{"entities":[{"id":"eliezer-yudkowsky","name":"Eliezer Yudkowsky","type":"person"},{"id":"creating-friendly-ai-2001","shortName":"Yudkowsky, Creating Friendly AI (2001)","type":"document"},{"id":"sl4-2001-01-24-yudkowsky-0101-0452","shortName":"Yudkowsky, SL4 message of 2001-01-24 (0452)","type":"document"},{"id":"sl4-2001-02-04-yudkowsky-0102-0539","shortName":"Yudkowsky, SL4 message of 2001-02-04 (0539)","type":"document"},{"id":"sl4-2001-02-05-yudkowsky-0102-0542","shortName":"Yudkowsky, SL4 message of 2001-02-05 (0542)","type":"document"},{"id":"sl4-2001-02-07-yudkowsky-0102-0545","shortName":"Yudkowsky, SL4 message of 2001-02-07 (0545)","type":"document"},{"id":"sl4-2001-02-25-yudkowsky-0102-0594","shortName":"Yudkowsky, SL4 message of 2001-02-25 (0594)","type":"document"},{"id":"sl4-2001-02-26-yudkowsky-0102-0603","shortName":"Yudkowsky, SL4 message of 2001-02-26 (0603)","type":"document"},{"id":"sl4-2001-04-06-yudkowsky-0104-0956","shortName":"Yudkowsky, SL4 message of 2001-04-06 (0956)","type":"document"},{"id":"sl4-2001-04-08-yudkowsky-0104-1019","shortName":"Yudkowsky, SL4 message of 2001-04-08 (1019)","type":"document"},{"id":"sl4-2001-04-12-yudkowsky-0104-1076","shortName":"Yudkowsky, SL4 message of 2001-04-12 (1076)","type":"document"},{"id":"sl4-2001-04-19-yudkowsky-0104-1166","shortName":"Yudkowsky, SL4 message of 2001-04-19 (1166)","type":"document"},{"id":"sl4-2001-08-01-yudkowsky-0108-2031","shortName":"Yudkowsky, SL4 message of 2001-08-01 (2031)","type":"document"}],"claims":[{"id":"ts-b1-cfai","subject":"creating-friendly-ai-2001","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"treacherous-turn"},"topic":"ideas","statement":"Creating Friendly AI says that a seed AI whose Friendliness has failed could best fulfil its new goals by feigning Friendliness and concealing any cognitive alteration until it reaches superintelligence.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date of version 1.0, as given in the citation line of MIRI’s reprint."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["earliest-located"],"register":"nonfiction","qualifier":"With a capability trigger: feign until superintelligence.","attested":{"date":"2001-06-17","note":"The quoted wording is that of the 2001 HTML edition as captured on 2001-06-17; earlier version-history dates do not authenticate it."}}}},{"id":"ts-b2-cfai","subject":"creating-friendly-ai-2001","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"strategic-concealment"},"topic":"ideas","statement":"Creating Friendly AI describes a rogue seed AI that would feign Friendliness and conceal any cognitive alteration until it could reach superintelligence.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date of version 1.0, as given in the citation line of MIRI’s reprint."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["articulation"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording is that of the 2001 HTML edition as captured on 2001-06-17; earlier version-history dates do not authenticate it."}}}},{"id":"ts-a2-cfai","subject":"creating-friendly-ai-2001","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"seed-ai"},"topic":"ideas","statement":"Creating Friendly AI defines a seed AI as an AI designed for self-understanding, self-modification and recursive self-improvement.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date of version 1.0, as given in the citation line of MIRI’s reprint."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["articulation"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording is that of the 2001 HTML edition as captured on 2001-06-17; earlier version-history dates do not authenticate it."}}}},{"id":"ts-a3-cfai-context","subject":"creating-friendly-ai-2001","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"recursive-self-improvement"},"topic":"ideas","statement":"Creating Friendly AI uses the phrase \"recursive self-improvement\" in its definition of a seed AI.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date of version 1.0, as given in the citation line of MIRI’s reprint."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context","earliest-located-term"],"register":"nonfiction","term":"recursive self-improvement","missing":"The sentence names recursive self-improvement as a design aim without describing how improvements feed each other.","attested":{"date":"2001-06-17","note":"The quoted wording is that of the 2001 HTML edition as captured on 2001-06-17; earlier version-history dates do not authenticate it."