kwan 龟仙人

keep working
Co-founder - solarxlab
OKX 推荐码:
Binance 推荐码 :

[kwan 龟仙人 @MasterRoshikwan]

@thsottiaux fix serena mcp ,everytime open codex will open a lot of website page .please

[kwan 龟仙人 @MasterRoshikwan]

@elonmusk @mark_k I think follow the claude ,building coding model roadmap can make the AGI. coding can easy to make model to "AGI" .grok code have great skill and power to make code easy. hope grok model can make better. using grok create b2b & b2c software(claude code) easy to help grok powerful

[kwan 龟仙人 @MasterRoshikwan]

@CuiMao 可以的. 唯一有口音

[kwan 龟仙人 @MasterRoshikwan]

@bcherny easy hite the limite using max . but the model so nice

[kwan 龟仙人 @MasterRoshikwan]

https://t.co/XflJSLeqHY

[kwan 龟仙人 @MasterRoshikwan]

claudecode 出问题了 og

[Om Patel @om_patel5]

CLAUDE CODE MAX BURNS YOUR LIMITS 40% FASTER AND NO ONE TOLD YOU WHY

this guy set up an HTTP proxy to capture full API requests across 4 different Claude Code versions.

here's what he found:

Claude Code v2.1.100 silently adds ~20,000 invisible tokens to every single request.

they are server-side so you can't see them and they don't show up in /context.

the proof:

> v2.1.98: 49,726 billed tokens
> v2.1.100: 69,922 billed tokens
> same project, same prompt, same account

v2.1.100 actually sends FEWER bytes but gets billed 20K MORE tokens. the inflation is 100% server-side.

and it's not just about billing. those 20K invisible tokens enter the model's actual context window.

which means:

> your CLAUDE.md instructions get diluted by 20K tokens of hidden content
> quality degrades faster in long sessions
> when Claude ignores your rules you can't tell if it's because of invisible context you can't audit

the fix: downgrade to v2.1.98

npx [email protected]

[kwan 龟仙人 @MasterRoshikwan]

@Leviticus_Aru 我今天才清理5gb 的对话和git 缓存. 怎么说, 让模型花 token 了解情况和提供信息吧

[kwan 龟仙人 @MasterRoshikwan]

https://t.co/crS5geBanx 使用claude code 最佳

[0xkaka10 @0xkakaakl]

codex-loop + agent team +tmux is the best plugin in claude code!!!!
using opus plan +codex(gpt5.4 /codex 5.3 )do the work.

[kwan 龟仙人 @MasterRoshikwan]

@0xLogicrw @Jiaxi_Cui 需要codexcli, 权限要写好

[kwan 龟仙人 @MasterRoshikwan]

@turingou 是的, 烦死了

[kwan 龟仙人 @MasterRoshikwan]

@CryptoDanta 跟了

[ChandlerGuo 郭宏才 宝二爷 @ChandlerGuo]

BTC在97k附近震荡 符合预期

强势突破94k后进入震荡区间 日线上涨略显乏力

周末大概率96k-98k盘整 破95k需警惕回92k

97k附近别瞎追空 也别all in做多 位置尴尬

趋势已开启 总体震荡走高 以低多为主

[kwan 龟仙人 @MasterRoshikwan]

manus 确定了ai 工具一��要出海

[123olp @123olp]

我似乎看到了奇点

[Aaron @defi88888888]

rules + skills喂一个

[Xiaomi MiMo @XiaomiMiMo]

⚡ Faster than Fast. Designed for Agentic AI.
Introducing Xiaomi MiMo-V2-Flash — our new open-source MoE model: 309B total params, 15B active.

Blazing speed meets frontier performance.

🔥 Highlights:
🏗️ Hybrid Attention: 5:1 interleaved 128-window SWA + Global | 256K context
📈 Performance:
⚔️ Matches DeepSeek-V3.2 on general benchmarks — at a fraction of the latency
🏆 SWE-Bench Verified: 73.4% | SWE-Bench Multilingual: 71.7% — new SOTA for open-source models
🚀 Speed: 150 output tokens/s with Day-0 support from @lmsysorg🤝

🤗 Model: https://t.co/4Etm0yZKTL
📝 Blog Post: https://t.co/5zxmcDuB6o
📄 Technical Report: https://t.co/crac1YTLYl
🎨 AI Studio: https://t.co/nSReUs6QgW

[kwan 龟仙人 @MasterRoshikwan]

@hunterweb303 还是 MBP 或者转个 linux 服务器, 链接cursor

[kwan 龟仙人 @MasterRoshikwan]

@hunterweb303 报名