Ignore "infinite". What we really mean is having access to the the full distribution rather than just a sample.
RESEARCH
-
Expert Identity Threats Drive Overconfident Predictions
By
–
Relevant paper: six studies show when an expert is wrong about a public prediction and is called out for a mistake by another expert, their identity becomes threatened. They tend to respond by doubling down with more overprecise predictions rather than acknowledging errors.
-
Innate Priors Shape AI Learning: Evolution Over Minimalism
By
–
– you still need some prior to organize that infinite data and decide how to generalize from it
– the choice to minimize is an aesthetic choice, not a scientific one; evolution has clearly endowed many animals with significant priors (eg baby ibex climbing down a mountain). -
Secret codeword for AGI existential risk research jobs
By
–
Is that like a secret codeword to get jobs in “AGI existential risk” research?
-
Deep Learning and AGI: Expectations vs Reality
By
–
Complaining deep learning is not AGI is like complaining a car doesn't fly.
-
Inductive Biases: Making Implicit Assumptions About Data Explicit
By
–
Inductive biases are always assumptions about the world generating the data. They may, however, be expressed very opaquely as network structure or even arbitrary hacks (easy and common but bad; you should make your assumptions explicit and then test/modify/refute them).
-
Data, Causality, and Action: Beyond Philosophical Definitions
By
–
But data can tell us what happens for every possible configuration of things that affect the barometer and the weather, including your actions. In this view, "causes" is a philosophical statement that is not required to guide your actions (or control a robot).
-
Strong innate priors in machine learning systems
By
–
that’s learning that the set of relevant cases is empty; it’s still a strong innate prior
-
Inductive bias guides learner function search in neural networks
By
–
Not exactly. The learner could well discover that none of the symmetries in the space hold. It's an inductive bias in the precise sense of the term: it causes the learner to search for some functions over others.
-
BIG-Bench Benchmarks Face Validity Scrutiny for AGI Predictions
By
–
Trouble in BIG-Bench paradise? – @ErnestSDavis looks at 48 of the benchmarks within and finds problems with most: https://
cs.nyu.edu/~davise/Benchm
arks/BigBenchDiscussion.html
… – Many project AGI timelines based on performance on these benchmarks. If the benchmarks aren’t valid, consequent timelines are problematic