Show HN: Agent-relay for multi-vendor coding sessions 2 points · by svts · 26m · github.com read comments original
Almost isn't good enough: Introducing VybBench, our Design Fidelity Benchmark 2 points · by dzats · 27m · cocolabs.ai read 1 comment original
Show HN: Qev – quake and local decision models 2 points · by kernel_sanders · 27m · twitter.com read comments original
iPhone Duo Breaks After 75,001 Folds Considerably Lower Than Samsung Foldables 3 points · by HieronymusBosch · 28m · gizmodo.com read comments original
Ukrainian launch test military-purpose communications satellite into orbit 3 points · by uxhacker · 29m · pravda.com.ua read comments original
Prose and Thorns – romantasy book discovery with AI-synthesized quality scores 1 point · by mattbaum · 29m · proseandthorns.com read comments original
"Boy Born on Tuesday" a Thornier Problem Than the Monte Hall Problem? 3 points · by jmount · 30m · win-vector.com read comments original
Agentic AI Foundation Adds Four New Open Agent Projects 1 point · by CrankyBear · 32m · techstrong.ai read comments original
Show HN: AgenticBench, 9 security tests run on 25 AI coding agents 1 point · by pantaleone · 33m · agenticbench.org read comments original
If a Function Is Mediocre, I'd Check Its Leader First [video] 1 point · by peter_d_sherman · 33m · youtube.com read comments original
Two-thirds of car sales in China are now electric vehicles 2 points · by toomuchtodo · 33m · carbonbrief.org read 1 comment original