HackerTrans
TopNewTrendsCommentsPastAskShowJobs

tims457

129 karmajoined 5 years ago
https://tims457.github.io/ https://twitter.com/tims457

Submissions

Yi Ma – Pursuing the Nature of Intelligence

youtube.com
1 points·by tims457·3 days ago·0 comments

NeuroMechFly v2: simulating embodied sensorimotor control in adult Drosophila

nature.com
2 points·by tims457·4 months ago·1 comments

Neural Algorithmic Reasoning

algo-reasoning.github.io
3 points·by tims457·last year·0 comments

Ask HN: Alternative to Causal for probabilistic spreadsheet models

2 points·by tims457·2 years ago·1 comments

The Thinking Game

tribecafilm.com
1 points·by tims457·2 years ago·0 comments

[untitled]

1 points·by tims457·2 years ago·0 comments

Friends from the Old Neighborhood Turn Rivals in Big Tech's A.I. Race

nytimes.com
2 points·by tims457·2 years ago·0 comments

CS224W: Machine Learning with Graphs – Notes

snap-stanford.github.io
3 points·by tims457·2 years ago·0 comments

Graph Convolutional Networks

tkipf.github.io
3 points·by tims457·2 years ago·0 comments

Collective intelligence for deep learning: A survey of recent developments

journals.sagepub.com
2 points·by tims457·2 years ago·0 comments

Ask HN: What are the best resources you've found on improving your writing?

1 points·by tims457·3 years ago·1 comments

comments

tims457
·4 months ago·discuss
https://www.biorxiv.org/content/10.1101/2023.09.18.556649v4
tims457
·3 years ago·discuss
No transparency here. What is it considering to come up with these scores? Are they prioritizing growth, value, financial health, or something else?
tims457
·3 years ago·discuss
Haven't read the paper yet, but it's clear that the brain is much more sample efficient than artificial neural networks. We should be spending more time on figuring out why than scaling up LLMs.
tims457
·3 years ago·discuss
I'm risking just posting another process that you might have seen, but I thought it was helpful. Maybe you or someone else will too.

Farnam Street annual review https://fs.blog/annual-review/ (Direct link without giving your email: https://fsmisc.s3.ca-central-1.amazonaws.com/2022+AR.pdf)