A fully automatic problem solver with human-style output · HackerPapers discussions

A fully automatic problem solver with human-style output — mentioned by trenchgun

Fri, 29 Apr 2022 11:27:36 GMT

This is not his first rodeo. https://arxiv.org/pdf/1309.4501.pdf

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

A fully automatic problem solver with human-style output — mentioned by markan

Sun, 03 Sep 2017 03:38:12 GMT

The presentation briefly mentioned simulating the brain, but I think what's more likely to succeed is mimicking the mind at a high level of abstraction (i.e. a level we can study with introspective or even linguistic methods rather than neuroscience). There's some precedent for this with projects like Soar and ACT-R (and even some recent interest from mathematicians [1]). IMHO this kind of methodology could be pushed much further. [1] https://arxiv.org/abs/1309.4501

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

A fully automatic problem solver with human-style output — mentioned by jbapple

Tue, 24 Mar 2015 01:01:17 GMT

There have been quite a few; Gowers himself (mentioned in the article) is working on one: "A fully automatic problem solver with human-style output" M. Ganesalingam, W. T. Gowers http://arxiv.org/abs/1309.4501

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

A fully automatic problem solver with human-style output — HN submission

Tue, 08 Oct 2013 05:58:51 GMT

A fully automatic problem solver with human-style output

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A fully automatic problem solver with human-style output — HN submission

Thu, 19 Sep 2013 16:54:10 GMT

A fully automatic problem solver with human-style output

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.