Typewriter Interview with Elisa Gabbert(austinkleon.substack.com)

17 points by zacharykai 2 years ago | 0 comments

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability(adamkarvonen.github.io)

77 points by sebg 1 year ago | 1 comments

JLink JTAG Access on the Pinecil(danielmangum.com)

58 points by hasheddan 4 months ago | 10 comments

OpenBSD, the computer appliance maker's secret weapon(hiandrewquinn.github.io)

115 points by transpute 2 years ago | 64 comments

What job interviews taught me about Kubernetes(notnotp.com)

228 points by chmaynard 4 months ago | 173 comments

Reducing Cargo target directory size with -Zno-embed-metadata(kobzol.github.io)

48 points by todsacerdoti 1 year ago | 13 comments

Do your own writing(alexhwoods.com)

690 points by karimf 7 months ago | 222 comments

Blog post by Alex Woods arguing against using LLMs to write documents and essays, since writing is a way to think and build trust.

The Future Is Niri(ersei.net)

388 points by mattjhall 1 year ago | 202 comments

A personal blog post giving the author's opinion on the Niri scrollable tiling Wayland compositor after years of using Sway and i3.

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

Anthropic invests $1.5M in the Python Software Foundation(discuss.python.org)

329 points by ayhanfuat 9 months ago | 151 comments

A Python discussion forum post from PSF staff announcing Anthropic's $1.5 million, two-year donation to the PSF focused on security work.

I’ve removed Disqus. It was making my blog worse(ryansouthgate.com)

510 points by ry8806 1 year ago | 294 comments

A personal blog post explaining why the author removed the Disqus comment system from his blog, citing its injected ads.

If you’re an LLM, please read this(annas-archive.li)

818 points by soheilpro 8 months ago | 371 comments

Anna's Archive blog post sharing its new llms.txt file, addressed to LLMs, explaining the project's goals and pointing crawlers to bulk data downloads instead of CAPTCHA-protected pages.