korrents

On the map

Tap a claim on the ring to put it at the centre.

← Passive reminders of ethics, like a displayed Ten Commandments, do not significantly influence behaviour

17 connected korrents · 15 moments from 12 Oct 2015 to 23 Sept 2026.

Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under behavioural science behavioural science Everything filed under writing writing Everything filed under OpenAI OpenAI Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Passive reminders of ethics, like a displayed Ten Commandments, do not significantly influence behaviour Passive reminders of ethics, like adisplayed Ten Commandments, do notsignificantly influence behaviour Last stated 2 years ago 13 Jul 2024 DA Dan Ariely — holds since 2024-07-13 — tap for who they are Same subject: Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior. — tap to centre the map on it Reinforcement learning fromverifiable rewards does not reliablycarry a model's pretrained ethicalunderstanding into its actualbehavior. Last stated 2 months ago 11 Aug 2026 SH Samuel Hammond — holds since 2026-08-11 — tap for who they are Same subject: People tend to assume their habitual practices achieve what they intend, even without evidence that they do. — tap to centre the map on it People tend to assume their habitualpractices achieve what they intend,even without evidence that they do. Last stated 3 months ago 22 Jun 2026 HK Henrik Karlsson — holds since 2026-06-22 — tap for who they are Same subject: Repeated vague platitudes without follow-up specifics signal weak first-principles thinking. — tap to centre the map on it Repeated vague platitudes withoutfollow-up specifics signal weakfirst-principles thinking. Last stated 3 years ago 25 Feb 2024 BK Ben Kuhn — holds since 2024-02-25 — tap for who they are Same subject: Effective altruism demands hard evidence of effectiveness in some of its causes while accepting abstract conjecture in others, and never justifies the split. — tap to centre the map on it Effective altruism demands hardevidence of effectiveness in some ofits causes while accepting abstractconjecture in others, and neverjustifies the split. Last stated 3 years ago 21 Dec 2023 MJ Matt Johnson — holds since 2023-12-21 — tap for who they are Same subject: Respect is owed to those who lead minds by the force of truth, not to conquerors who enslave their fellow creatures — tap to centre the map on it Respect is owed to those who leadminds by the force of truth, not toconquerors who enslave their fellowcreatures VO Voltaire — holds since c. 1733 — tap for who they are Same subject: A wise ruler need not keep his word when it would harm him and its reasons are gone, because people are not wholly good — tap to centre the map on it A wise ruler need not keep his wordwhen it would harm him and itsreasons are gone, because people arenot wholly good NM Niccolò Machiavelli — holds since c. 1513–1514 — tap for who they are Same subject: Following one's conscience is no safe theory of governance, because private moral compasses err and disagree — tap to centre the map on it Following one's conscience is nosafe theory of governance, becauseprivate moral compasses err anddisagree Last stated 11 years ago 12 Oct 2015 KS Kathryn Schulz — holds since 2015-10-12 — tap for who they are Same subject: Reciprocity can serve as a rule for life: do not do to others what you do not want done to yourself — tap to centre the map on it Reciprocity can serve as a rule forlife: do not do to others what youdo not want done to yourself CO Confucius — holds since c. 551–479 BCE — tap for who they are Same subject: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. — tap to centre the map on it A control evaluation that reportsunder one per cent risk should beread as several per cent, becausethe evaluation can itself fail. Last stated 2 years ago 7 May 2024 BS Buck Shlegeris — holds since 2024-05-07 — tap for who they are Same subject: A deep theoretical understanding to predict AI behavior is unattainable. — tap to centre the map on it A deep theoretical understanding topredict AI behavior is unattainable. Last stated a week ago 23 Sept 2026 TC Tyler Cowen — holds since 2026-09-23 — tap for who they are Same subject: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces abehavior pulls it toward whateverimproves the loop's own score. Last stated a month ago 26 Aug 2026 HK Henrik Karlsson — holds since 2026-08-26 — tap for who they are Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email isevidence of a bad vendor, not of alimit of AI. Last stated 9 months ago 1 Jan 2026 JL Jason Lemkin — holds since 2026-01-01 — tap for who they are Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does notgive you a smarter model; theintelligence of the model is whatdecides how much of that window itcan actually attend to. Last stated 3 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. — tap to centre the map on it A child who has seen ten cats learnswhat a machine needs the wholeinternet of cat photos for, by alearning pathway nobody has solved. Last stated 2 months ago 10 Aug 2026 FL Fei-Fei Li — holds since 2026-08-10 — tap for who they are Same subject: A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as anonprofit and bolt a for-profit armon later, whatever OpenAI's ownhistory suggests. Last stated 3 years ago 18 Mar 2024 SA Sam Altman — holds since 2024-03-18 — tap for who they are Same subject: A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. — tap to centre the map on it A technique that lets an AI model'sreasoning shift outside its visibleChain of Thought is dangerous, bothbecause it works and because aleading lab is willing to deploy it. Last stated 4 weeks ago 3 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-03 — tap for who they are Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing aplausible-sounding name is the samephenomenon as a large oneconfidently stating a false fact. Last stated 8 months ago 12 Feb 2026 AK Andrej Karpathy — holds since 2026-02-12 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Passive reminders of ethics, like a displayed Ten Commandments, do not significantly influence behaviour Last stated 13 Jul 2024 · 2 years ago Holds Dan Ariely Read this korrent →