TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: How are you making sure LLM provider doesn't ban you from user prompts?

1 点作者 spxneo大约 1 年前
One of my worry is my users submitting malicious prompts and getting my account banned for everybody.<p>How do you ensure that the prompt doesn&#x27;t violate LLM providers Terms of Service?<p>Does this mean we have to call the text gen API twice? First to analyze and ask if it violates TOS and then second to finally fulfill the user&#x27;s requests?<p>Are there any other solutions that is working for you?

3 条评论

dragonwriter大约 1 年前
&gt; Does this mean we have to call the text gen API twice? First to analyze and ask if it violates TOS and then second to finally fulfill the user&#x27;s requests?<p>This just means the user generated content gets sent to the API once with different framing (risking a ban or strike or whatever) and if it doesn&#x27;t trigger your detection gets sent again with the normal framing (giving another chance at a provider ban, strike, etc.)<p>Seems like that would just accelerate your ban by having you send each potentially-violating interaction twice, with slightly different context, giving more chances of a violation and possibly doubling violations for some content.<p>You can probably do better at reducing your risk by running a local classifier (or a comparatively small local LLM) as your trouble detector, before deciding to send a request to the backend, though validating the trouble detector setup may be problematic.
评论 #40293726 未加载
mepian大约 1 年前
You can use a local LLM like Llama 3, they&#x27;re pretty good. Zero risk of getting banned by them.
JojoFatsani大约 1 年前
Wouldn’t the “check” api call be enough to violate TOC?
评论 #40293729 未加载