热点
"模型规范" 相关文章
我们对AI认识远远不足，所以透明度才至关重要｜腾研对话海外名家
腾讯研究院 2025-11-06T10:26:42.000000Z
我们对AI认识远远不足，所以透明度才至关重要
36氪 AI 2025-11-06T10:14:50.000000Z
AI Craziness Mitigation Efforts
少点错误 2025-10-28T19:41:09.000000Z
AI人格分裂实锤！30万道送命题，撕开OpenAI、谷歌「遮羞布」
智源社区 2025-10-27T17:39:43.000000Z
Anthropic、Thinking Machines Lab论文曝光：30万次压力测试揭示AI规范缺陷
机器之心 2025-10-27T09:42:21.000000Z
AI人格分裂实锤，30万道送命题，撕开OpenAI、谷歌「遮羞布」
36kr-科技 2025-10-27T01:03:57.000000Z
AI人格分裂实锤！30万道送命题，撕开OpenAI、谷歌「遮羞布」
新智元 2025-10-26T15:57:42.000000Z
A New AI Research from Anthropic and Thinking Machines Lab Stress Tests Model Specs and Reveal Character Differences among Language Models
MarkTechPost@AI 2025-10-26T15:39:10.000000Z
Anthropic、Thinking Machines Lab论文曝光：30万次压力测试揭示AI规范缺陷
机器之心 2025-10-25T08:55:24.000000Z
Anthropic、Thinking Machines Lab论文曝光：30万次压力测试揭示AI规范缺陷
机器之心 2025-10-25T07:32:39.000000Z
Stress-Testing Model Specs Reveals Character Differences among Language Models
cs.AI updates on arXiv.org 2025-10-10T04:11:52.000000Z
Stress-Testing Model Specs Reveals Character Differences among Language Models
cs.AI updates on arXiv.org 2025-10-10T04:11:52.000000Z
Quoting Nick Turley
https://simonwillison.net/atom/everything 2025-09-30T11:08:54.000000Z
OpenAI玩崩了！GPT-4o更新后变马屁精差评如潮，奥特曼：一周才能完全修复
智源社区 2025-04-30T07:08:10.000000Z
OpenAI玩崩了，GPT-4o更新后变马屁精差评如潮
虎嗅 2025-04-29T07:08:25.000000Z
GPT-4o Is An Absurd Sycophant
少点错误 2025-04-28T19:02:26.000000Z
Character training and the secret arts of post-training
Interconnects 2025-02-26T13:14:38.000000Z
奥特曼剧透 GPT-5 将免费使用！o3 独立发布被腰斩，OpenAI 疑似内涵 DeepSeek
APPSO 2025-02-15T02:15:23.000000Z
GPT-4.5马上发布，GPT-5免费畅聊！奥特曼剧透大动作，网友：让DeepSeek整破防了
硅星人Pro 2025-02-15T02:09:17.000000Z
GPT-4.5马上发布，GPT-5免费畅聊！奥特曼剧透大动作，网友：让DeepSeek整破防了
智源社区 2025-02-14T05:07:11.000000Z