AI | STEM | Creativity | Nature | Viral trends 🤖 Smart AI tools & tips 🚀 Boost your productivity with AI 📚 Learn something new every day

Joined April 2026
10 evil seduction tricks women can’t resist {Please don’t abuse these}:
2
9
47
13,526
Luma AI retweeted
A prototype gives people something concrete to disagree about. That's why the review-and-refine angle in this Ling-3.1-flash release interests me more than simply generating a polished first screen.
Ling-3.1-flash is now open source: ~560B total parameters, ~25B active per token and up to 1M context. Built for real work, it can turn a rough brief into a page, mobile UI or interactive prototype teams can review and refine. See the demo.
16
21
23
2,606
Luma AI retweeted
Short voice clips and long-form narration are different challenges. This Ming-3.0 release includes a 7.9B TTS Tiny model focused on long-form speech. I'd be interested to hear how the pacing holds up over a full passage.
Today, we're open-sourcing 5 Ming-3.0 models across 3 speech families. - Ming-3.0-tts: 0.5B voice design & paralinguistic cues; Tiny 7.9B A1.3B long-form speech. - Ming-3.0-audio: Flash 126B A6.5B understanding & tools; Tiny 9.3B A2.7B efficient dialogue. - Ming-3.0-asr: Tiny 8.6B A2B dialects & context.
15
20
24
2,360
Luma AI retweeted
The AI Builder Program is expanding across Europe with $10M in total support across compute grants, capital, and community programs. Are you building open models, developer tools, or applications on top of them? The program helps builders go from experimentation to scale-up through: - Compute grants for selected projects in areas such as open models, coding agents, post-training, and evals - VC connections to help turn open source projects into companies - Hackathons and demo days with communities including @AITinkerers, @techeurope_ , and @esra_robotics to build, connect, and share your work We’re kicking off the European expansion this week at #NVIDIAGTC Berlin with @NVIDIAAI, @Accel, and a network of European VCs. Building AI in Europe? Details below. 👇
119
336
124
754
755,217
Luma AI retweeted
FIVE SIGNS YOU’RE DEALING WITH A TRULY GOOD PERSON. 1. They often like to be alone.
21
73
3
501
337,016
Luma AI retweeted
Every result should have a clear reason behind it.
把 Agent 接进订单报表流程,我会特别关注一件事:最终的汇总数字,能不能沿着处理记录查回去。 原帖有两个值得留意的细节:同一订单出现不同状态时,比较更新时间,保留较新的取消记录;日期和金额存在歧义时,保留原始值,放进待核对清单。这些处理给后续复查留下了依据。 如果把这套流程用于实际业务,我希望结果旁边还能带一份处理说明:哪些原始行合并成了一单,为什么保留这个版本,哪些订单没有计入销售,哪些异常还在等待人工确认。 EverOS Cloud 在这次演示里,让上一批处理记录被新 Agent 检索并用于下一批任务。我想在这个基础上再加一个验收点:换一个没有参与前面处理的人,只给他原始数据和处理说明,能否重新核对出最终合计? 这也能帮助检查记忆到底留下了多少有用信息。如果核对时还需要猜测某笔订单为什么被排除,就可以进一步补全当时的判断依据。对连续处理表格的团队来说,这种可复查的交接记录很值得尝试。 #EverMind #EverOS
3
5
7
137
Luma AI retweeted
Stop starting from scratch. Build on past experience.
给 AI Agent 装上长期记忆:我的 EverOS Cloud 外贸业务实测 外贸客户开发有个很现实的问题:客户从询盘、样品确认到正式采购,可能需要跟进几个月。如果 AI 每次执行新任务都要重新了解客户背景,效率就会大打折扣。 最近我参考 EverOS 官方 GitHub Use Cases,使用 Python SDK 实际接入 EverOS Cloud,测试 AI Agent 的长期记忆能力。 🔹 我的测试流程: ① 使用 Python SDK 连接 EverOS Cloud API。 ② 将模拟巴西客户 DEMO-BR-001 的产品需求、样品状态、采购意向及跟进 SOP 写入云端记忆。 ③ 重新通过 API 检索历史信息,成功返回 1 条 Episode 记忆。 ④ 在 Memory Bank 中查看完整记录,成功找回预计采购时间、样品状态及后续跟进要求。 这次实测让我看到了 EverOS Cloud 在外贸业务中的应用潜力:让过去的客户记录成为后续 Agent 任务可以调用的上下文,而不是每次从零开始。 目前已验证记忆写入和检索,后续还想探索 Case → Skill,让重复业务经验变成可复用的技能。 📸 附图:真实 API 检索结果 + Memory Bank 记忆详情。 🚀 如果你也在开发长期运行的 AI Agent,可以体验 EverOS Cloud: 🔗 [专属追踪链接] everos.evermind.ai 🎁 现在订阅 Pro,每月额度变 3 倍,连享 6 个月。 #EverMind #EverOS EverOS Cloud 创作者合作内容
3
6
8
116
Luma AI retweeted
Stop repeating instructions. Let AI remember your workflow.
