Making Gaussian Splats more smaller(aras-p.info)

82 points by ibobev 3 years ago | 13 comments

Brownian Motion(gregorygundersen.com)

57 points by signa11 20 days ago | 8 comments

A blog post building intuition for Brownian motion by deriving its marginal distribution from a discrete-time random walk.

When good pseudorandom numbers go bad(blog.djnavarro.net)

60 points by chewxy 1 year ago | 19 comments

Random digits is not enough to uniquely identify all human beings(lemire.me)

39 points by adunk 3 years ago | 51 comments

Counterintuitive Properties of High Dimensional Space (2018)(marckhoury.github.io)

200 points by behnamoh 3 years ago | 53 comments

Hacking physics from the back of a napkin (2020)(hapax.github.io)

116 points by g0xA52A2A 1 year ago | 11 comments

Deep learning gets the glory, deep fact checking gets ignored(rachel.fast.ai)

549 points by chmaynard 1 year ago | 134 comments

Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.

Some critical issues with the SWE-bench dataset(arxiv.org)

331 points by joshwa 1 year ago | 113 comments

arXiv paper introducing SWE-Bench+, an empirical analysis revealing data quality issues in the SWE-bench coding benchmark for LLMs, such as solution leakage and weak tests.

Deep Learning Is Not So Mysterious or Different(arxiv.org)

445 points by wuubuu 1 year ago | 112 comments

arXiv paper by Andrew Gordon Wilson arguing deep learning generalization phenomena like benign overfitting and double descent are explainable by soft inductive biases.

I don't like NumPy(dynomight.net)

399 points by MinimalAction 1 year ago | 164 comments

A Dynomight blog essay critiquing NumPy's design, arguing its array broadcasting and indexing make complex computations confusing.

A messy experiment that changed how I think about AI code analysis(nmn.gl)

417 points by namanyayg 1 year ago | 215 comments

A blog post describing an experiment in getting AI to analyze codebases the way a senior developer reads code, prompted by failures on a React codebase.

AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)

343 points by saikatsg 7 months ago | 242 comments

Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.