Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution · HackerPapers discussions

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution — mentioned by marvin-hansen

Sun, 13 Jul 2025 10:45:40 GMT

Okay, read the abstract and Intro. Recently, in the paper "What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models" your thesis of Ai's lack of capacity to abstract or at least extract understanding from noisy data was largely experimentally confirmed. I am uncertain though about the exact mechanics b/c as they used LLM's, its not transparent what happened internally that lead to constant failure to abstract the concept despite ample predictive power. One interesting experiment was the introduction of the Oracle that literally enabled the LLM to solve the task that…

Paper and discussion history. A mention is not an endorsement.

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution — mentioned by vokolk

Sat, 28 Apr 2018 05:30:10 GMT

Check out this paper by Turin-award winner Judea Pearl for fundamental limitations of current approaches to ML: https://arxiv.org/abs/1801.04016

Paper and discussion history. A mention is not an endorsement.

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution — mentioned by matiasz

Tue, 03 Apr 2018 17:05:11 GMT

Yes [1]. [1] https://arxiv.org/abs/1801.04016

Paper and discussion history. A mention is not an endorsement.

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution — HN submission

Mon, 15 Jan 2018 19:35:26 GMT

Theoretical Impediments to Machine Learning with Seven Sparks from Causality

71 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution — mentioned by mark_l_watson

Mon, 15 Jan 2018 18:38:18 GMT

Great result. At my job I manage a machine learning team and so I am fairly much all-in for deep learning to solve practical problems. That said, I think the path to 'real' AGI lies in some combination of DL, probabilistic graph models, symbolic systems, and something we have not even imagined yet. BTW, a good paper just released on the limitations of DL by Judea Pearl https://arxiv.org/abs/1801.04016

Paper and discussion history. A mention is not an endorsement.