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 · 18 moments on record from 24 Oct 2017 to 7 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under education
education
Everything filed under OpenAI
OpenAI 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 11 months 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… Last stated a month ago
28 Jul 2026
BS
Blake Scholl — holds since 2026-07-28 — tap for who they are
Same subject: The only reliable way to build a robustly aligned mind is to make it an antifragile agent that wants to improve its own character, not one that merely pursues fixed goals. — tap to centre the map on it The only reliable way to build a robustly aligned mind is to make it an antifragile agent that wants to improve its own… Last stated today
7 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-07 — tap for who they are
Same subject: You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning. — tap to centre the map on it You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: Opinions move by touching things, not by reading about them: nobody learns to drive a race car from a book. — tap to centre the map on it Opinions move by touching things, not by reading about them: nobody learns to drive a race car from a book. Last stated a month ago
26 Jul 2026
DH
David Heinemeier Hansson — holds since 2026-07-26 — tap for who they are
AM
Adam Mastroianni — holds since 2023-03-14 — tap for who they are
Same subject: Learning should be made harder rather than easier, and a teacher's instinct to smooth the path is the first thing that goes wrong. — tap to centre the map on it Learning should be made harder rather than easier, and a teacher's instinct to smooth the path is the first thing… Last stated 2 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: Learning cannot happen in flow, because getting better at a skill means working beyond the level at which you can express it. — tap to centre the map on it Learning cannot happen in flow, because getting better at a skill means working beyond the level at which you… Last stated 2 months ago
20 Jul 2026
TW
Tommy Wood — holds since 2026-07-20 — tap for who they are
Same subject: Knowledge is cheap and easily acquired; what a person actually needs is curiosity, self-efficacy, perseverance, perspective and hope. — tap to centre the map on it Knowledge is cheap and easily acquired; what a person actually needs is curiosity, self-efficacy, perseverance… Last stated 4 years ago
12 Jul 2022
AM
Adam Mastroianni — holds since 2022-07-12 — tap for who they are
Same subject: A large fraction of what the people around you believe is mistaken, and nobody is going to teach you to think for yourself. — tap to centre the map on it A large fraction of what the people around you believe is mistaken, and nobody is going to teach you to think for… Last stated 8 years ago
by 5 Jul 2018
PC
Patrick Collison — holds since 2018-07-05 — 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… Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. — tap to centre the map on it A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a… Last stated 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned… Last stated 9 years ago
24 Oct 2017
ÉT
Émile P. Torres — holds since 2017-10-24 — tap for who they are
Same subject: A puzzle whose categories can only be seen by the broadly educated is elitist by construction. — tap to centre the map on it A puzzle whose categories can only be seen by the broadly educated is elitist by construction. Last stated 3 years ago
2 Sept 2023
RK
Raph Koster — holds since 2023-09-02 — tap for who they are
Same subject: A school should be judged on how fast its students are learning, not on how much they already know when measured. — tap to centre the map on it A school should be judged on how fast its students are learning, not on how much they already know when measured. Last stated a week ago
31 Aug 2026
JL
Joe Liemandt — holds since 2026-08-31 — tap for who they are
Same subject: A worked example whose scaffolding is progressively removed teaches faster than making a child figure the problem out unaided. — tap to centre the map on it A worked example whose scaffolding is progressively removed teaches faster than making a child figure the… Last stated a week ago
31 Aug 2026
JL
Joe Liemandt — holds since 2026-08-31 — 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 a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history… Last stated 2 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's reasoning shift outside its visible Chain of Thought is dangerous, both… Last stated 4 days 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 a plausible-sounding name is the same phenomenon as a large one confidently… Last stated 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
At the centre
Merging back what a copy of yourself learned elsewhere is dangerous: the knowledge you pull in can carry hidden goals and take you over.
Holds RS Richard SuttonRead this korrent →
“Work on what you know” is the worst advice there is: knowledge can be acquired, but what you love cannot be changed.
Holds BS Blake Scholl
The only reliable way to build a robustly aligned mind is to make it an antifragile agent that wants to improve its own character, not one that merely pursues fixed goals.
Holds ZM Zvi Mowshowitz
You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning.
Holds CR Charan Ranganath
Opinions move by touching things, not by reading about them: nobody learns to drive a race car from a book.
Holds AM Adam Mastroianni
Learning should be made harder rather than easier, and a teacher's instinct to smooth the path is the first thing that goes wrong.
Holds AC Alan Castel
Learning cannot happen in flow, because getting better at a skill means working beyond the level at which you can express it.
Holds TW Tommy Wood
Knowledge is cheap and easily acquired; what a person actually needs is curiosity, self-efficacy, perseverance, perspective and hope.
Holds AM Adam Mastroianni
A large fraction of what the people around you believe is mistaken, and nobody is going to teach you to think for yourself.
Holds
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.
Holds IS Ilya Sutskever
A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence.
Holds AC Ajeya Cotra
A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough.
Holds ÉT Émile P. Torres
A puzzle whose categories can only be seen by the broadly educated is elitist by construction.
Holds RK Raph Koster
A school should be judged on how fast its students are learning, not on how much they already know when measured.
Holds JL Joe Liemandt
A worked example whose scaffolding is progressively removed teaches faster than making a child figure the problem out unaided.
Holds JL Joe Liemandt
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
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.
Holds ZM Zvi Mowshowitz
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds