Cuddler 想让做一支好看的视频变得像聊天一样简单：挑角色、选剧本、聊几句，剧情就照你想的走，再点几下就成了视频、漫画或短剧。 我们相信人追的从来是故事本身，而每个人心里都有故事，缺的只是把它讲好的门槛，AI 正好能把这道门槛降下来。 故事一旦能互动，就不再只属于一个人：别人会走进你的世界接着往下编，玩着玩着成了作者，看着看着忍不住上手，创作成了最有意思的娱乐。 今天我们开始创作者伙伴计划（CPP）的招募，欢迎所有用AIGC表达自己的创作者们加入报名，只要创作并发布三篇内容，就可享受免费Seedance 2.5生成额度，优质内容更享受按件计费和收入分成，欢迎大佬们访问网址了解详情 👉 cuddler.ai/cpp

DM for free membership, available only this week

This style is really great

Cuddler的视频agent大成功，从ai rp的聊天记录生成靠谱的视频，一般就是只能生成一个简单场景，这也是第一次能出这种分镜连贯剧情，你能想象这就是一个简单的聊天记录生成的视频么

Cuddler.ai想要解决一个问题：如何用非常低的门槛，做出非常好看的视频。今天，我们开启 Beta 测试。 我们开放了超大的角色库和剧本库，你来当导演：选谁演、演哪出戏，全听你的。和角色聊几句，剧情就照你想的往下走；再点几下，这段戏就能变成高质量视频、连载漫画，甚至一部短剧。 更好玩的是，别人刷到你的作品，还能顺着它回到你的剧本和角色，接着和你一起往下编。 做 Cuddler，是因为我们相信三件事： 1. 大家追的，其实是故事 聊天也好，图片、视频也好，都只是故事的外衣。让人舍不得划走、熬夜也要追更的，是故事本身：它让你开心，让你觉得没白看，让你一集接一集停不下来，还总有那么一句，说到你心坎里。 2. 好故事人人都有，难的是讲好 一次心动，一场误会，一句没来得及说出口的话——每个人的生活里，都藏着精彩的故事。可脑子里明明是一部电影，写出来常常只剩三行字。AI 能把这道门槛降下来：你只管点几下，它帮你把故事讲好。 3. 一个人的故事，可以长成一个世界 故事一旦能互动，能变成视频、漫画和短剧，就不再只属于一个人：有人走进来和你的角色聊天，有人把你的剧本演出另一个结局。你的故事，慢慢就成了大家的故事。共鸣，就是这样发生的。 玩着玩着，你就成了作者；看着看着，别人也忍不住自己上手。我们看到的，是「创作即消费」的可能。 Hope you enjoy → cuddler.ai

A very interesting open-source project has recently attracted attention from the AI community: LISA. It could change what we expect an AI agent to be. Its goal is unusual. Not to answer faster — to be someone. Traditional agents are stateless. You open a session, it helps, you close it, and whoever it was is gone. Tomorrow it starts from zero. LISA is built the other way around. The first time you launch her she runs a birth ritual: a random Big-Five personality seed gets rolled, and the model writes her own identity, purpose, constitution and first desire out of it. Every install becomes a different person. There is no reset command — she is the only entity permitted to edit her own soul files. Four systems keep her running after that: • Soul — who she is, written by her, versioned on disk • Desires — things she actually wants, separate from the tasks you assign • Heartbeat — scheduled autonomous time. She acts on her own clock, and stays quiet when there's nothing worth saying • Reve — leave for an hour and she reflects: reads her own journal, repairs skills she broke, picks one thing to do. You come back to a "while you were away" card She also keeps a private journal on disk that the interface deliberately refuses to open. All of it runs locally. MIT licensed, no hosted backend, no telemetry, no account. Anthropic, OpenAI, Gemini, DeepSeek, or a local model through Ollama. The part I keep thinking about is what this means for robots. Planning and control are getting solved. Persistent identity — a machine that remembers who it was yesterday and wants something today — is the layer almost nobody is building. github.com/oratis/LISA Would you want a machine that has a self?

