← 返回列表

@jeremyphoward: RT @ProximalHQ: Deepseek V4 works more thoroughly than other open source models: It writes its own tests and performs extensive validation.…

@jeremyphoward 3 信息等级 3 1 噪音/剔除；2 较弱；3 普通事实；4 重要行业动态；5 极重大事件。该分数是信息显著性，不是投资建议。 发布：2026-05-04T22:29 抓取：2026-05-06 04:02
🔗 原文链接
AI
摘要

Deepseek V4 模型能够比其他开源模型更彻底地工作，包括自行编写测试并进行广泛验证。

客观事实
  • Deepseek V4 能自动编写测试
  • Deepseek V4 能进行广泛验证
Deepseek

原文

RT @ProximalHQ: Deepseek V4 works more thoroughly than other open source models: It writes its own tests and performs extensive validation.…

likes: 31 | retweets: 4 | replies: 2 | views: 6914