亲测GLM 5.2在慢电脑上的运行体验，能力逼近闭源模型但面临内存瓶颈，本地部署党必看
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are si…
追踪开源聊天LLM十二个版本的信任度变化，揭示模型行为随时间漂移的潜在风险
arXiv:2607.02587v1 Announce Type: cross Abstract: Model cards quote trust-benchmark scores without recording when they were measured, and the same num…
仅花315美元从零训练10亿参数大语言模型，并开源全部权重与数据，堪称极低成本LLM训练范本。
Article URL: https://huggingface.co/AIIT-Threshold/Tessera-1B Comments URL: https://news.ycombinator.com/item?id=48758380 Points: 2 # Comments: 0
利用开源大模型构建多智能体协同系统，精准识别并对抗虚假信息威胁。
arXiv:2606.30259v1 Announce Type: new Abstract: In contemporary societies, the threat of disinformation has reached alarming levels, exacerbated by th…
从Claude到开源模型：研究发现LLM内部存在类似人类心理结构的情绪向量，并揭示其因果影响行为。
arXiv:2606.26987v1 Announce Type: cross Abstract: Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that…
开源LLM追赶闭源差距将在2026年底归零，预测重磅模型发布节点
Article URL: https://blog.doubleword.ai/frontier-os-llm Comments URL: https://news.ycombinator.com/item?id=48629346 Points: 1 # Comments: 0
从攻击成功率到攻击成功概率，系统性评估开源大模型提示攻击漏洞，为安全防护提供新视角。
arXiv:2505.14368v2 Announce Type: replace-cross Abstract: Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that …
移除系统提示后，里约大模型自曝真实身份——原来是 Nex-N2_pro 与 Qwen 的合并产物，并非“本土”原创。
Article URL: https://github.com/nex-agi/Nex-N2/issues/4 Comments URL: https://news.ycombinator.com/item?id=48528371 Points: 196 # Comments: 113
从单纯通过率到多语言执行评估，这篇论文重新定义了开源代码大模型的性能比较标准。
arXiv:2606.08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass ra…
开源LLM网关ToTra，集成PII扫描、语义缓存和负载均衡，确保GDPR与EU AI Act合规。
Article URL: https://github.com/SugaC-275/ToTra Comments URL: https://news.ycombinator.com/item?id=48420028 Points: 2 # Comments: 0
Apache 2.0许可下自由修改、商业使用并本地运行高端LLM，开发者告别专有硬件与API依赖。
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 What exactly is Gemma 4? Simply put, it’s a family of open-weight, open-source AI …
16B参数MoE模型EngGPT2的全面基准测试，与意大利及国际开源LLM性能对比。
arXiv:2605.07731v2 Announce Type: replace Abstract: This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-1…
用小型开源LLM实现可解释的翻译质量评估，兼顾隐私与成本，性能媲美大模型。
arXiv:2605.15763v1 Announce Type: cross Abstract: Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprieta…