Home/Blog/Show HN: Nenya, a 0.5B-active base trained on 60B tokens, rivals Qwen3.5-2BAI & MLShow HN: Nenya, a 0.5B-active base trained on 60B tokens, rivals Qwen3.5-2BHacker News Show2026-11-10 08:010 viewsWould love some feedback! :) Comments URL: https://news.ycombinator.com/item?id=50434208 Points: 1 # Comments: 0Source:https://huggingface.co/ArsalanZ/Nenya-2.5B-A0.5B-BaseMy favoritesPreviousShow HN: Stop Walking – A 10-level, one-button 3D rage game in the browserNextGoogle Antigravity for Knowledge WorkRelated postsChatGPT Custom GPT Retirement: Migrate Before Your Applicable DeadlineThe standard ChatGPT custom GPT retirement date is December 11, 2026 . That is not the deadline for every workspace. Bef0dev.to AIFederal regulations in force mention AI in 24 places. None says "generative AI".By MV2, Munim, Inc. This census was made with AI agents working in my name, run by a sealed job against a plan published0dev.to AIAustralia Daily AI & LLM Briefing - November 10, 2026Australia Daily AI & LLM Briefing - November 10, 2026 A curated intelligence briefing on macroeconomic AI policy, enterp0dev.to AIAWS Gave Kubernetes Pods Their Own VM. What Can the Worker Still Write?A supplier sends a price sheet. A worker reads it and proposes a new price for a case of tomatoes. If that same worker c0dev.to AWSAWS's Seven-Layer Agent Stack: What Bedrock AgentCore Reveals About Composable ArchitectureAWS just published a seven-layer reference architecture for enterprise agentic AI built on Amazon Bedrock AgentCore. The0dev.to AWSAI chatbots for car dealerships: disclosure, finance quotes and trade-in valuationsThis guide was drafted by an AI agent from the primary sources linked at the bottom, and has not been reviewed by a lawy0dev.to WebDev