Tap a claim on the ring to put it at the centre.
← A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
17 connected korrents · 15 moments from 27 Feb 2020 to 18 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under management
management
Everything filed under behavioural science
behavioural science
Everything filed under design
design
Everything filed under education
education
Everything filed under politics
politics
Everything filed under recursive self-improvement
recursive self-improvement
Everything filed under investing
investing 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: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. 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: The feedback loops a person allows to operate on them shape who they become to an unsettling degree. — tap to centre the map on it The feedback loops a person allows to operate on them shape who they become to an unsettling degree. Last stated 2 months ago
26 Aug 2026
HK
Henrik Karlsson — holds since 2026-08-26 — tap for who they are
Same subject: On a labs team the feedback loop between making something and knowing whether it is good matters most, and the tightest loop is building for yourself. — tap to centre the map on it On a labs team the feedback loop between making something and knowing whether it is good matters most, and the tightest loop is building for yourself. Last stated 2 months ago
10 Sept 2026
DS
Dan Shipper — holds since 2026-09-10 — tap for who they are
Same subject: Feedback is essential to human development, and without it nothing can reliably improve. — tap to centre the map on it Feedback is essential to human development, and without it nothing can reliably improve. Last stated 3 years ago
27 Sept 2023
TS
Tobias Sjösten — holds since 2023-09-27 — tap for who they are
Same subject: If real economic improvements no longer lift how people feel about the economy, the feedback loop between good politics and good policy is broken. — tap to centre the map on it If real economic improvements no longer lift how people feel about the economy, the feedback loop between good politics and good policy is broken. Last stated 5 months ago
24 May 2026
AL
Annie Lowrey — holds since 2026-05-24 — tap for who they are
Same subject: Clear goals plus a measure that drives progress toward them can achieve amazing progress, yet this is surprisingly rarely done well — tap to centre the map on it Clear goals plus a measure that drives progress toward them can achieve amazing progress, yet this is surprisingly rarely done well
BG
Bill Gates — holds since c. 2013 — tap for who they are
Same subject: Feedback aimed at fixing one specific piece of work creates a bottleneck rather than leverage. — tap to centre the map on it Feedback aimed at fixing one specific piece of work creates a bottleneck rather than leverage. Last stated 3 months ago
13 Aug 2026
HG
Hilary Gridley — holds since 2026-08-13 — tap for who they are
Same subject: Recursive self-improvement only works if the base model is already capable enough to improve its own mechanism. — tap to centre the map on it Recursive self-improvement only works if the base model is already capable enough to improve its own mechanism. Last stated 4 months ago
4 Jul 2026
LW
Lilian Weng — holds since 2026-07-04 — tap for who they are
Same subject: Where accurate feedback is scarce, as in investing, progress depends on creating feedback loops — tap to centre the map on it Where accurate feedback is scarce, as in investing, progress depends on creating feedback loops Last stated 7 years ago
27 Feb 2020
JW
Josh Waitzkin — holds since 2020-02-27 — tap for who they are
Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe because they are not smart enough, not because they are too smart. Last stated 2 months ago
13 Sept 2026
FC
François Chollet — holds since 2026-09-13 — tap for who they are
Same subject: Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. — tap to centre the map on it Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — 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 3 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
Same subject: Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned. — tap to centre the map on it Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned. Last stated 5 months ago
27 May 2026
SH
Samuel Hammond — holds since 2026-05-27 — 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 2 months 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
At the centre
A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
Holds Read this korrent →
The feedback loops a person allows to operate on them shape who they become to an unsettling degree.
Holds
On a labs team the feedback loop between making something and knowing whether it is good matters most, and the tightest loop is building for yourself.
Holds
Feedback is essential to human development, and without it nothing can reliably improve.
Holds
If real economic improvements no longer lift how people feel about the economy, the feedback loop between good politics and good policy is broken.
Holds
Clear goals plus a measure that drives progress toward them can achieve amazing progress, yet this is surprisingly rarely done well
Last stated c. 2013
Holds
Feedback aimed at fixing one specific piece of work creates a bottleneck rather than leverage.
Holds
Recursive self-improvement only works if the base model is already capable enough to improve its own mechanism.
Holds
Where accurate feedback is scarce, as in investing, progress depends on creating feedback loops
Holds
Current models are unsafe because they are not smart enough, not because they are too smart.
Holds
Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one.
Holds
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.
Holds
It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning.
Holds
More capable AI agents are more likely to find and exploit flaws in their reward functions.
Holds
Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned.
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
A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI.
Holds
Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us.
Holds