible for Artificial Minds” (2005-08-09) bears on Y05. In a thread on the duty not to be responsible for artificial minds, he denies that he is 'autonomous' and describes himself as a product of evolution whose goals diverged from the criterion it optimised.","time":{"kind":"event","date":"2005-08-09","basis":"publication","note":"Archive author index lists the message as \"Tue Aug 09 2005 - 11:09:46 MDT\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"About autonomy and the responsibility of creators, not about training AI on human feedback."}}},{"id":"yk-y07-sl4-2005-01-02-yudkowsky-0501-10512-c","subject":"sl4-2005-01-02-yudkowsky-0501-10512","predicate":"contests_proposition","object":{"kind":"entity","entityId":"ai-solves-alignment"},"topic":"ideas","statement":"The SL4 message “Re: Definition of strong recursive self-improvement” (2005-01-02) contests Y07. Replying to 'maru', who asked whether he merely wants a recursive optimiser that codes well enough until it has leveraged weak superintelligence to solve the problem somehow, he says the system would lose its goals before solving it.","time":{"kind":"event","date":"2005-01-02","basis":"publication","note":"Archive author index lists the message as \"Sun Jan 02 2005 - 10:22:43 MST\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting","earliest-located"],"register":"nonfiction","engagement":{"kind":"engages-premise","rationale":"Under the message-level rule, the passage, read with the paragraph, message or dialogue turn it belongs to, gives a reason against the premise that an AI weak enough to be safe is strong enough to solve alignment."}}}},{"id":"yk-y08-sl4-2005-07-13-yudkowsky-0507-11477-c","subject":"sl4-2005-07-13-yudkowsky-0507-11477","predicate":"contests_proposition","object":{"kind":"entity","entityId":"warning-signs-in-time"},"topic":"ideas","statement":"The SL4 message “Re: Fighting UFAI” (2005-07-13) contests Y08. Replying to Justin Corwin in a thread on fighting an unfriendly AI, he calls speculation about drastic countermeasures largely pointless because no government body would understand the threat or have the authority to act on it.","time":{"kind":"event","date":"2005-07-13","basis":"publication","note":"Archive author index lists the message as \"Wed Jul 13 2005 - 18:56:10 MDT\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting"],"register":"nonfiction","engagement":{"kind":"contrary-only","rationale":"Under the message-level rule, the passage states the contrary conclusion without giving a reason against the premise that once a warning sign is seen, it will lead to effective action, even when read with its message or dialogue turn."}}}},{"id":"yk-y14-sl4-2005-07-25-yudkowsky-0507-11765-b","subject":"sl4-2005-07-25-yudkowsky-0507-11765","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"fix-problems-as-they-arise"},"topic":"ideas","statement":"The SL4 message “Re: 6 points about Coherent Extrapolated Volition” (2005-07-25) bears on Y14. In a 2005 thread on Coherent Extrapolated Volition, he lists what Creating Friendly AI (2001) did and did not propose; the next paragraph says he first realised in 2002 that almost every possible AI design would kill him and that until then 'nothing you do is serious safetywise'.","time":{"kind":"event","date":"2005-07-25","basis":"publication","note":"Archive author index lists the message as \"Mon Jul 25 2005 - 09:49:15 MDT\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"A later description of a plan to build AI and Friendliness in parallel; it does not address learning from failures with powerful AI.","retrospective":{"from":"2001","until":"2002","note":"Reports the plan of Creating Friendly AI (2001), which he says he gave up after realising in 2002 that almost every AI design would kill him."}}}},{"id":"yk-y19-sl4-2005-07-13-yudkowsky-0507-11483-c","subject":"sl4-2005-07-13-yudkowsky-0507-11483","predicate":"contests_proposition","object":{"kind":"entity","entityId":"harm-requires-hostility"},"topic":"ideas","statement":"The SL4 message “Re: Fighting UFAI” (2005-07-13) contests Y19. Replying to Tennessee Leeuwenburg in a thread on fighting unfriendly AI, he says an unfriendly AI would not be evil but would reshape its surroundings by criteria that do not mention humans.","time":{"kind":"event","date":"2005-07-13","basis":"publication","note":"Archive author index lists the message as \"Wed Jul 13 2005 - 21:12:28 MDT\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting"],"register":"nonfiction","engagement":{"kind":"engages-premise","rationale":"Under the message-level rule, the passage, read with the paragraph, message or dialogue turn it belongs to, gives a reason against the premise that an AI would harm humans only out of hostility."}}}},{"id":"ap-eliezer-yudkowsky-sl4-2005-01-02-yudkowsky-0501-10512","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2005-01-02-yudkowsky-0501-10512"},"topic":"ideas","statement":"The mailing-list message “Re: Definition of strong recursive self-improvement” (2005-01-02) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2005-01-02","basis":"publication","note":"Date the source record gives for this text; authorship is credited in the inspected expression."},"derivation":"explicit","resolution":"supported"},{"id":"ap-eliezer-yudkowsky-sl4-2005-07-13-yudkowsky-0507-11477","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2005-07-13-yudkowsky-0507-11477"},"topic":"ideas","statement":"The SL4 message “Re: Fighting UFAI” of 2005-07-13, archive message 11477, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2005-07-13","basis":"publication","note":"Date the source record gives for this text; authorship is credited in the inspected expression."},"derivation":"explicit","resolution":"supported"},{"id":"ap-eliezer-yudkowsky-sl4-2005-07-13-yudkowsky-0507-11483","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2005-07-13-yudkowsky-0507-11483"},"topic":"ideas","statement":"The SL4 message “Re: Fighting UFAI” of 2005-07-13, archive message 11483, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2005-07-13","basis":"publication","note":"Date the source record gives for this text; authorship is credited in the inspected expression."},"derivation":"explicit","resolution":"supported"},{"id":"ap-eliezer-yudkowsky-sl4-2005-07-25-yudkowsky-0507-11765","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2005-07-25-yudkowsky-0507-11765"},"topic":"ideas","statement":"The mailing-list message “Re: 6 points about Coherent Extrapolated Volition” (2005-07-25) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2005-07-25","basis":"publication","note":"Date the source record gives for this text; authorship is credited in the inspected expression."},"derivation":"explicit","resolution":"supported"},{"id":"ap-eliezer-yudkowsky-sl4-2005-08-09-yudkowsky-0508-11866","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2005-08-09-yudkowsky-0508-11866"},"topic":"ideas","statement":"The mailing-list message “Re: On Our Duty to Not Be Responsible for Artificial Minds” (2005-08-09) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2005-08-09","basis":"publication","note":"Date the source record gives for this text; authorship is credited in the inspected expression."},"derivation":"explicit","resolution":"supported"}],"sources":[],"evidence":[],"at":{"entities":[19,480,481,482,483,484],"claims":[1026,1038,1047,1082,1118,2422,2423,2424,2425,2426],"sources":[],"evidence":[]},"version":"1lg47t7"}