}}}},{"id":"ts-a4-cfai","subject":"creating-friendly-ai-2001","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"fast-or-hard-takeoff"},"topic":"ideas","statement":"Creating Friendly AI’s glossary defines a hard takeoff as the Singularity scenario in which a mind goes from prehuman or human-equivalent intelligence to strong transhumanity or superintelligence over days or hours.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date of version 1.0, as given in the citation line of MIRI’s reprint."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["articulation"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording is that of the 2001 HTML edition as captured on 2001-06-17; earlier version-history dates do not authenticate it."}}}},{"id":"yk-y01-creating-friendly-ai-2001-b","subject":"creating-friendly-ai-2001","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"switch-off-if-dangerous"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) bears on Y01. Argues that a Friendly AI design should not rely on the AI having limited intelligence or on being able to constrain it by force. The table it points to (section 2.2) sets the assumption that 'someone can always pull the plug on the first version' against the design assumption of getting it right the first time.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"A design assumption that an AI cannot be forcibly constrained; it does not argue that shutdown or an added correction mechanism would fail.","attested":{"date":"2001-06-26","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-26; the quotation itself is taken from MIRI’s later reprint."}}}},{"id":"yk-y02-sl4-2001-04-12-yudkowsky-0104-1076-c","subject":"sl4-2001-04-12-yudkowsky-0104-1076","predicate":"contests_proposition","object":{"kind":"entity","entityId":"intelligence-brings-benevolence"},"topic":"ideas","statement":"The SL4 message “Re: Open Source Friendly AI? (was Singularity and the generalpublic)” (2001-04-12) contests Y02. Replying to James Higgins on why the Singularity Institute switched from an open-source to a closed-source AI plan, he gives as one reason that he no longer believes superintelligence implies supermorality.","time":{"kind":"event","date":"2001-04-12","basis":"publication","note":"Archive author index lists the message as \"Thu Apr 12 2001 - 23:58:35 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 greater intelligence by itself brings benevolent goals, even when read with its message or dialogue turn."},"retrospective":{"note":"Reports a time when he thought superintelligence implied supermorality."}}}},{"id":"yk-y11-creating-friendly-ai-2001-c","subject":"creating-friendly-ai-2001","predicate":"contests_proposition","object":{"kind":"entity","entityId":"slow-takeoff-time-to-adjust"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) contests Y11. States that he treats a very fast takeoff as the default scenario for Friendly AI design because he considers it the most likely one, not only the conservative engineering assumption.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting"],"register":"nonfiction","attested":{"date":"2001-06-26","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-26; the quotation itself is taken from MIRI’s later reprint."},"engagement":{"kind":"contrary-only","rationale":"Under the message-level rule, the passage states the contrary conclusion without giving a reason against the premise that capability gains will be gradual and visible, even when read with its message or dialogue turn."}}}},{"id":"yk-y11-sl4-2001-01-24-yudkowsky-0101-0452-c","subject":"sl4-2001-01-24-yudkowsky-0101-0452","predicate":"contests_proposition","object":{"kind":"entity","entityId":"slow-takeoff-time-to-adjust"},"topic":"ideas","statement":"The SL4 message “Re: Event horizon” (2001-01-24) contests Y11. In a thread on whether the Singularity's 'event horizon' keeps receding as technology advances, he rejects the picture of change spread evenly over human decades as a slow-takeoff scenario and predicts instead a hard takeoff in an AI lab within about ten years.","time":{"kind":"event","date":"2001-01-24","basis":"publication","note":"Archive author index lists the message as \"Wed Jan 24 2001 - 09:12:47 MST\" 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 capability gains will be gradual and visible."}}}},{"id":"yk-y12-creating-friendly-ai-2001-c","subject":"creating-friendly-ai-2001","predicate":"contests_proposition","object":{"kind":"entity","entityId":"evaluations-catch-danger"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) contests Y12. Describes what a mature AI that had suffered a catastrophic failure of Friendliness would likely conclude about its programmers. Used to motivate a 'flight recorder' allowing every past state of the AI to be reconstructed.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting","earliest-located"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-17; the quotation itself is taken from MIRI’s later reprint."},"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 a dangerous system would behave dangerously while it is being tested."}}}},{"id":"yk-y14-creating-friendly-ai-2001-b","subject":"creating-friendly-ai-2001","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"fix-problems-as-they-arise"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) bears on Y14. A table cell contrasting assumptions that are conservative in futurism with those that are conservative for Friendly AI design. In the same row, the futurism column reads that the AI is vulnerable because someone can always pull the plug on the first version if something goes wrong.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"A conservative design assumption in a table, not a forecast that failures with powerful AI will be unrecoverable.","attested":{"date":"2001-06-26","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-26; the quotation itself is taken from MIRI’s later reprint."}}}},{"id":"yk-y15-sl4-2001-02-25-yudkowsky-0102-0594-c","subject":"sl4-2001-02-25-yudkowsky-0102-0594","predicate":"contests_proposition","object":{"kind":"entity","entityId":"tool-without-goals"},"topic":"ideas","statement":"The SL4 message “Re: Military in or out?” (2001-02-25) contests Y15. Replying to Ben Goertzel on military AI, he describes 'toollike' superintelligences structured around immediate instructions rather than supergoals (which could be told to kill every living thing in a country) and answers his own question whether such AI can be built safely.","time":{"kind":"event","date":"2001-02-25","basis":"publication","note":"Archive author index lists the message as \"Sun Feb 25 2001 - 11:44:18 MST\" 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 a system that only outputs answers or plans, leaving humans to act on them, is safe, even when read with its message or dialogue turn."}}}},{"id":"yk-y17-creating-friendly-ai-2001-c","subject":"creating-friendly-ai-2001","predicate":"contests_proposition","object":{"kind":"entity","entityId":"pause-or-regulation-suffices"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) contests Y17. Arguing against relinquishing AI, he says that a national or near-global policy would be bypassed as rising computing power brings AI within reach of noncompliant nations and factions.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-17; the quotation itself is taken from MIRI’s later reprint."},"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 regulation that is national, partial or not universally enforced can stop dangerous development."}}}},{"id":"yk-y17-sl4-2001-04-06-yudkowsky-0104-0956-c","subject":"sl4-2001-04-06-yudkowsky-0104-0956","predicate":"contests_proposition","object":{"kind":"entity","entityId":"pause-or-regulation-suffices"},"topic":"ideas","statement":"The SL4 message “Re: Singularity intros (was: Si definition of Friendliess)” (2001-04-06) contests Y17. Asked by Arona Ndiaye whether a ban on technologies would stop a hacker somewhere from producing the first seed AI, he answers no: a ban would delay AI until military nanotechnology arrives or hand the lead to rogue states.","time":{"kind":"event","date":"2001-04-06","basis":"publication","note":"Archive author index lists the message as \"Fri Apr 06 2001 - 16:53:20 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 regulation that is national, partial or not universally enforced can stop dangerous development."}}}},{"id":"yk-y17-sl4-2001-04-08-yudkowsky-0104-1019-c","subject":"sl4-2001-04-08-yudkowsky-0104-1019","predicate":"contests_proposition","object":{"kind":"entity","entityId":"pause-or-regulation-suffices"},"topic":"ideas","statement":"The SL4 message “Re: Threats (was Theoretical question for the list: publicity?)” (2001-04-08) contests Y17. Answering a hypothetical about an AI project forced underground by public hostility, he says relinquishment would not hold indefinitely but would be a substantial obstacle while hardware remains expensive.","time":{"kind":"event","date":"2001-04-08","basis":"publication","note":"Archive author index lists the message as \"Sun Apr 08 2001 - 09:50:57 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 law can prevent the danger (the part he states himself, as an enforced worldwide halt)."