独立开发者对抗Token欺诈的6种模式与防御体系
How I fight token fraud as a solo founder
独立开发者做AI产品的必读避坑指南。不仅列出了具体的攻击手法,还给出了从关闭免费试用到具体技术栈(Vercel/Jev/Stripe)的完整防御清单,直接可抄作业。
Today I’m walking you through a problem that has cost me tens of thousands of dollars over the past year and eaten almost all of my engineering energy: token fraud. I’m the solo founder of ChatPRD, a bootstrapped AI platform for product managers, and fraudsters have been farming our free trials, reselling promo codes, wrapping the product in relays, and installing a custom MCP that ran as a 24/7 compute worker. I’ll walk through the six abuse patterns I’ve seen, the business and technical controls I put in place, the Jev loop that classifies fraud in real time, and why I finally killed free trials for good. If you sell AI, you sell compute.
今天我要带大家了解一个问题:代币欺诈。在过去一年里,这个问题让我损失了数万美元,并几乎耗尽了我的工程精力。我是 ChatPRD 的独立创始人,这是一家为产品经理打造的自举型 AI 平台。欺诈者一直在批量使用我们的免费试用、转售促销码、通过中继包装产品,并安装了一个作为 24/7 计算节点运行的自定义 MCP(Model Context Protocol)。我将详细介绍我所看到的六种滥用模式、我部署的业务和技术控制措施、用于实时分类欺诈的 Jev 循环,以及我为何最终彻底取消了免费试用。如果你销售 AI,你就是在销售算力。
Listen or watch on YouTube, Spotify, or Apple Podcasts
在 YouTube、Spotify 或 Apple Podcasts 上收听或观看
What you’ll learn:
你将学到:
- What token fraud is and why AI SaaS is uniquely exposed
- The six attack patterns I’ve seen at ChatPRD
- Why I finally turned off free trials for good
- The Roblox and Fortnite maps I accidentally funded
- Business controls that actually slow fraud down
- How I use Jev to classify fraud in real time
- Why your AI support desk can become an attack vector
- What “if you sell AI, you sell compute” actually means
- 什么是代币欺诈,以及为什么 AI SaaS 面临独特的暴露风险
- 我在 ChatPRD 看到的六种攻击模式
- 我为何最终彻底关闭了免费试用
- 我不小心资助的 Roblox 和 Fortnite 地图
- 真正能减缓欺诈的业务控制措施
- 我如何使用 Jev 实时分类欺诈
- 为什么你的 AI 支持台可能成为攻击向量
- "如果你销售 AI,你就是在销售算力" 的真正含义
Brought to you by:
由以下机构赞助播出:
WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
WorkOS——让你的应用具备企业级就绪能力,支持 SSO、SCIM、RBAC 等更多功能
Auros—The human network behind AI
Auros——AI 背后的人际网络
In this episode, we cover:
在本集中,我们将涵盖:
(00:00) Token fraud and what it cost me
(00:00) 代币欺诈及其给我的成本
(05:25) Six abuse patterns
(05:25) 六种滥用模式
(11:24) Four kinds of abusers
(11:24) 四类滥用者
(13:45) Business controls
(13:45) 业务控制措施
(21:27) Technical defenses
(21:27) 技术防御
(30:25) Bots that watch the bots
(30:25) 监控机器人的机器人
(35:30) Final takeaways
(35:30) 最终要点
Tools referenced:
提及的工具:
• Stripe Radar: https://stripe.com/radar
• Vercel AI Gateway: https://vercel.com/docs/ai-gateway
• Vercel Bot ID: https://vercel.com/docs/botid
• Vercel Firewall: https://vercel.com/docs/vercel-firewall
• Clerk: https://clerk.com/
• Codex: https://openai.com/codex
• Jev (TypeSafe AI): https://docs.typesafe.ai/introduction/quickstart
Other references:
其他参考资料:
• Claire Vo on token fraud at ChatPRD: https://x.com/clairevo/status/2119985786045227197
• Claire Vo 关于 ChatPRD 中的令牌欺诈问题: https://x.com/clairevo/status/2119985786045227197
• Gareth Wham (Atlassian) on fighting AI abuse: https://x.com/gareth_w/status/2120226872177095114
• Gareth Wham (Atlassian) 关于打击 AI 滥用行为: https://x.com/gareth_w/status/2120226872177095114
• FBI Internet Crime Complaint Center (IC3): https://www.ic3.gov
• FBI 网络犯罪投诉中心 (IC3): https://www.ic3.gov
• Simon Willison’s pelican riding a bicycle: https://simonwillison.net/tags/pelican-riding-a-bicycle/
• Simon Willison 的骑单车鹈鹕: https://simonwillison.net/tags/pelican-riding-a-bicycle/
• How I AI: I’m using Jev more than Opus 5.5 or GPT-6: https://www.youtube.com/watch?v=-KIBgpGA_XI
• How I AI: 我使用 Jev 的频率高于 Opus 5.5 或 GPT-6: https://www.youtube.com/watch?v=-KIBgpGA_XI
Where to find Claire Vo:
如何找到 Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
网站: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].
制作与营销由 https://penname.co/. 如需咨询赞助播客事宜,请发送邮件至 [email protected]。
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力