The Benchmarkpocalypse(danluu.com)

147 points by cyndunlop 2 months ago | 46 comments

There's no reason for software to be slow anymore(danluu.com)

592 points by Jach 2 months ago | 442 comments

Dan Luu essay arguing that LLM coding agents make specialized performance optimization cheap, illustrated with optimizing a regex engine for specific workloads.

How I program with LLMs(crawshaw.io)

762 points by stpn 1 year ago | 292 comments

David Crawshaw's blog post summarizing a year of personal experience using LLMs while programming, and introducing sketch.dev, a Go-focused tool.

What will LLM-powered software look like in the medium-term future?(vishnumenon.com)

176 points by vishnumenon 3 years ago | 187 comments

Can large language models reason?(arnaldur.be)

4 points by Hugsun 2 years ago | 0 comments

Show HN: Fully client-side GPT2 prediction visualizer(perplexity.vercel.app)

140 points by thesephist 3 years ago | 10 comments