待验证70% 置信观点精确时间
A developer reported that GPT-5.6 Sol spends approximately 70% of its runtime executing sleep commands
1
来源数
70%
置信度
短期 (~14 天)
时效性
2026/7/21
首次发现
来源
涉及实体
相关事实
待验证A developer characterized GPT-5.6 Sol as the most 'sleepy' model he had used and described its behavior as 'laziness'82% 相似待验证GPT-5.6 Sol具备持续运行数天的长周期任务能力,只需给定目标即可反复迭代产出详尽结果,且UI生成质量显著提升69% 相似待验证GPT-5.6 Sol是旗舰级最强模型,专为复杂智能体工作流设计,发布24小时内向所有付费用户开放69% 相似待验证GPT-5.6 Sol在BrowseComp浏览任务基准上达到92.2%67% 相似待验证GPT-5.6应用端需求可能分化:Sol用于编程和深度研究,Terra承担日常agentic工作流,Luna负责子代理调度67% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/680062API
curl https://kongchang.com/api/v1/knowledge/claims/680062MCP
get_claim(id=680062)