StarRiver
259 posts
StarRiver
@StarRiverXH
Solo Dev / AI Product Builder / Content Creator
🧵 Deli AutoResearch SKILL is now officially open source! 🎉 victorchen96.github.io/auto_research/… Alongside it, we’re dropping our 4th survey paper — this time on Self-play. victorchen96.github.io/auto_research/… Inspired by AlphaZero, we got a powerful insight: prior knowledge doesn’t always lift the ceiling. Models can discover more globally optimal solutions just by playing against themselves. The biggest change in this paper? For the first time, the AutoResearch Agent autonomously planned GPU experiments — and submitted actual RL runs on the DeepSeek 285B model. The entire RL pipeline — experiment design, code writing, running, debugging, and conclusion summarization — was 100% automated, with zero human intervention from me. This was incredibly difficult, but an incredibly important step. victorchen96.github.io/blog_self_play… GRPO is the tool being called by the AutoResearch Agent here. We see this as the beginning of our Continual Learning research journey. 🚀 As always, this is my personal research project, unaffiliated with any organization. All views are my own. #AI #ReinforcementLearning #SelfPlay #OpenSource #AutoML #ContinualLearning #DeepSeek
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.
还在把 DeepSeek 网页版当成普通的聊天框在用？赶紧给它装上这个开源物理外挂！一秒把网页版魔改成神级 AI Agent 工作台：DeepSeek++！ 🚀 让人直拍大腿的逆天增强： 🔌 无缝支持 MCP 协议：直接打破浏览器限制，让 DeepSeek 狂暴联动本地工具与外部数据，化身真正能干活的特工。 🧠 注入记忆与技能（Skill）：自带记忆宫殿，定制专属技能流，让 AI 拒绝当健忘复读机，越调教越懂你。 🤖 自动化与对话导出：复杂任务一键自动化运行，对话记录完美格式化导出，生产力直接拉到大气层。 支持 Chrome、Edge、Firefox 全平台。完全开源纯净，极客把玩大模型的终极姿势，速冲👇 🔗 Chrome 商店直达：chromewebstore.google.com/detail/deepsee… 🔗 开源仓库：github.com/zhu1090093659/… #DeepSeek #开源 #Chrome插件 #AIAgent #生产力工具 #黑科技 #极客必备
🚀 1,000+ TOKENS/S ON A 1T MODEL! 🚀 We are thrilled to release Xiaomi MiMo-V2.5-Pro-UltraSpeed in collaboration with @TileRT_AI , breaking the 1,000 tokens/s output speed on a 1 Trillion parameter model for the FIRST TIME! Not wafer-scale integration like Cerebras. Not pure on-chip SRAM chips like Groq. We achieve 1,000 tps on a 1T MoE model using just a SINGLE, STANDARD 8-GPGPU NODE. Read the full technical deep dive：mimo.xiaomi.com/blog/mimo-tile… Want to experience the future of real-time AI? 👉 Apply for UltraSpeed now: platform.xiaomimimo.com/ultraspeed ⏳ Limited-Time Access: Application-based · Jun 8 – Jun 23 (PDT) 💬 Chat Experience: Completely FREE for a limited time — try the blazing-fast web chat now. ⚡ UltraSpeed API: Just 3x the price for a ~10x boost in output experience. 🤝 Enterprise & Large-Scale Needs: business-mimo@xiaomi.com