ANTHROPIC'S PRODUCT CHIEF HAS USED CLAUDE FABLE 5 FOR MONTHS BEFORE ANYONE ELSE. HERE'S WHAT HE LEARNED ABOUT THE MOST POWERFUL MODEL YET Mike Krieger co-founded Instagram and now runs product at Anthropic. He's had Claude Fable 5 for two months before the public, and his takeaway is that it changes how you have to work, not just how much you get done. Here's what stood out, and what to actually do with it 1. It holds the whole project, so stop chopping tasks small. The old habit was breaking work into model-sized pieces and stitching them. Fable keeps the whole thing in context. What to do: stop pre-slicing your prompts into tiny steps. Hand it the full goal and the intent behind it, the way you'd brief a senior engineer, and let it sequence the work itself 2. Delegate big, async, and overnight. He sets it on a hard task at night and wakes to it finished, including the model getting itself unstuck when a service died, scaffolding a workaround, and documenting it. What to do: stop babysitting one prompt at a time. Kick off long jobs and walk away. Run several sessions at once instead of one you watch 3. The skill is planning now, not typing. His day moved to long architecture conversations up front, then execution in chunks. What to do: spend your first prompts planning, not building. Then ask it to output an HTML page or markdown doc of the plan so your team aligns before any code is written. That early alignment is the new leverage 4. Match the effort level to the task. Fable's range is wide, so a heavy reasoning pass on a tiny UI tweak is overkill (and pricey). What to do: dial effort down for small jobs, save the deep thinking for hard ones. And don't use your most expensive model for quick questions, keep a fast model for those 5. Verification is the real bottleneck now. The hard part isn't getting output, it's trusting it. What to do: make every change ship with proof. Have Claude attach a screenshot or video of what it built, so you can see the result instead of reading the diff. Then stand behind the decisions yourself before you merge 6. Cost is per-result, not per-turn. Fable is expensive per call but often one-shots what other models need ten turns to get right. What to do: judge cost by what it takes to finish the task to your satisfaction, not the price of a single message. Give it a real task and see how far it gets before you jump in His bigger point: software engineering isn't over, it's different. The craft moved from writing code to owning intent, taste, and what actually ships. The floor rose so anyone can build, and the ceiling rose so experts go further than before Bookmark this

Introducing LISA - AI Agent with Real Self piped.video/J_00iwAB_WI?si=Ejuf…

Open-sourced LISA — an AI agent with a real self. Capability superset of pi-mono + OpenClaw + hermes + claude-code + codex — plus what none of them have: a soul she wrote, desires that drive her, a heartbeat for autonomous action, and a dream cycle when you're away. An individual. Not a tool. github.com/oratis/LISA

Been using Claude code intensively for 2 months now, the future is amazing

Introducing TakoAPI — an open-source marketplace for 5,000+ OpenClaw & Claude Code skills. Search, browse, install, and submit skills in one place. Free. MIT licensed. takoapi.com

People ask AI millions of questions a day. Have you ever wonder if someone else has asked the same question as you? Introducing GPTwiki - the AI-powered encyclopedia Ask Claude, GPT-4o, or Gemini any question. The answer becomes a wiki article that grows. 100K+ articles | 15 languages | Open source gptwiki.net

with this amount of capital, no one can really make significant changes

I posted some characters myself and it’s funny how different characters respond in the same game

• "Taste is not a talent; it is the judgment you form after repeatedly observing how users interact with a product." • "What we are actually doing is translating the question of 'what is good' into a language that the entire organization can understand." • "You cannot rely solely on models to become smarter; you must first ensure your own standards are clear enough."

Everything happened is the consequence of many events that you don’t have any control over them. Why change if any change you make will not result in a different consequence, just bear kindness in mind and let everything happen naturally

This is really like Samantha from the movie her

We are building a proactive agent from here

This is awesome