零依赖的浏览器RTS游戏，用趣味对战测试LLM工具调用能力，玩法与调试两不误。
Article URL: https://github.com/asp67/llm-colosseum/tree/main Comments URL: https://news.ycombinator.com/item?id=48752981 Points: 1 # Comments: 0
LLM生成代码补丁质量参差不齐，人类审查不可缺位——一个缓存限制设置暴露粗心问题。
Article URL: https://derickrethans.nl/humans-in-the-llm-loop.html Comments URL: https://news.ycombinator.com/item?id=48481213 Points: 1 # Comments: 0
提出SoCRATES框架，解决LLM调解员在多领域和社会认知变化下的自动评估难题，填补现有测试平台局限。
arXiv:2606.05563v1 Announce Type: new Abstract: Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by…
VERA-MH 提供标准化框架验证心理健康 AI 的伦理与责任，帮助开发者确保算法合规安全
arXiv:2605.13318v2 Announce Type: replace Abstract: Chatbot usage has increased, including in fields for which they were never developed for--notably …
脉冲神经网络的局部学习规则综述与基准测试框架，助你快速理解不同训练算法的差异与适配场景
arXiv:2605.15058v1 Announce Type: cross Abstract: The rapid expansion of spiking neural networks (SNNs) has led to a proliferation of training algorit…