Michaelkaoi

上个月我用 PolyCop 跟单系统试了一单，结果真的只花 5 分钟就自动跟上高手仓位，单笔 +207.8%（$177.41）。 最爽的是完全零经验也能跑，因为它会即时追踪我关注的几个高胜率地址，自动执行 + 止盈。 截图如下👇 你最近有试过 Polymarket 跟单吗？ 最难的是「选地址」还是「设参数」？ 分享一下你的经验，我在下面回覆大家实际配置～ #Polymarket #加密跟单 #polycop

@CommandCodeAI Will command code have official gateway that allow hermes agent/codex to use?👀

Command Code is the only code agent that has: 1. $1 Go plan with 10x free credits (best overall) 2. optimizes for top open models 3. repairs open models tool calls free 3. doesn't charge 400% more on open models like DeepSeek/MiMo - almost every other coding agent does, check!

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

@nhxao 只要登入/注册就可以吗？

🎉 重磅！Cavoti 品牌全面升级 + 永久免费福利来袭！ 为了感谢大家的支持，我们决定： 对所有用户永久免费赠送一个订阅套餐！ ✅ 每月免费获赠 80 美元 GPT + Claude 使用额度 ✅ 永久有效，每月自动发放 ✅ 是的，你没听错 —— 真正永久免费！ 无论你是老用户还是新朋友，注册后即可直接领取这个永久免费套餐。 这波品牌升级后，我们将以订阅制为主 + 按量使用为辅，带来更稳定、更优惠、更贴心的长期服务。80 美元/月的免费额度，足够大多数人日常高强度使用 GPT-5 和 Claude 系列了！ 预计7天内发布 敬请期待！

@nhxao 怎么没看到啊？不见了吗

创建密钥的时候选择公益分组 ❤️赶紧去无限爽蹬吧！！！

@nhxao 公益分组（无限白嫖）没了吗？昨天用了一下，发现今天那个分组找不到了

🎉 Cavoti 正式上线 自建 Max 号池 · 保真保纯 注册即赠几亿 Tokens 欢迎奖励 GPT 官价优惠 96% Claude 官价优惠 93% 全球节点加速 · 高并发稳定支持 开发者首选的 AI API 代理服务 立即体验：cavoti.com #AI #API #GPT #Claude #开发者工具

@reve Why limit the access region? I remember that there is no restrictions before

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

@PrismML @PrismML will u have 1bit image edit model?👀

Today we’re releasing 1-bit and Ternary Bonsai Image 4B. A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.

me: "i'm not signing up for another free tier that gives me 3 requests then asks for my credit card" also me, 20 minutes later: running FreeTheAI as my main api provider the catch? there is none: • 50+ models actually work (not "50 listed, 2 online") • /signup in Discord, get key instantly • /checkin daily = infinite credits, seriously • OpenAI-compatible, just switch base_url i've thrown chat, streaming, tool calls, and image gen at it. bill: $0.00 if you're still funding your side projects with your actual credit card in 2026... why tho? quick start for the lazy (compiled this for you): Get key: discord.gg/MZPzuBS72d Site: freetheai.xyz Base URL: api.freetheai.xyz/v1

@Lentils80 Can you share the prompt

Seeing as Claude Mythos is releasing soon, I have two VERY astonishing outputs to share from it. 👀 ZERO-SHOT and LOW effort as well! These are the best outputs I've seen for this prompt ever since the October 2025 Gemini A/B models.

I think there are two very urgent needs. First, for custom API and end-Point., When configuring the custom API and endPoint at the beginning. after opening the UI, there should be a dropdown option allowing me to choose which model to use. This way, I don't have to type in the configuration which model I want and less chance to crash

Tonight, as promised 🦞 That volcano plan this morning? Not a chatbot — it was MetaSkill, OpenSquilla's self-organizing skill protocol. You describe the goal in plain words. It discovers, picks, and composes the right skills into a real, safe workflow — and it can even write new skills itself. The Children's Day gift, for everyone: 🎁 MetaSkill is open source, starting now. 🎁 One sentence → one skill: show us what it builds for you, win token credits. 🔗github.com/opensquilla/op… Full story 🧵👇 #SayItBuildIt Challenge: one sentence → MetaSkill builds your workflow share your result in any form — screenshot, video, whatever. tag @OpenSquilla + #SayItBuildIt to enter. 3 categories · 1 winner each · 100M tokens per winner: 🔧 Most Useful 😂 Most Funny 🤯 Most Unexpected #SayItBuildIt #OpenSquilla

白嫖党狂喜，亲测可用。 FreeTheAI — 50+ AI 模型完全免费调用，OpenAI API 直接兼容，不需要信用卡。 流程： 1️⃣ 进 Discord：discord.gg/MZPzuBS72d 2️⃣ #commands 频道打 /signup 拿 API key 3️⃣ 每天 /checkin 一下，额度续上，无限用 chat、streaming、tool calling、生图都能跑。我已经把 base_url 切过去测了一波，确实零账单。 适合想 prototype 又不想烧 credits 的兄弟。 Base URL api.freetheai.xyz/v1是這個

@ideogram_ai When will Ideogram have image edit model?👀

Introducing Ideogram 4.0: the best open image model in the world. Think it. Make it. Own it. Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.

@EvanWritesX App叫什么

谷歌刚刚为 iOS 和 Mac 推出了一款免费的 AI 语音听写应用。 所有高级功能无需任何订阅即可使用。 100% 免费，完全本地运行，由 Gemma 4 提供支持。

@ftium4real 地区限制的api也可以用吗？

FreeLLMAPI — 聚合白嫖多家免费 AI Token 把 Google、Groq、Cerebras、Mistral、GitHub Models、Cloudflare、Zhipu 等免费额度串起来，用一个统一 key 调用，自动路由+故障切换，拿到接近 10亿 级别的月度免费 token。 🔗：<github.com/tashfeenahmed/…>

@crystalsssup will kimi k3 in native multi model and 1M token? I believe kimi with 1M token will be a beast of oepn source model

@AYi_AInotes 你邮箱哪里拿的

免费领 1 年 Cursor Pro，价值 $240🤩 继续给大家分享优质福利，这条专给还在读书的兄弟（不是学生的，转给你在校的朋友）。 在校大学生，用 .edu 邮箱通过 SheerID 验证，就能白嫖整整 12 个月 Cursor Pro，和花 $20/月的付费版一模一样： Claude / GPT / Gemini 全模型 + Agent 多文件编辑，每月还白送 $20 模型额度。 不用信用卡，验证过了直接开通! 毕业前赶紧薅，截至2026.6仍旧有效！ 入口评论区自取！

@iBigQiang Linux.do 要被邀请才可以进去

@michaelkaoi 其实在 linuxdo论坛就又很多人分享，重新写得详细教程 得花点时间了

免费薅羊毛来的 any 公益站 居然今天也上线了 claude Opus 4.8 你敢相信？还是纯免费，再次感谢 any公益菩萨😄

@Sapient_Int Can you provide a demo app or web app? I saw the model is not a chat model and need self training but I am not the tech master😅

Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models. The kicker? The full model trains in roughly one day on a $1,000 budget. This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game. Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.

@iBigQiang 求教程

@michaelkaoi 用 CC switch 工具设置挺简单的吧，还不行的话晚点我出个教程