korrents

On the map

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

← Gradient descent finds a solution to the problems a model has seen;…

8 connected korrents · 6 moments from 22 Dec 2014 to 6 Sept 2026.

Everything filed under optimizers optimizers Everything filed under AI alignment AI alignment Everything filed under robotics robotics Everything filed under LLMs LLMs Everything filed under creativity creativity Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Gradient descent finds a solution to the problems a model has seen; nothing in the algorithm makes it pick the one that generalises well. Gradient descent finds a solution to theproblems a model has seen; nothing in thealgorithm makes it pick the one thatgeneralises well. Last stated a year ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — tap for who they are Same subject: An optimizer that is invariant to rescaling the gradients and cheap in memory is what makes very large models practical to train. — tap to centre the map on it An optimizer that is invariant torescaling the gradients and cheap inmemory is what makes very largemodels practical to train. Last stated 12 years ago 22 Dec 2014 JB Jimmy Ba — holds since 2014-12-22 — tap for who they are DK Diederik P. Kingma — holds since 2014-12-22 — tap for who they are Same subject: An optimizer's hyper-parameters should mean something a practitioner can reason about, and should rarely need tuning. — tap to centre the map on it An optimizer's hyper-parametersshould mean something a practitionercan reason about, and should rarelyneed tuning. Last stated 12 years ago 22 Dec 2014 JB Jimmy Ba — holds since 2014-12-22 — tap for who they are DK Diederik P. Kingma — holds since 2014-12-22 — tap for who they are Same subject: Stochastic optimization can be done well using only adaptive estimates of the gradient's lower-order moments. — tap to centre the map on it Stochastic optimization can be donewell using only adaptive estimatesof the gradient's lower-ordermoments. Last stated 12 years ago 22 Dec 2014 JB Jimmy Ba — holds since 2014-12-22 — tap for who they are DK Diederik P. Kingma — holds since 2014-12-22 — tap for who they are Same subject: The same optimizer should handle objectives that move under it and gradients that are noisy or sparse. — tap to centre the map on it The same optimizer should handleobjectives that move under it andgradients that are noisy or sparse. Last stated 12 years ago 22 Dec 2014 JB Jimmy Ba — holds since 2014-12-22 — tap for who they are DK Diederik P. Kingma — holds since 2014-12-22 — tap for who they are Same subject: You cannot build an AI that has only the capabilities you want, because the algorithms that solve the problems you want generalize to the ones you do not. — tap to centre the map on it You cannot build an AI that has onlythe capabilities you want, becausethe algorithms that solve theproblems you want generalize to theones you do not. Last stated 4 years ago 10 Jun 2022 EY Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are Same subject: It is the diversity of a robot data set, not its size, that produces generalization: dropping the most diverse slice hurts far more than dropping a random fifth. — tap to centre the map on it It is the diversity of a robot dataset, not its size, that producesgeneralization: dropping the mostdiverse slice hurts far more thandropping a random fifth. Last stated 2 months ago 12 Aug 2026 CF Chelsea Finn — holds since 2026-08-12 — tap for who they are Same subject: A model can make an existing algorithm a hundred times faster and still cannot invent a better one, however long you give it. — tap to centre the map on it A model can make an existingalgorithm a hundred times faster andstill cannot invent a better one,however long you give it. Last stated 4 months ago 26 Jun 2026 NB Noam Brown — holds since 2026-06-26 — tap for who they are Same subject: An AI loop can climb to a local maximum but then plateaus, and human intuition is needed to find the next hill. — tap to centre the map on it An AI loop can climb to a localmaximum but then plateaus, and humanintuition is needed to find the nexthill. Last stated 2 months ago 6 Sept 2026 AA Anish Acharya — holds since 2026-09-06 — 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 2014 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Gradient descent finds a solution to the problems a model has seen; nothing in the algorithm makes it pick the one that generalises well. Last stated 26 Sept 2025 · a year ago Holds Richard Sutton Read this korrent →