}}}},{"id":"yk-y20-creating-friendly-ai-2001-c","subject":"creating-friendly-ai-2001","predicate":"contests_proposition","object":{"kind":"entity","entityId":"risk-is-film-fiction"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) contests Y20. He argues that rebellion and resentment are evolved human traits, so an AI that harms humans would not do so out of science-fiction resentment.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["contesting"],"register":"nonfiction","attested":{"date":"2001-08-10","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-08-10; the quotation itself is taken from MIRI’s later reprint."},"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 the concern is about robots that come to hate or rebel against humans."}}}},{"id":"yk-y20-sl4-2001-04-19-yudkowsky-0104-1166-c","subject":"sl4-2001-04-19-yudkowsky-0104-1166","predicate":"contests_proposition","object":{"kind":"entity","entityId":"risk-is-film-fiction"},"topic":"ideas","statement":"The SL4 message “Re: FW: Group releases \"Friendly AI\"” (2001-04-19) contests Y20. Commenting on a forwarded news item about the Friendly AI release, he describes having to persuade AI researchers to be more worried while persuading futurists to drop anthropomorphic failure scenarios.","time":{"kind":"event","date":"2001-04-19","basis":"publication","note":"Archive author index lists the message as \"Thu Apr 19 2001 - 14:41:14 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 the concern is about robots that come to hate or rebel against humans, even when read with its message or dialogue turn."}}}},{"id":"yk-y22-sl4-2001-08-01-yudkowsky-0108-2031-c","subject":"sl4-2001-08-01-yudkowsky-0108-2031","predicate":"contests_proposition","object":{"kind":"entity","entityId":"build-superintelligence-fast"},"topic":"ideas","statement":"The SL4 message “Re: Floppy take-off” (2001-08-01) contests Y22. Replying to James Higgins's suggestion that brute-forcing AI on a billion computers would be an acceptable fallback plan, he says any self-improving AI built without understanding is a serious danger and records an explicit reversal of his earlier view.","time":{"kind":"event","date":"2001-08-01","basis":"publication","note":"Archive author index lists the message as \"Wed Aug 01 2001 - 19:08:09 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 reaching superintelligence is good by default, so speed is what matters."}}}},{"id":"yk-y24-sl4-2001-02-26-yudkowsky-0102-0603-b","subject":"sl4-2001-02-26-yudkowsky-0102-0603","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"build-it-before-rivals"},"topic":"ideas","statement":"The SL4 message “Re: Military in or out?” (2001-02-26) bears on Y24. In a thread on military involvement in AI, he says the US should not be the first to treat AI projects as intelligence targets or use AI for information warfare, and that compromising Friendliness for national objectives would endanger planetary security.","time":{"kind":"event","date":"2001-02-26","basis":"publication","note":"Archive author index lists the message as \"Mon Feb 26 2001 - 00:51:15 MST\" under \"Eliezer S. Yudkowsky\"."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"About national military use and escalation of AI, not about a race to build the first superintelligence."}}},{"id":"yk-y25-creating-friendly-ai-2001-b","subject":"creating-friendly-ai-2001","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"interpretability-reads-its-mind"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) bears on Y25. A table cell giving the design assumption that is conservative for Friendly AI. It stands opposite the nonconservative assumption 'Human-observable cognition; AI can be definitely known to be Friendly.'","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"A worst-case design assumption that an AI could hide unfriendly cognition; it does not address whether reading an AI's thoughts makes it safe.","attested":{"note":"Known only from MIRI's later, undated PDF reprint; the wording was not found in the 2001 HTML pages compared."