Launch HN: Societies.io (YC W25) – 针对目标受众的 AI 模拟
6 分•作者: p-sharpe•10 个月前
嗨，HN，我们是 Patrick 和 James！Artificial Societies (<a href="https://societies.io">https://societies.io</a>) 让你模拟你的目标受众，这样你就可以在发布营销、信息和内容之前进行测试。<p>这里有一个快速的产品演示：<a href="https://www.loom.com/share/c0ce8ab860c044c586c13a24b6c9b391?sid=b7b4e23c-5223-4aad-ae08-b5c704d45aad" rel="nofollow">https://www.loom.com/share/c0ce8ab860c044c586c13a24b6c9b391?...</a><p>营销人员总是说他们一半的支出会被浪费掉——他们只是不知道是哪一半。 现实世界的实验有所帮助，但它们运行起来太慢且昂贵，无法大规模进行。 因此，我们正在构建模拟，让你能够快速、廉价地进行测试，以找到你信息的最佳版本。<p>工作原理：<p>- 我们根据来自真实个人的真实世界数据创建 AI 人物角色，这些数据是从公开的社交媒体资料和网络资源中收集的。<p>- 对于每个受众，我们从数据库中检索相关人物角色，并将它们映射到交互式社交网络图上，该图旨在复制社会影响模式。<p>- 一旦你起草了你的信息，每个实验都会运行一个多智能体模拟，其中人物角色对你的内容做出反应并相互交互——这些模拟需要 30 秒到 2 分钟的时间来运行。 然后，我们会呈现结果和见解，以帮助你改进你的信息传递。<p>我们面临的两个最大挑战是准确性和用户界面。 我们已经测试了我们预测 LinkedIn 帖子表现的性能，初步结果很有希望。 我们的模型的 R2 值为 0.78，我们发现，在查看同一作者发布的帖子时，模拟中的“信息传播”是实际参与度的最重要预测指标。 但将这些模拟推广到其他环境以及寻找评估的真实数据还有很长的路要走。 我们在这里提供了关于准确性的一些更多信息：<a href="https://societies.io/#accuracy">https://societies.io/#accuracy</a><p>在用户界面方面，我们最大的挑战是弄清楚“实验”形式对用户是否具有吸引力。 我们特意关注这一点（而不是 AI 调查），因为实验利用了我们在社会影响以及想法如何在人物角色之间传播方面的专业知识。<p>James 和我都是行为科学家出身，但走上了不同的道路。 我帮助企业运行 A/B 测试以提高销售额和客户留存率。 与此同时，James 成为了一名数据科学家，并在业余时间将 33,000 个 LLM 聊天机器人连接在一起，并撰写了一篇关于它的论文 (<a href="https://bpspsychub.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/bjop.12764" rel="nofollow">https://bpspsychub.onlinelibrary.wiley.com/doi/pdfdirect/10....</a>)。 他向我展示了这些模拟，我们决定以此为基础创办一家初创公司。<p>定价：Artificial Societies 免费试用。 新用户可获得 3 个免费积分，然后是为期两周的免费试用。 Pro 账户每月 40 美元即可获得无限次模拟。 我们计划稍后推出团队功能，以及为定制受众提供的企业定价。<p>我们希望你试用该工具并分享你的想法！
查看原文
Hi HN, we’re Patrick and James! Artificial Societies (<a href="https://societies.io">https://societies.io</a>) lets you simulate your target audience so you can test marketing, messaging and content before you launch them.<p>Here’s a quick product demo: <a href="https://www.loom.com/share/c0ce8ab860c044c586c13a24b6c9b391?sid=b7b4e23c-5223-4aad-ae08-b5c704d45aad" rel="nofollow">https://www.loom.com/share/c0ce8ab860c044c586c13a24b6c9b391?...</a><p>Marketers always say that half their spend will be wasted - they just don’t know which half. Real-world experiments help, but they’re too slow and expensive to run at scale. So, we’re building simulations that let you test rapidly and cheaply to find the best version of your message.<p>How it works:<p>- We create AI personas based on real-world data from actual individuals, collected from publicly available social media profiles and web sources.<p>- For each audience, we retrieve relevant personas from our database and map them out on an interactive social network graph, which is designed to replicate patterns of social influence.<p>- Once you’ve drafted your message, each experiment runs a multi-agent simulation where the personas react to your content and interact with each other - these take 30s to 2 minutes to run. Then, we then surface results and insights to help you improve your messaging.<p>Our two biggest challenges are accuracy and UI. We’ve tested our performance at predicting how LinkedIn posts perform, and the initial results have been promising. Our model has an R2 of 0.78 and we’ve found that “message spread” in our simulations is the single most important predictor of actual engagements when looking at posts made by the same authors. But there’s a long way to go in generalising these simulations to other contexts, and finding ground truth data for evals. We have some more info on accuracy here: <a href="https://societies.io/#accuracy">https://societies.io/#accuracy</a><p>In terms of UI, our biggest challenge is figuring out whether the ‘experiment’ form factor is attractive to users. We’ve deliberately focused on this (over AI surveys) as experiments leverage our expertise in social influence and how ideas spread between personas.<p>James and I are both behavioral scientists by training but took different paths to get here. I helped businesses run A/B tests to boost sales and retention. Meanwhile, James became a data scientist and, in his spare time, hooked together 33,000 LLM chatbots and wrote a paper about it (<a href="https://bpspsychub.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/bjop.12764" rel="nofollow">https://bpspsychub.onlinelibrary.wiley.com/doi/pdfdirect/10....</a>). He showed me the simulations and we decided to make a startup out of it.<p>Pricing: Artificial Societies is free to try. New users get 3 free credits and then a two week free trial. Pro accounts get unlimited simulations for $40/month. We’re planning on introducing teams later, and enterprise pricing for custom-built audiences.<p>We’d love you to give the tool a try and share your thoughts!