1
Are LLMs ready for HardChoices?
大模型能否应对"HardChoices"？这篇Konvens 2026论文给出了前瞻性测评。
arXiv:2607.11471v1 Announce Type: new Abstract: A lot of research attention has been devoted to checking whether large language models (LLMs) are poli…
2
The Effect of Scripts and Formats on LLM Numeracy
实证研究揭示脚本与格式对LLM数值推理能力的显著影响，为优化大模型数学表现提供新视角。
arXiv:2601.15251v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling hu…
3
Ask HN: Best prompt to show that AI isn't ready to take over
用一条简单汽车清单提问，揭示当前AI模型常识推理的短板。
Claude: please give me a list of famous cars named after fish, like the Plymouth Barracuda for example. Comments URL: https://news.ycombinator.com/ite…
4
Claude 通过率不到4%，SaaS-Bench撕碎了Computer-Use的「全自动办公」幻想
Claude Opus 4.7在106个真实办公任务中完全通过率仅3.8%，这场残酷评测撕碎了AI全自动办公的幻想。
UniPat AI 发布 SaaS-Bench 评测，Claude 等主流大模型在真实办公任务中完全通过率最高仅 3.8%，AI 全自动办公远未落地。