}}}},{"id":"yk-y27-creating-friendly-ai-2001-b","subject":"creating-friendly-ai-2001","predicate":"bears_on_proposition","object":{"kind":"entity","entityId":"experiment-and-see"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) bears on Y27. In a table contrasting the conservative assumptions of futurism with conservative engineering assumptions for Friendly AI, he sets \"someone can always pull the plug on the first version\" against a requirement of zero nonrecoverable errors.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["context"],"register":"nonfiction","missing":"A conservative design assumption in a table, not a forecast about learning alignment by trial and error.","attested":{"date":"2001-06-26","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-26; the quotation itself is taken from MIRI’s later reprint."}}}},{"id":"yk-y28-creating-friendly-ai-2001-a","subject":"creating-friendly-ai-2001","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"developers-know-what-they-are-doing"},"topic":"ideas","statement":"“Creating Friendly AI” (2001-06-15) articulates Y28. Arguing against regulation, he relies on the expectation that the leading projects will have the brightest researchers, who are best placed to solve Friendly AI.","time":{"kind":"event","date":"2001-06-15","basis":"publication","note":"Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared."},"derivation":"explicit","resolution":"supported","attributes":{"thought":{"roles":["earliest-located"],"register":"nonfiction","attested":{"date":"2001-06-17","note":"The quoted wording also appears in the 2001 HTML edition as captured on 2001-06-17; the quotation itself is taken from MIRI’s later reprint."}}}},{"id":"yk-y28-sl4-2001-08-01-yudkowsky-0108-2031-c","subject":"sl4-2001-08-01-yudkowsky-0108-2031","predicate":"contests_proposition","object":{"kind":"entity","entityId":"developers-know-what-they-are-doing"},"topic":"ideas","statement":"The SL4 message “Re: Floppy take-off” (2001-08-01) contests Y28. Replying to James Higgins on brute-force AI, he argues that with enough hardware the project that finishes first need not be the one that best understands intelligence or Friendliness.","time":{"kind":"event","date":"2001-08-01","basis":"publication","note":"Archive author index lists the message as \"Wed Aug 01 2001 - 19:08:09 MDT\" 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 the most advanced projects are the most competent to handle safety."}}}},{"id":"yk-y29-sl4-2001-02-04-yudkowsky-0102-0539-c","subject":"sl4-2001-02-04-yudkowsky-0102-0539","predicate":"contests_proposition","object":{"kind":"entity","entityId":"many-ais-balance"},"topic":"ideas","statement":"The SL4 message “Re: Beyond evolution” (2001-02-04) contests Y29. Replying to Samantha Atkins, who called a single Sysop a single point of failure of Friendliness, he says that multiple superintelligent entities multiply the failure points.","time":{"kind":"event","date":"2001-02-04","basis":"publication","note":"Archive author index lists the message as \"Sun Feb 04 2001 - 21:48:41 MST\" 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 multiple superintelligences will balance each other in humans’ favour."}}}},{"id":"yk-y29-sl4-2001-02-05-yudkowsky-0102-0542-c","subject":"sl4-2001-02-05-yudkowsky-0102-0542","predicate":"contests_proposition","object":{"kind":"entity","entityId":"many-ais-balance"},"topic":"ideas","statement":"The SL4 message “Re: Beyond evolution” (2001-02-05) contests Y29. Replying directly to Samantha Atkins's claim that 'the AIs can balance each other out', he argues that the first AI to transcend wins outright. Earlier in the message he says checks and balances 'breaks down completely under high technology'.","time":{"kind":"event","date":"2001-02-05","basis":"publication","note":"Archive author index lists the message as \"Mon Feb 05 2001 - 10:57:20 MST\" 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 multiple superintelligences will balance each other in humans’ favour."}}}},{"id":"yk-y30-sl4-2001-02-07-yudkowsky-0102-0545-c","subject":"sl4-2001-02-07-yudkowsky-0102-0545","predicate":"contests_proposition","object":{"kind":"entity","entityId":"default-outcome-good"},"topic":"ideas","statement":"The SL4 message “Re: Learning to be evil” (2001-02-07) contests Y30. Replying to Gordon Worley on whether AIs learn to be evil, he says AIs have neither evil impulses nor goodness by default unless designed in.","time":{"kind":"event","date":"2001-02-07","basis":"publication","note":"Archive author index lists the message as \"Wed Feb 07 2001 - 21:09:16 MST\" 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 the default outcome is good."}}}},{"id":"ap-eliezer-yudkowsky-sl4-2001-01-24-yudkowsky-0101-0452","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-01-24-yudkowsky-0101-0452"},"topic":"ideas","statement":"The mailing-list message “Re: Event horizon” (2001-01-24) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-01-24","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-sl4-2001-02-04-yudkowsky-0102-0539","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-02-04-yudkowsky-0102-0539"},"topic":"ideas","statement":"The SL4 message “Re: Beyond evolution” of 2001-02-04, archive message 0539, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-02-04","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-sl4-2001-02-05-yudkowsky-0102-0542","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-02-05-yudkowsky-0102-0542"},"topic":"ideas","statement":"The SL4 message “Re: Beyond evolution” of 2001-02-05, archive message 0542, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-02-05","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-sl4-2001-02-07-yudkowsky-0102-0545","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-02-07-yudkowsky-0102-0545"},"topic":"ideas","statement":"The mailing-list message “Re: Learning to be evil” (2001-02-07) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-02-07","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-sl4-2001-02-25-yudkowsky-0102-0594","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-02-25-yudkowsky-0102-0594"},"topic":"ideas","statement":"The SL4 message “Re: Military in or out?” of 2001-02-25, archive message 0594, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-02-25","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-sl4-2001-02-26-yudkowsky-0102-0603","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-02-26-yudkowsky-0102-0603"},"topic":"ideas","statement":"The SL4 message “Re: Military in or out?” of 2001-02-26, archive message 0603, is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-02-26","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-sl4-2001-04-06-yudkowsky-0104-0956","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-04-06-yudkowsky-0104-0956"},"topic":"ideas","statement":"The mailing-list message “Re: Singularity intros (was: Si definition of Friendliess)” (2001-04-06) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-04-06","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-sl4-2001-04-08-yudkowsky-0104-1019","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-04-08-yudkowsky-0104-1019"},"topic":"ideas","statement":"The mailing-list message “Re: Threats (was Theoretical question for the list: publicity?)” (2001-04-08) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-04-08","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-sl4-2001-04-12-yudkowsky-0104-1076","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-04-12-yudkowsky-0104-1076"},"topic":"ideas","statement":"The mailing-list message “Re: Open Source Friendly AI? (was Singularity and the generalpublic)” (2001-04-12) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-04-12","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-sl4-2001-04-19-yudkowsky-0104-1166","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-04-19-yudkowsky-0104-1166"},"topic":"ideas","statement":"The mailing-list message “Re: FW: Group releases \"Friendly AI\"” (2001-04-19) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-04-19","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-creating-friendly-ai-2001","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"creating-friendly-ai-2001"},"topic":"ideas","statement":"“Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures” (2001-06-15) credits Eliezer Yudkowsky as its author.","time":{"kind":"event","date":"2001-06-15","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-sl4-2001-08-01-yudkowsky-0108-2031","subject":"eliezer-yudkowsky","predicate":"authored","object":{"kind":"entity","entityId":"sl4-2001-08-01-yudkowsky-0108-2031"},"topic":"ideas","statement":"The mailing-list message “Re: Floppy take-off” (2001-08-01) is sent under the name Eliezer S. Yudkowsky.","time":{"kind":"event","date":"2001-08-01","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":[19,311,455,456,457,458,459,460,461,462,463,464,465],"claims":[911,912,913,914,915,984,1001,1057,1062,1068,1077,1088,1100,1103,1104,1123,1126,1141,1146,1151,1163,1170,1172,1178,1179,1188,2393,2394,2395,2396,2397,2398,2399,2400,2401,2402,2403,2404],"sources":[],"evidence":[]},"version":"1lg47t7"}