Esteban Puello·12h agoMy benchmark fooled me three timesLast week I told people my vector index was about twice as fast as pgvector. A few days later I found out that pgvector had been running…
Wojdylak Michal·16h agoAgentic RAG, Graph-R1, MetaRAG and Friends on One Search Engine: What Actually Helps in 2026?RAG papers each bring their own retriever, corpus split, generator and metric, so their tables don’t compose. The practical question is…
OpenVidu·1d agoARM or x86 for WebRTC media servers? Participants per node on 3 cloudsOn every major cloud, an ARM instance costs less per hour than the x86 instance of the same size. On AWS, for example, a 4-vCPU Graviton3…
Model Dex News·2d agoThe Best AI Agent Scores Just 12% on a Tough New Test of Expert WorkSemiAnalysis’s GDPx puts AI agents in realistic jobs from chip design to law. Every model scored zero on finance and legal pass-or-fail…
Kenneth B.C. Wang·2d agoA Coding-Agent Team Solved 60% of Fresh GitHub Issues in My New Open BenchmarkA Claude Haiku 5.5 coder-and-reviewer team resolved 29 of 48 issues filed after the model’s training cutoff, for under 10 cents each.
InGoPenAIbyArXiv In-depth Analysis·Oct 29Frontier Models Look Excellent Until a Human Has to Do What They SayThe benchmark figures on technical report slides routinely show frontier multimodal models posting strong scores on visual question…
InTowards DevbyArXiv In-depth Analysis·Oct 27The 5% Compliance Blindspot: What Peking University and Ant International Learned Testing AI Agents…Why frontier LLMs with strong end-goal performance struggle in real enterprise operations: irreversible ledger mutations, phantom…A response icon1A response icon1
Sidekick Interactive·Oct 26Compose vs SwiftUI Gesture Performance BenchmarkThe right way to compare Jetpack Compose and SwiftUI gesture performance is to run the same interactive transition on controlled hardware…
yapapp·Oct 26Parakeet v3 vs Whisper vs Apple’s on-device model in 25 languages, every transcript publishedWe make Yap, a dictation app that runs NVIDIA’s Parakeet v3 on the device (Mac, Windows and phones). Before saying anything about accuracy…A response icon1A response icon1
