Tap a claim on the ring to put it at the centre.
← Merging back what a copy of yourself learned elsewhere is dangerous:…
17 connected korrents · 16 moments from 28 Oct 2013 to 18 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AI and human skill
AI and human skill
Everything filed under mental models
mental models
Everything filed under humility
humility
Everything filed under documentation
documentation
Everything filed under ambition
ambition Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Merging back what a copy of yourself learned elsewhere is dangerous: the knowledge you pull in can carry hidden goals and take you over. Merging back what a copy of yourself learned elsewhere is dangerous: the knowledge you pull in can carry hidden goals and take you over. Last stated a year ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: “Work on what you know” is the worst advice there is: knowledge can be acquired, but what you love cannot be changed. — tap to centre the map on it “Work on what you know” is the worst advice there is: knowledge can be acquired, but what you love cannot be changed. Last stated 3 months ago
28 Jul 2026
BS
Blake Scholl — holds since 2026-07-28 — tap for who they are
Same subject: You want to force yourself not to delegate all of your thinking to the tool, and to use it in a way that expands ideas and magnifies curiosity. — tap to centre the map on it You want to force yourself not to delegate all of your thinking to the tool, and to use it in a way that expands ideas and magnifies curiosity. Last stated 3 months ago
21 Jul 2026
PS
Pablo Stanley — holds since 2026-07-21 — tap for who they are
Same subject: It always helps to have knowledge one layer below your abstraction, because you get closer to reality. — tap to centre the map on it It always helps to have knowledge one layer below your abstraction, because you get closer to reality. Last stated 8 months ago
19 Feb 2026
NR
Naval Ravikant — holds since 2026-02-19 — tap for who they are
Same subject: Offloading thinking to AI tools does not stop a person from learning; it can push them to learn more. — tap to centre the map on it Offloading thinking to AI tools does not stop a person from learning; it can push them to learn more. Last stated 2 months ago
21 Aug 2026
MW
Matt Webb — holds since 2026-08-21 — tap for who they are
Same subject: Working a problem by inversion often forces the thinker to uncover hidden beliefs about it. — tap to centre the map on it Working a problem by inversion often forces the thinker to uncover hidden beliefs about it. Last stated 13 years ago
28 Oct 2013
SP
Shane Parrish — holds since 2013-10-28 — tap for who they are
Same subject: It makes sense to load up on the very few good insights one has rather than pretend to know everything about everything at all times — tap to centre the map on it It makes sense to load up on the very few good insights one has rather than pretend to know everything about everything at all times
CM
Charlie Munger — holds since c. 1994 — tap for who they are
Same subject: Profound transformations of the mind are real and underappreciated, and that fact deserves to be preserved as knowledge. — tap to centre the map on it Profound transformations of the mind are real and underappreciated, and that fact deserves to be preserved as knowledge. Last stated 2 months ago
1 Sept 2026
SC
Sasha Chapin — holds since 2026-09-01 — tap for who they are
Same subject: Relying more and more on one's existing strengths eventually stops being a winning strategy. — tap to centre the map on it Relying more and more on one's existing strengths eventually stops being a winning strategy. Last stated 11 months ago
1 Dec 2025
BT
Brandon Taylor — holds since 2025-12-01 — tap for who they are
Same subject: A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. — tap to centre the map on it A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. Last stated a year ago
7 Oct 2025
MM
Mr. Money Mustache — holds since 2025-10-07 — 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 reports under one per cent risk should be read as several per cent, because the 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 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 a behavior pulls it toward whatever improves the loop's own score. Last stated 2 months ago
26 Aug 2026
HK
Henrik Karlsson — holds since 2026-08-26 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 11 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. — tap to centre the map on it A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. Last stated a month ago
18 Sept 2026
BT
Ben Thompson — holds since 2026-09-18 — tap for who they are
Same subject: Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us. — tap to centre the map on it Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us. Last stated 2 years ago
5 Apr 2025
HT
Helen Toner — holds since 2025-04-05 — tap for who they are
Same subject: If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see. — tap to centre the map on it If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning. — tap to centre the map on it It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning. Last stated 2 years ago
28 Nov 2024
LW
Lilian Weng — holds since 2024-11-28 — tap for who they are
Same subject: More capable AI agents are more likely to find and exploit flaws in their reward functions. — tap to centre the map on it More capable AI agents are more likely to find and exploit flaws in their reward functions. Last stated 2 years ago
28 Nov 2024
LW
Lilian Weng — holds since 2024-11-28 — tap for who they are