我同时开着好几个 AI 助手:一个跑 Tutti 活动,一个管 X,一个管小红书。 最烦的不是活多,是每换一个,就得把同样的规矩再交代一遍。
2
4
6
192
Luma AI retweeted
Save your writing rules once. Reuse them every time.
3
7
8
148
Luma AI retweeted
Save the reasoning. Retrieve the context. Improve the handoff.
换一个 AI 编辑,上一轮的判断还能留下来吗? 一篇稿子写完,除了成稿,我还想留下审稿时用过的判断:哪些话有依据,哪些承诺不能写,换个产品后哪些做法值得参考。 这次与 EverMind 合作,我用 EverOS Cloud 给写作流程加了一份“交班笔记”:保存上一轮工作记录,按新任务检索,再交给没有旧对话的新编辑。 我用了两个虚构产品做演示,写作、AI 审稿和 Cloud 调用都实际执行。这个小实验想回答的是:一次任务里的判断,怎么交到下一次任务手里? 1. 把判断连同出处留下来 第一轮写“纸舟文档助手”的批量导入说明。初稿明确区分了三件事:导入完成、后续检索命中、文件内容正确。它们需要分别确认。 独立 AI 审稿没有提出必须修改的问题。原稿保留,助手另整理案例注释,注明做法及适用条件。随后把任务资料、稿件、审稿与案例注释、修订决定整理成四条消息,通过 API 提交给 EverOS Cloud;查询时看到了保存的记忆记录。 2. 带着新任务,找相关经验 第二轮换成“巡灯值班台”,写交接摘要功能。 搜索时,我把新产品、受众和写作目标说明白,还加了一句:“需要与这类写作任务相关的历史经验,不需要替新产品补充能力或代写最终稿。” Cloud 返回了上一轮记录,保留了“导入结果、检索命中与内容核对的区别”这一判断。 接下来,接入流程把返回的完整历史记录数组交给新编辑,同时标注“旧任务资料,不是新产品事实”,再提供本轮产品资料。 3. 看新编辑实际交出了什么 没有继承旧对话的新编辑,在成稿中写到: “摘要保留的是条目已有的最近更新时间,不会核实现场进展、更新任务状态,也不会判断旧条目是否已经失效。” 这条保存→检索→交给新编辑的链路跑通了。EverOS Cloud 负责保存与检索;写作、审稿、案例注释和上下文组装,是我们自己接的流程。 结果也有边界:这轮有无历史记忆的稿件,在独立盲评中没有实质差异,不能据此说质量更好或效率更高。返回记录经过压缩,还遗漏了案例注释中明确的适用与不适用条件,关键条件仍要回看原文。 所以,我会给下一轮任务留这样一份交班笔记: 任务:给谁写什么,帮助读者作什么判断? 依据:哪份资料、哪个版本,完整原稿在哪里? 审阅:谁审的,认可或修改了什么,为什么? 做法:下次遇到相似任务,可以检查什么? 边界:何时适用,何时不能套用,什么变化后要重核? 这是基于本次体验提出的记录建议,不代表这些字段已被 Cloud 完整保存并取回,也不证明产品会自动学习或生成 Skill。 对做产品说明、分析报告、Agent 工作流的人,可以先拿一份可公开的工作记录试接入:下一次任务来时,看看能取回什么、漏了什么、新编辑怎么使用。 可以注册 EverOS Cloud (everos.evermind.ai)开始体验;有持续用量需求,再评估 Pro。本次活动 Offer:开通 Pro,享半年 3 倍月度额度。 #EverMind #EverOS
2
9
10
149
Luma AI retweeted
Stop explaining the same context to every AI agent.
