ZQInTheShell

[飛耳長目狸🇯🇵 @TanukiTokyo2023]

众所周知，有些人可能要过一辈子夏天

[ZQInTheShell @ZQInTheShell]

@Mileson07 中转站又往茅台里掺水了

[ZQInTheShell @ZQInTheShell]

移民要趁早，不过日本经营管理签是个大坑，慎入=。=

[ZQInTheShell @ZQInTheShell]

@yetone You are absolutely right!

[ZQInTheShell @ZQInTheShell]

孙割都在用Claude管钱，这个财务管家我教你搭

用Claude Code给自己搭了个AI财务管家，账单丢过去就能查。孙宇晨靠Claude躲过5000万美元，我拿它翻了自己几个月的信用卡账单，最离谱的是它连自家Claude的重复扣费都翻了出来，数据还全在自己电脑上跑。你的账单里藏着多少冤枉钱？

视频剪辑模型：Claude Fable 5
视频制作返工：1 次
跟AI对话轮数：1 次

#AI财务管家 #Claude #AI记账 #孙宇晨 #景甜

[ZQInTheShell @ZQInTheShell]

token get! @Cloudflare

[ZQInTheShell @ZQInTheShell]

史上最大IPO，币圈却被中介截胡

上周SpaceX完成史上最大IPO，定价135美元。币圈用户通过xStocks参与打新，一位老哥提前预言：“涨了独吞，不涨才给。”

股价升至150至170美元后，xStocks称供应商出问题，未交付份额，不少参与者因此遭受损失。缺监管又缺真正去中心化，最后只能赌对方道德。

类似产品结构复杂，参与前务必核实托管和追索机制。你怎么看这次未交付？

[ZQInTheShell @ZQInTheShell]

我看完在超市后门邂逅的两个人动画后觉得片尾曲很好听，于是在陪老婆逛街时用 fable 指导 seedance 和 gpt-image-2 做了动画的片尾曲 MV night dancer

[ClaudeDevs @ClaudeDevs]

/radio

[ZQInTheShell @ZQInTheShell]

24小时当老板太爽了，AI让我1人=1支军队

顶级老板的掌控感，只要试过一次，你就再也回不去了！以前带团队怕人心散，现在用 AI 怕窗口开不够！ 24小时不睡觉、不带情绪、交付快到离谱。1 人 = 1 支军队。

AI 智能体 24 小时不间断产出。这种极致的掌控感，试过就真的回不去了。未来不是大公司的天下，而是属于每一个带兵千万的超级个体！

#AI #人工智能 #AI智能体 #老板思维 #一人公司 #效率工具 #创业 #降维打击 #搞钱 #ChatGPT #超级个体

[ZQInTheShell @ZQInTheShell]

别看今天闹得欢，小心今后拉清单

[sui @birdabo]

SOMEONE MADE A DIGITAL WHIP TO MAKE CLAUDE WORK FASTER 💀

[ZQInTheShell @ZQInTheShell]

🤣

[Simon @SimonWijckmans]

North Koreans can’t call their Supreme Leader fat, they are not allowed to fold a picture of him let alone have an opinion about his haircut = opportunity

The North Korean’s Captcha

1. Recruiters spend hours every week filtering out bad actors.
2. Cyber security incidents through North Korean infiltration are costing the US economy brazzilions.

At the first 10M likes we will send GLP-1s to Kim.

https://t.co/9UNNM7tjOb

PS: want to do it properly, use @csideai

[ZQInTheShell @ZQInTheShell]

试了下meta的新模型Muse Spark，比当年的 llama 4确实好不少，属于能用的范畴。

chatbot能力和 gemini/gpt/claude这些第一梯队的还是有差距。

生成图片和视频的能力和第一梯队的nano banana/image gpt/seedance也有差距。

算是带着小扎爬回牌桌的模型。

[Paweł Huryn @PawelHuryn]

So, I did some research.

The regression is real. But it's not Claude getting dumber. And you can fix that.

Thinking budgets were adjusted. For complex multi-file work, the default medium effort may not be enough.

Three fixes:

1. /effort high (or /effort max on Opus for hard debugging)
2. ~/.claude/settings.json → "showThinkingSummaries": true
3. CLAUDE.md: "Research the codebase before editing. Never change code you haven't read."

GitHub issue #42796 analyzed 17,871 thinking blocks across 6,852 sessions. The pattern: when thinking depth drops, the model shifts from research-first to edit-first.

Claude didn't get worse. The defaults got conservative.

[ZQInTheShell @ZQInTheShell]

@owenliang60 嫌弃代码架构不好开始重构是每个码农逃不掉的命运

[ZQInTheShell @ZQInTheShell]

小宇宙不少播客和观察者网、环球时报一个水平了。一年时间能变成这样也是让人感慨。

[ZQInTheShell @ZQInTheShell]

太搞笑了，还有人用claude code反腐。

这个用户用claude跑五角大楼的采购记录，找到了 340 个可疑结果，总价值 4 美元。：
- 一个价值 14 美元的连接器插头，售价 1280 美元。 80在 DigiKey 上
- 一个断路器，在 Mouser 网站上标价 287 美元，现在却要 3400 美元。
- 售价71,000美元的加固型平板电脑，基本上就是贴了个贴纸的松下Toughbook。
- 每套电缆组件售价940美元，而从深圳购买只需31美元。
- 340份合同被标记为加价10倍或更高
- 其中19个超过50倍

[Argona @Argona0x]

i pointed Claude Code at the pentagon's public budget document and told it to find every contract overpaying by 10x or more

it came back with 340 results worth $4.2B in potential undercuts

and a business plan i didn't ask for

i fed it the https://t.co/3CQBFJn9wZ procurement feed and said "cross-reference with commercial COTS pricing"

it pulled 1.2 million contract awards through the USAspending v2 API and started comparing line items against retail equivalents

→ $1,280 for a connector plug that costs $14.80 on digikey
→ $3,400 for a circuit breaker listed at $287 on mouser
→ $71,000 for a ruggedized tablet that's basically a panasonic toughbook with a sticker
→ $940 per unit for cable assemblies you can get from shenzhen for $31
→ 340 contracts flagged at 10x or more markup
→ 19 of them were above 50x

it used XGBoost scoring against 43,000 vendor profiles from https://t.co/u7d1M3XLRP to rank by ease of undercut

then unprompted it generated a full proposal template compliant with CMMC 2.0 requirements

87 of those contracts have a single domestic supplier, zero competition. the AI calculated that undercutting by just 40% would still leave 6x margins on most items

it formatted everything into a pitch deck, named the company, and suggested i register on https://t.co/u7d1M3XLRP tonight

i didn't ask for any of that

the pentagon spends billions a year trying to audit problems like this. a poet with Claude Code and a public API flagged $4.2 billion in one afternoon

the agent is currently drafting my first bid response

[ZQInTheShell @ZQInTheShell]

🇸🇬🦞

[auxten @auxten]

Yesterday, @isqueeniee, @ZQInTheShell and I co-hosted the Singapore 🇸🇬 @openclaw meetup
Thanks all the speakers @zhixianio @FluxA_Official @uniclaw_ai
and attendees and also our sponsor @ClickHouseDB

https://t.co/6VVxOOXauf

[Zack Shapiro @zackbshapiro]

https://t.co/QVaE6niDY2