🔓 提示駭客攻擊
🟢 防禦措施
🟢 概述
🟢 過濾
🟢 指令防禦
🟢 Post-Prompting
🟢 Random Sequence Enclosure
🟢 Sandwich Defense
🟢 XML Tagging
🟢 獨立的 LLM 評估提示
🟢 其他方法
🟢 進攻措施
🟢 概述
🟢 混淆/令牌走私
🟢 負載分割
🟢 定義的字典攻擊
🟢 虛擬化
🟢 間接注入
🟢 遞迴注入
🟢 程式碼注入
🔨 工具
提示工程 IDE
🟢 Introduction
GPT-3 Playground
Dust
Soaked
Everyprompt
Prompt IDE
PromptTools
PromptSource
PromptChainer
Prompts.ai
Snorkel 🚧
Human Loop
Spellbook 🚧
Kolla Prompt 🚧
Lang Chain
OpenPrompt
OpenAI DALLE IDE
Dream Studio
Patience
Promptmetheus
PromptSandbox.io
The Forge AI
AnySolve
Conclusion
🔨 工具提示工程 IDESoaked

Soaked

Reading Time: 1 minute
Last updated on August 7, 2024

Sander Schulhoff

Soaked is a prompt engineering IDE that focuses on visual prompt chaining with a graphical interface. It is currently in beta, but active development has ceased.

Features

Soaked provides a graphical interface for chaining prompts together, where you can easily see how different components flow together. It also provides a lower level prompt view with the option to generate multiple completions at once. It also provides a cost estimate for completions. It currently supports GPT3 and requires an OpenAI key to use.

Sander Schulhoff

Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.