Agent Memory 我已经用了好久了。手头同时跑好几个 Agent 和 Bot,最烦的就是换个工具或者团队交接时,之前排障踩过的坑又要从头交代一遍。所以在公司我一直想把记忆做成云端共享,让大家做过的工作变成下一次任务所有人都能直接调用的经验。 这次体验 EverOS Cloud,刚好把团队云端记忆这块补齐了。不管你是主力用 Antigravity、Codex 这类开发 Agent,还是自己搭的 Grok Bot、Muse、Hermes 等 Personal Bot,都能通过支持的 API 或 MCP 等方式接入。对于手头跑着好几个 Bot 的玩家来说,只要是已写入或导入云端、且允许访问的内容,它都能在不同 Agent 之间把上下文串联起来,不用换个窗口或换个 Bot 就从头交代背景。 它的能力主要分成三块。第一块是 User Memory,用来记录用户偏好与长期上下文;第二块是文档知识库,把文档、PDF、表格等业务资料转成可检索的记忆;第三块是 Agent Memory,专门把每次任务过程记录成 Case,从重复经验里提炼出可复用的 Skill,结合团队 SOP 给后续任务提供参考,正式流程调整依然由团队审核。 录屏里我专门拿 User Memory 做了一个演示,直接从控制台复制官方的 Agent Prompt 丢给 Antigravity 自动配好 SDK,把一次接口排障的上下文写入 User Memory,新开任务前再调 API 把这条记忆检索出来用。 进后台的 Memory Bank 就能直接翻看存下来的每条记忆,记偏了随时能调 API 纠正、删除或评价,而且 Cloud 版和自托管版共享核心 API,后续做核心功能迁移时也很省心。 现在订阅 Pro,每月额度变 3 倍,连享 6 个月。 Cloud 注册体验 everos.evermind.ai #EverMind #EverOS
2
6
8
210
Luma AI retweeted
Stop explaining the same context to every AI agent.
Agent Memory 我已经用了好久了。手头同时跑好几个 Agent 和 Bot,最烦的就是换个工具或者团队交接时,之前排障踩过的坑又要从头交代一遍。所以在公司我一直想把记忆做成云端共享,让大家做过的工作变成下一次任务所有人都能直接调用的经验。 这次体验 EverOS Cloud,刚好把团队云端记忆这块补齐了。不管你是主力用 Antigravity、Codex 这类开发 Agent,还是自己搭的 Grok Bot、Muse、Hermes 等 Personal Bot,都能通过支持的 API 或 MCP 等方式接入。对于手头跑着好几个 Bot 的玩家来说,只要是已写入或导入云端、且允许访问的内容,它都能在不同 Agent 之间把上下文串联起来,不用换个窗口或换个 Bot 就从头交代背景。 它的能力主要分成三块。第一块是 User Memory,用来记录用户偏好与长期上下文;第二块是文档知识库,把文档、PDF、表格等业务资料转成可检索的记忆;第三块是 Agent Memory,专门把每次任务过程记录成 Case,从重复经验里提炼出可复用的 Skill,结合团队 SOP 给后续任务提供参考,正式流程调整依然由团队审核。 录屏里我专门拿 User Memory 做了一个演示,直接从控制台复制官方的 Agent Prompt 丢给 Antigravity 自动配好 SDK,把一次接口排障的上下文写入 User Memory,新开任务前再调 API 把这条记忆检索出来用。 进后台的 Memory Bank 就能直接翻看存下来的每条记忆,记偏了随时能调 API 纠正、删除或评价,而且 Cloud 版和自托管版共享核心 API,后续做核心功能迁移时也很省心。 现在订阅 Pro,每月额度变 3 倍,连享 6 个月。 Cloud 注册体验 everos.evermind.ai #EverMind #EverOS
3
8
9
173
Luma AI retweeted
AI agents need memory, not just prompts.
