1
Show HN: Crilio – pytest for prompts
用pytest风格测试LLM提示词，Crilio让AI输出验证变得可编程。
Article URL: https://github.com/mukundzha/crilio Comments URL: https://news.ycombinator.com/item?id=49433864 Points: 5 # Comments: 0
2
How to Test AI Agents Without Calling More LLMs
避免昂贵循环调用LLM，分离编排与语言质量测试，实现低成本高效CI。
AI-agent testing often starts with an expensive loop: call the agent, send its answer to another model, ask for a quality score, and hope the score is…
3
idemkit: make any Python operation safe to retry (HTTP, queues, functions)
Python操作重试不再头痛！idemkit让HTTP调用、队列和函数都能安全重试，支持多种后端，真实服务器测试保障。
A few years ago, I spent about a month cleaning up duplicate charges. Every service involved already had idempotency "handled": the client sends an Id…
4
LLM Colosseum – A zero-dependency browser RTS to test LLM tool calling
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
5
Humans in the LLM Loop
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
6
SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
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…
7
VERA-MH: Validation of Ethical and Responsible AI in Mental Health
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 …
8
NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework
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…