Muchenxuan Tong

Enjoy a boring life.

[Muchenxuan Tong @demon386]

@SowingAlphaSeed There is no best choice here. A weighted combo of two might be considered too

[Muchenxuan Tong @demon386]

@DerivativesDon @ftraderft This depends on whether you're doing risk management or playing tactical shorting. For the former, enforcing stop for hedging is the way to live. The retest may have a high probability of happening, but risk management cannot rely on that.

[Muchenxuan Tong @demon386]

@DerivativesDon @readwise save thread

[Muchenxuan Tong @demon386]

@DerivativesDon @dampedspring @tytrade @readwise save thread

[Muchenxuan Tong @demon386]

@Young_AGI 好像还不支持 subagent 描述？只能建一个skill?

[Muchenxuan Tong @demon386]

@mranti 解决了，用"CLAUDE_CODE_EFFORT_LEVEL=auto"就行，之前是 max

[Muchenxuan Tong @demon386]

@mranti 奇怪 能展示一下 deepseek 对应的模型环境变量设置吗

[Muchenxuan Tong @demon386]

@DerivativesDon @readwise save thread

[Muchenxuan Tong @demon386]

@mranti 要用 /deepresearch，普通功能没问题

[Muchenxuan Tong @demon386]

你所有模型都是 pro[1m] 吗，这是我的配置：
export ANTHROPIC_MODEL=deepseek-v4-pro[1m]
export ANTHROPIC_DEFAULT_OPUS_MODEL=deepseek-v4-pro[1m]
export ANTHROPIC_DEFAULT_SONNET_MODEL=deepseek-v4-pro[1m]
export ANTHROPIC_DEFAULT_HAIKU_MODEL=deepseek-v4-pro[1m]
export CLAUDE_CODE_SUBAGENT_MODEL=deepseek-v4-pro[1m]
export CLAUDE_CODE_EFFORT_LEVEL=max

[Muchenxuan Tong @demon386]

@mranti 不过有些功能还是会出错(websearch, deepresearch)，不知道是不是因为我 subanget 也用 pro: API Error: 400 thinking options type cannot be disabled when reasoning_effort is set

[Muchenxuan Tong @demon386]

@Franktradinglog 为啥要过6月

[Muchenxuan Tong @demon386]

@Alpha_Ex_LLC Can you explain a little bit what does vix / vixeq measure different from spx 1m implied correlation?

[Muchenxuan Tong @demon386]

@real_kai42 没太懂这个和 plugin 的关系 https://t.co/hAnwbrI9Xr

[Xiaoyin Qu @quxiaoyin]

I Went From $3,000/Month on Claude to $5/Week on DeepSeek

And honestly? 80% of my work is identical.

For the past two months, I was burning $3-5K monthly on Claude Code. Every idea from design to development to testing - full end-to-end automation, even simulating users to test my products and provide feedback.

Extremely token-intensive. But Claude's caching sucked, making it insanely expensive.

Then I discovered DeepSeek V4.

The numbers:
• Claude: $5 input, $25 output per million tokens
• DeepSeek: $0.28 input, <$1 output (with their current discount)
• DeepSeek cached: $0.0002 - literally less than a penny

The caching optimization is game-changing. Once DeepSeek has seen content, it basically stops charging tokens.

My result: $5/week vs $1,000/week for the same workload.

What works exactly the same:
• UX modifications
• Product development
• Competitor research
• Content writing
• Code reviews

Where Claude still wins:
• Complex architectural decisions
• Extremely nuanced problems

But here's the thing - Claude has been getting dumber recently. It often says "done!" when it's clearly not done. Then apologizes but still doesn't finish the work.

My current stack:
• DeepSeek V4 Flash/Pro for 80% of daily work
• Codex 5.5 for the hardest problems (more reliable execution)
• Claude Code occasionally (because I already paid for it 🤷‍♂️)

DeepSeek is also 3x faster than Claude. For tasks like "compare these repos" or "read this long document," DeepSeek finishes instantly while Claude takes 3+ minutes.

Fun fact: I heard DeepSeek's speed comes from both optimization and gradually switching to Chinese chips (Huawei). If that's true, we might see even better performance later this year.

Everyone's betting on Anthropic's rising valuation in secondary markets. But when 80% of daily dev work can be done faster, better, and cheaper by open-source models...

Is Anthropic guaranteed to be the final winner? I think it's too early to call.

[Muchenxuan Tong @demon386]

@iwinux 可以的

[Muchenxuan Tong @demon386]

Kimi 2.6 Thinking 模式和 Deep Research 效果出人意料地好。Deep Research 个人体验比御三家的都好。@ppwwyyxx

[Dr. Sean @SeanQ81715949]

不能因为看过很多A片就认为自己经验很充足。
要知行合一，文献调研可以用AI，但思考不能。

[Muchenxuan Tong @demon386]

@options_insight I think the rolling itself shouldn't generate profit / loss, the carry happens day to day.