Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)

Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)
Apple releases iPhone Duo simulator and Xcode 27.1 beta
https://developer.apple.com/documentation/xcode-release-notes/xcode-27_1-release-notes
Saving another 100TB of RAM with math (and Rust)
US Military had close call after using AI for hallucinated intelligence report
https://www.cnn.com/2026/09/18/politics/us-military-ai-false-intelligence-china-ship
Photon-Emission-Guided Laser Fault Injection Enables RP2350 Secure Debug
https://donjon.ledger.com/blog/rp2350-secure-debug-laser-fault-injection/
C++26: Trivial infinite loops are no longer undefined behaviour
https://www.sandordargo.com/blog/2026/09/16/cpp26-trivial-infinite-loops
I Vibed a Proof of Conway's Conjecture
https://overreacted.io/how-i-vibed-a-proof-of-conways-conjecture/
Subnormal floating-point numbers are expensive on Intel processors
ZCode, the GLM coding agent, silently uploads your Git history
https://tokenstead.ai/guides/zcode-silent-git-history-upload
Microsoft exec called AI scraping 'the largest theft of labor in human history'
🏆 Best of Hacker News — Sep 17, 2026
Hister: A private search engine for the pages you visit and…
596 points · 162 comments
📖 HN Reader: https://hn.jsdev.space/story/49743097
🔗 Original: https://github.com/asciimoo/hister
💬 HN: https://news.ycombinator.com/item?id=49743097
Goose: 1.16x faster than C++ and 1.12x than safe Rust, while memory safe
Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint