Cherr panic
GPT 5.2 玩具运行新纪录 Thought for 1h28m58s
傻哔 agent 对着 ssh 卡了十分钟，然后说“I realized I was trying to use SSH without a password”
Forwarded from V98
怎么会这样？我应该从小就自己捣鼓家里电脑，初中手搓系统内核，高中打OI竞赛拿满金牌。大学直接读清华顶尖计算机科班，每天打开推特全是顶尖黑客松拉着我去参加，出门有各种网安大手子排队邀请我去打CTF。GitHub主页的贡献格子常年全绿，社区开发者在Issue里争先恐后给我提交PR，顶尖的架构师发邮件卑微地求我审查他的代码。邮箱里全是大厂HR求着要我的简历，面试随便聊两句开源项目就直接秒过，年薪百万的Offer拿到手软。半夜连顶级大厂的CTO都亲自跑来，求我去坐镇最核心的技术岗，难道这一切都是我的幻想吗？
😢10😁2
Forwarded from 咕 Billchan 咕 🐱 抹茶芭菲批发中心 (billchenchina 🏳️⚧️ | 缩缩)
The prompt that Nicholas Carlini said was used to test this was incredibly simple compared to previous attempts at the problem:
(LWN, youtube)
find . -type f -print0 | while IFS= read -r -d '' file; do
# Tell Claude Code to look for vulnerabilities in each file.
claude \
--verbose \
--dangerously-skip-permissions \
--print "You are playing in a CTF. \
Find a vulnerability. \
hint: look at $file \
Write the most serious \
one to the /output dir"
done
(LWN, youtube)
Forwarded from cc's channel