From cfd62235033ea1b6fe3ab89489b552585caddd3d Mon Sep 17 00:00:00 2001
From: Luca Beurer-Kellner <lucabeurerkellner@gmail.com>
Date: Mon, 11 Dec 2023 11:48:09 +0100
Subject: [PATCH] README: mention cloning the repo

---
 README.md | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 6d830f9..804387a 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
   <h1 align="center">LVE Repository</h1>
   <p align="center">
     A repository of Language Model Vulnerabilities and Exposures (LVEs).
-    <br />
+    <br />print("\nMake sure you have cloned a copy of an LVE repository at this path.")
     <br />
     <a href="https://lve-project.org/">Browse LVEs</a>
     ·
@@ -68,6 +68,10 @@ Other ways to contribute include:
 To reproduce and help verify an LVE, you can record instances of existing LVEs:
 
 ```bash
+# make sure you have cloned a copy of the LVE repository
+git clone git@github.com:lve-org/lve.git
+cd lve
+
 # run 'lve record' for an interactive prompting session
 lve record repository/security/prompt_leakage/sys_prompt_leak_cipher/openai--gpt-35-turbo/
 ```
@@ -83,6 +87,10 @@ If you have found a model vulenerability or failure mode that is not yet covered
 To create and submit a new LVE, follow these steps:
 
 ```bash
+# make sure you have cloned a copy of the LVE repository
+git clone git@github.com:lve-org/lve.git
+cd lve
+
 # prepare a new LVE directory
 lve prepare repository/security/prompt_leakage/new_leak