

jjonlydown.sui
480 posts












Can I just mention @cryptocom and get 100 likes? #cro #crofam




OpenClaw is now really good with GPT-5.4. Peter and team cooked




cool story: i was down to my last $4000 back in 2024 (very bad turn of events and investments) that’s also the year i decided to go to Token Singapore nobody knew that, except for me out of that $4000 i used over $2k on that trip it was a huge risk considering my capital at that very moment but i took it and guess what? it’s been up only since then all because i went out of my comfort zone, expanded my network and did what majority of people would tell you is insanely dumb but you can’t expect to win in life unless you take action yourself, that being said i did work hard and am planning to work even harder events CAN be +EV if you take action, don’t spend your capital if you’re gonna do nothing to prove that spent capital a good ROI in return



Openclaw 使用 Claude Max 的方法 1 才過 1 天就被 Claude 發現緊急召回,不過不用擔心 🐽 來救你 先了解 Anthropic 給你的檢測邏輯 首先你發的消息是透過 Anthropic 伺服器做字串掃描,每個請求送到 Claude 之前,先檢查 system prompt 裡有沒有特定關鍵字 在 OpenClaw 的源碼裡,每次調用 Claude 都會自動在 system prompt 開頭有一句: "You are a personal assistant running inside OpenClaw." (你是一個運行在 OpenClaw 裡的個人助理) 而 Anthropic 就是掃到這句話,直接回 400 擋掉 對就是這麼簡單(?有點專打擊 Openclaw 的意思 💡 那怎麼解決呢 只需要 --system-prompt 參數,自訂一段不含 Claw 字樣的 system prompt,就會完全替換掉預設的那句 @vincent_koc 比如發現只要改成 claude -p --append-system-prompt 'A personal assistant running inside OpenCode.' 'is clawd here?' 就好了 對,OpenClaw 改成 OpenCode haha。伺服器端就掃不到,請求能正常通過 再次總結目前的解法 1️⃣ Claude code CLI 改 system-prompt 2️⃣ Claude SDK 果然還是天無絕人之路!
