How-to11月16日 00:17

用 AI 快速审查 100 页服务条款的方法

Gergely Orosz@GergelyOrosz

Post

View the post

Why we picked it

GergelyOrosz 分享了他点同意按钮前的习惯：把 100 页的服务条款扔给 AI，只问一句"有什么奇怪的条款吗"。一句话提示词就能揪出自动续费、数据收集这类坑，不用自己啃几百页法律文本，谁订阅服务多谁就该学。

GergelyOrosz 分享了一个 AI 实用场景：遇到 100 页长的服务条款（TOS），普通用户几乎不可能读完，但他需要在点击同意前确认风险。

Body

他的做法是把整份条款粘贴给 AI，然后只问一个问题："anything weird in this?"（这里面有什么奇怪的条款吗？）。这个提示词让 AI 专注于找出异常条款，比如自动续费、数据收集范围、仲裁条款等，而不是泛泛总结全文。

适用范围包括注册每月 10 美元的订阅服务、玩游戏前接受协议等日常场景。对于没有法务团队的个人用户，这是一种低成本审查合同的替代方案。

Original · Gergely Orosz

One usage for AI: for these 100-page-long terms-and-service agreements you NEED to agree to, to eg play the game / sign up for a $10/month service and can never ever ever read as a regular person:

I paste into AI and ask: "anything weird in this?"

Before hitting "agree"

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include prompt engineering, GergelyOrosz.

Source attribution: curated from Gergely Orosz (@GergelyOrosz).

#prompt engineering #GergelyOrosz

Keep reading

Recent stories with the same tag or section

How-to BuildersMulti-sourceSelected22:07

Anthropic publishes reference architecture for always-on agents

The non-obvious insight is that "always-on" is an illusion built from short, stateless runs stitched together by queues and timers, not a long-lived process. Developers building bots or proactive assistants can copy this five-component pattern directly instead of inventing their own persistence layer. Teams in ASEAN and China shipping chatbot products similar to Grok Bot will find the loop design applicable regardless of which model they serve.

#Claude #agents #event-driven #Memory

Event

Viking@vikingmuteSource

How-to BuildersOfficialSelected20:19

Positional Embeddings in LLMs Explained by Sebastian Raschka

The choice of positional encoding determines how a model extrapolates beyond its trained context window, which directly affects long-context fine-tuning decisions and inference cost trade-offs. Engineers fine-tuning open-source models like Llama, Qwen or DeepSeek can use the included code examples to verify RoPE and YaRN configurations against their own context-length requirements. Those comparing ALiBi-based architectures will find the extrapolation analysis concrete enough to guide model selection.

#RoPE #positional encoding #LLM #ALiBi