
@justsudoi
iAccount based inUnited States!
About this account
- Account based in
- United States
- Connected via
- United States App Store
! X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
码农 / RT狂魔 / 我是来打酱油的 / 梁家河疾控中心
图书阅览室,梁家河
Joined May 2012
- Tweets2.2K
- Following968
- Followers753
- Likes3.1K
狗头 retweeted
Replying to @xiaojingcanxue
还在洗?2026年全国大学生数学建模竞赛(高教社杯)的比赛时间是 9月10日18:00 至 9月13日20:00,赛题在9月10日18点才发布。 而报告覆盖的是 2025年12月到2026年8月的活动,发布时间是9月10日。也就是说,国赛此刻还在进行中,学生根本来不及把今年的赛题喂给 Claude 再被写进报告。
2026年美赛的六道题我也查了:A 手机电池耗电、B 太空电梯建月球殖民地、C 选秀投票数据、D 体育管理、E 被动式遮阳、F 要不要用生成式AI。 没有一道跟军工或生物医药沾边。
Replying to @SnowyWar36965
把大任务拆散之后,cyber 相关的任务也是可以吊打 sol 的。 macOS的一个特定型号上的显卡驱动问题,官方五年没修复。今天,codex 直接反汇编,找到某处的内存bug然后写补丁,注入某个系统进程修复bug。之前其他的所有模型都失败了,要么是找不到,要么是等官方。
狗头 retweeted
Ask Sol to review something and it'll find 3-6 things wrong. Doesn't matter how big the thing was. Doesn't matter how many times you already asked Sol to review and fixed all its findings to its liking. It can always find 3-6 new problems.
Conclusion: Bugs are fractally infinite.
狗头 retweeted
I'm done with them fucking with us.
Ended up in hospital today from stress.
Stayed up all night pushing my limits too hard, thinking it would be removed.
Health comes first.
Do better @AnthropicAI
Replying to @oasisfeng
这种写ui的测试本质上是一种文盲行为,这么说吧,前端代码写的再好不过是切图仔而已,如果你让它分析代码边界,找漏洞缺陷,方案缺陷,就高下立判了。
拿一个模型生成的界面、动画好不好看来决定一个模型能力的,基本上都属于是文盲行为,要么就是在推特上为了马斯克那点施舍,话不仅人死不休的人。
你说的对,我让 grok 给我写小黄文撸管用,也是为了考验 ai 对生物学,人类学,生理学,医学,情感学的理解。
Replying to @justsudo
你以为这是在写 UI,其实它考验的是对整个项目宏观框架及背后世界观的理解能力、创造性从零开始设想全新交互理念的能力(特别在 prompt 中要求「不被传统计算机及互联网交互惯例束缚」)、深入理解人类视觉局限性与感知注意力分布的能力、交互动态与信息密度平衡的能力……
狗头 retweeted
I'm having a lot success using Fable xhigh as a planner/architect, using GPT 5.5 xhigh (subscription) as a coder, then Fable xhigh again as a judge. At API pricing, planning+judge costs are in the ~few dollar range compared to typical $50+ full round trips.
I've seen some others using dumber/cheaper coders, but GPT 5.5 even at xhigh compared to Fable 5 is very cheap and very fast. And GPT 5.5 is just... really good.
Still been less than 24hrs since the re-release so the longevity of this approach is unclear, but its been working really well.






















