Tap a claim on the ring to put it at the centre.
← It is very hard to actually get stuck, because the action space is always larger than it appears.
8 connected korrents · 9 moments on record from 15 Aug 2021 to 2 Sept 2026.
−
+
Fit
Full text
Drag to move · pinch or scroll to zoom
Everything filed under AI alignment
AI alignment Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: It is very hard to actually get stuck, because the action space is always larger than it appears. It is very hard to actually get stuck, because the action space is always larger than it appears. Last stated a month ago
7 Aug 2026
MH
Max Hodak — holds since 2026-08-07 — tap for who they are
Same subject: The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. — tap to centre the map on it The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of… Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: Relying on gradual, continuous shifts in AI training behavior to catch misalignment will eventually fail because the dangerous shift itself may be discontinuous. — tap to centre the map on it Relying on gradual, continuous shifts in AI training behavior to catch misalignment will eventually fail because the… Last stated 5 days ago
2 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-02 — tap for who they are
Same subject: Being stuck is not an obstacle to understanding something; it is probably the most important part of the whole process. — tap to centre the map on it Being stuck is not an obstacle to understanding something; it is probably the most important part of the whole process. Last stated 5 months ago
7 Apr 2026
MN
Michael Nielsen — holds since 2026-04-07 — tap for who they are
Same subject: Nobody can get on top of everything, because you are part of the everything you are trying to get on top of. — tap to centre the map on it Nobody can get on top of everything, because you are part of the everything you are trying to get on top of. Last stated 5 years ago
by 15 Aug 2021
OB
Oliver Burkeman — holds since 2021-08-15 — tap for who they are
Same subject: The scarce skill is now context switching across parallel agents, not sustained deep work. — tap to centre the map on it The scarce skill is now context switching across parallel agents, not sustained deep work. Last stated 6 months ago
4 Mar 2026
BC
Boris Cherny — holds since 2026-03-04 — tap for who they are
Same subject: Concurrency is hard not because human brains cannot handle it but because nobody gets enough practice at it. — tap to centre the map on it Concurrency is hard not because human brains cannot handle it but because nobody gets enough practice at it. Last stated a month ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility. — tap to centre the map on it The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build… Last stated 5 months ago
29 Mar 2026
CH
Chip Huyen — holds since 2026-03-29 — tap for who they are
Same subject: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad… Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are