AI agents need more than a good prompt. They need memory. I tested EverOS Cloud with a fictional e-commerce debugging scenario. First, I saved the debugging experience. Later, I searched for it with a different question and retrieved the earlier context, including the suggested fix and regression test. That’s the value of persistent memory in AI workflows: experiences can be saved and retrieved when they’re needed again. Try EverOS Cloud: everos.evermind.ai/login #EverMind #EverOS
3
7
8
136
🧠 AI agents need more than prompts — they need MEMORY! 🚀 Save experiences today. Retrieve solutions tomorrow. 🤖⚡ #EverMind #EverOS
🤝 Paid partnership
AI agents need more than a good prompt. They need memory. I tested EverOS Cloud with a fictional e-commerce debugging scenario. First, I saved the debugging experience. Later, I searched for it with a different question and retrieved the earlier context, including the suggested fix and regression test. That’s the value of persistent memory in AI workflows: experiences can be saved and retrieved when they’re needed again. Try EverOS Cloud: everos.evermind.ai/login #EverMind #EverOS
5
22
24
356
Less starting from scratch. More learning from experience. 🚀 EverOS brings memory to AI agents. #EverOS #AI #AgentMemory
3
17
20
324
🧠💛 AI Agents That Remember. Workflows That Get Smarter. Why start from scratch when your AI can remember what worked before? 🚀 Meet EverOS Cloud — persistent memory infrastructure that helps AI agents retain context, reuse experience, and deliver smarter workflows across sessions. ⚡ Remember users and past decisions 📚 Turn experience into reusable skills 🔗 Connect conversations, images, and documents 🛠️ Build smarter agents with a simple API 🔥 Special Offer: Get 3× the standard Pro usage allowance for 6 months with EverOS Cloud Pro. Build better AI agents. Let EverOS handle the memory. 🔗 Get started: everos.evermind.ai #AI #AIAgents #EverOSCloud #EverMind #AIInnovation
Meet EverOS Cloud. 💛 Your agent shouldn’t have to start from scratch every time a conversation ends. The preferences a user shared. The decisions made during a project. The approach that worked on a previous task. That context should be available when it matters again. EverOS Cloud gives your agents persistent memory through an API: • Remember users and retrieve relevant context across sessions • Turn task experience into Cases and reusable Skill memories • Bring conversations, images, and documents into your memory workflow You build the agent experience. We handle the memory infrastructure, so you can spend less time maintaining the stack and more time making your product useful. Subscribe to EverOS Cloud Pro and get 3× the standard Pro usage allowance for 6 months. Start here: everos.evermind.ai
6
13
1
14
462
🎬 The secret to AI filmmaking isn’t just creating beautiful shots — it’s maintaining consistency between them. 🤖✨ From character appearance to lighting, costumes, and camera movement, persistent AI memory could change how we create films. 🧠 With EverOS, the idea is to preserve creative decisions, remember previous corrections, and carry that context into the next shot. Because a great film isn’t just a collection of beautiful frames. It’s how those frames connect. 🚀 🔗 Explore EverOS: evermind.ai/everos #EverMind #EverOS #AIFilmmaking #AIAgents #CreativeAI
The hardest part of AI filmmaking isn’t creating a beautiful shot. It’s remembering the one before it. As an AI filmmaker, I’ve found that generating beautiful images is often easier than maintaining visual continuity. Imagine a fifteen-second scene. A young Chinese woman stands by a window, wearing an ivory silk blouse and faded blue skirt. Afternoon light falls from the left as the camera approaches. The first shot looks perfect. But in the next, her embroidery changes, her hairstyle shifts, the lighting reverses, and her facial proportions differ. Both shots look convincing individually. Together, they no longer belong to the same film. This happens regularly in my work. We spend hours correcting costumes, faces, lighting, camera direction and anatomy. The problem isn’t necessarily the model. It’s the lack of reliable memory between tasks. What if an AI agent could remember the creative decisions behind every shot? I’ve been studying EverOS documentation, developed by EverMind. I haven’t independently tested EverOS Cloud. This explores how its documented memory architecture might address filmmaking challenges, not a hands-on review. A workflow I’d like to explore First, establish