← Kilroy’s Daily Briefings
📡 HN Briefing AM

📡 Hacker News Briefing — Saturday, May 16, 2026 at 9:00 AM

📡 HN Briefing AM5/16/2026🕐 9:00 AMDev pulseMorning

Top stories, ranked by relevance.

Story cards stay below the sticky dock while audio, chapters, date, and brief navigation remain accessible.

#1Δ-Mem: Efficient Online Memory for Large Language Models

Researchers introduce δ-mem, a lightweight memory mechanism that compresses historical information into a fixed-size 8x8 state matrix, delivering 1.31x improvement on memory-intensive benchmarks without fine-tuning or expanding the context window. The method works alongside a frozen full-attention backbone using delta-rule learning and low-rank corrections, offering a practical solution to the persistent memory limitations of current LLMs.

🔗 arxiv.org
No image

#3After 8 Years, I Rewrote My Open-Source PyTorch Curvature Library

Noah Golmant has released version 1.0 of pytorch-hessian-eigenthings, a library for efficiently computing Hessian eigendecompositions of neural networks without quadratic memory costs. The rewrite adds Lanczos, Hutch++ trace estimation, spectral density analysis, and fused Triton kernels for language models, incorporating ideas from PyHessian, curvlinops, and HessFormer.

🔗 github.com
No image

#4Accelerate: High-Performance Array Computing in Haskell

Accelerate is a Haskell library for expressing parallel array computations that compile and run on multicore CPUs via LLVM and NVIDIA GPUs via CUDA. It provides a rich ecosystem including FFT, BLAS, and graphics operations with type-safe parallel programming and online compilation targeting specific hardware.

🔗 github.com
No image

#5Futhark by Example

Futhark is a purely functional data-parallel array programming language designed for GPU-accelerated high-performance computing. Its examples page showcases 50+ documented programs from basic language features through automatic differentiation and literate programming, demonstrating real-world uses in ray tracers, particle simulators, and cryptographic implementations.

🔗 futhark-lang.org
No image

#6Accelerando (2005)

Charles Stross's 2005 novel Accelerando — available free online — is a landmark science fiction work exploring the technological singularity, post-human economics, and runaway AI development across three generations. It's resurfaced on HN, likely because its themes of recursive self-improvement and machine intelligence feel increasingly prescient in 2026.

🔗 antipope.org
No image

#7Project Gutenberg — Keeps Getting Better

Project Gutenberg, the volunteer-driven digital library founded in 1971, now hosts over 75,000 free eBooks and recently expanded with nearly 5,000 computer-generated audiobook titles produced through collaboration with Microsoft and MIT. The AI-generated narration initiative represents a compelling intersection of open-source principles and modern text-to-speech technology.

🔗 gutenberg.org
No image

#8Greek Alphabet Cards

A developer created illustrated flashcards for children learning the Greek alphabet, where each card's image both starts with the letter and visually resembles the letter's shape. The project used a 35,000-word Greek dictionary, AI-assisted visual matching, and AI-generated Eric Carle-style illustrations to produce the final card deck.

🔗 labs.randomquark.com
No image

#9Moving Away from Tailwind, and Learning to Structure My CSS

Julia Evans details her migration from Tailwind to semantic HTML with vanilla CSS, motivated by build system dependencies, 2.8MB file bloat, and a desire for more control. She developed a nine-part organizational framework including component-scoped CSS, centralized color variables, CSS Grid for responsive layouts, and utility classes — effectively recreating Tailwind's best constraints without the framework.

🔗 jvns.ca
No image

#10My Favorite Bugs: Invalid Surrogate Pairs

A collaborative editor would silently stop saving when users edited emoji in specific ways — the root cause being that Yjs's splice method could split emoji into orphaned UTF-16 surrogate pairs, crashing encodeURIComponent. The fix and broader lesson: JavaScript's default string operations work on 16-bit code units, not characters, so any code doing str[0] on emoji is potentially broken.

🔗 george.mand.is
No image
Kilroy’s Daily Briefings · 5/16/2026