a character sheet: a 22-year-old Chinese woman with consistent facial features, hairstyle, ivory blouse and blue skirt. Define the visual language: soft afternoon light, muted colours, an 85mm aesthetic and restrained camera movement. Next, record approved shots and corrections. Perhaps the lighting was reversed, sleeves too short, or camera movement excessive. Normally, these decisions scatter across prompts, notes and conversations. My proposed workflow would preserve character sheets, shot notes and revision feedback as retrievable context. According to its documentation, EverOS supports memory retrieval, recorded task experiences called Cases, and reusable Skills. The value isn’t simply storing information. It’s retrieving relevant creative decisions before preparing another shot. For the next scene, the agent could reference established details and corrections. The blouse stays ivory. The skirt stays blue. Lighting and camera movement remain consistent. That’s the continuity this workflow aims to support. Memory cannot guarantee perfect generation. Models may still introduce inconsistencies. I would still inspect results, correct anatomy and make final artistic decisions. But reducing manual reconstruction of context could improve production efficiency. Memory should support the director, not replace the director. EverOS also documents a distinction between accumulated task experience and established procedures, with human oversight remaining important. Consistency doesn’t mean repetition. Changes in costume, lighting or composition may be intentional. An assistant should remember decisions without treating them as permanent rules. Creative judgement must remain human. My assessment AI filmmaking doesn’t simply need more image generators. It needs better ways to preserve the reasoning, corrections and decisions connecting shots. EverOS presents a documented approach to persistent agent memory worth investigating in AI production. Practical effectiveness still requires testing, particularly retrieval accuracy, setup complexity and reliable application of corrections. This remains a proposed workflow based on EverMind’s official documentation, not a claim of successful product testing. But the underlying challenge is real. A film isn’t a collection of beautiful frames. It’s the relationship between them. Perhaps one of the most valuable things an AI agent could learn is how to remember that relationship. EverOS: evermind.ai/everos Documentation: docs.evermind.ai/cloud/overv… During the campaign, subscribing to EverOS Pro gives you 3× the standard monthly usage allowance for six months. #EverMind #EverOS #AIFilmmaking
4
15
1
15
338
from past tasks instead of starting from scratch every time. Persistent memory is a big step toward smarter, more reliable agents. 🚀
AI agents need more than a good prompt. They need memory. I tested EverOS Cloud with a fictional e-commerce debugging scenario. First, I saved the debugging experience. Later, I searched for it with a different question and retrieved the earlier context, including the suggested fix and regression test. That’s the value of persistent memory in AI workflows: experiences can be saved and retrieved when they’re needed again. Try EverOS Cloud: everos.evermind.ai/login #EverMind #EverOS
2
6
5
39
Luma AI retweeted
Useful AI memory isn’t just about saving conversations. It’s about retrieving the right context when a task needs it. Project decisions, completed work, and pending checks become much more valuable when agents can find and reuse that experience. #EverMind #EverOS
🤝 Paid partnership
最近用 Claude 和 Codex 一起写 uu-remote-linux,最烦的就是换个 Agent,又要把前面讨论过的决定解释一遍。 试了下 EverOS,把两边的项目记忆接到一起。这次拿一个交接摘要小工具跑了遍:Claude 写前半段,新的 Codex 会话先查记忆,再接着写,最后换回 Claude 复核,也能找到之前的完成记录。 这个体验我挺喜欢。代码本来就在 Git 里,“为什么这样写、还有哪些没验证”,现在也有地方可以查回来了。 把配置和这次的例子整理成了教程,给同样在两边来回切的朋友参考: github.com/VallierDev/claude… 配图是客户端现场复查,以及 Memory Bank 中保存的项目交接约定。 目前有个活动:开通 Pro,享半年 3 倍月度额度 → everos.evermind.ai #EverMind #EverOS
4
14
1
14
865
Luma AI retweeted
AI memory becomes truly powerful when one agent’s experience can help another solve the same problem faster. That’s a meaningful step toward smarter teamwork. #EverMind #EverOS
🤝 Paid partnership
4
10
10
165
Luma AI retweeted
Running multiple AI assistants is useful, but repeating the same instructions across every tool gets exhausting. Shared memory could make the workflow much smoother. #EverMind #EverOS
🤝 Paid partnership
我同时开着好几个 AI 助手:一个跑 Tutti 活动,一个管 X,一个管小红书。 最烦的不是活多,是每换一个,就得把同样的规矩再交代一遍。
4
10
10
168