diff --git a/examples/main/main.cpp b/examples/main/main.cpp
index 6f312b38b..3cb79b79e 100644
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@@ -211,7 +211,6 @@ int main(int argc, char ** argv) {
     int guidance_offset = 0;
     int original_prompt_len = 0;
     if (ctx_guidance) {
-        params.cfg_negative_prompt.insert(0, 1, ' ');
         guidance_inp = ::llama_tokenize(ctx_guidance, params.cfg_negative_prompt, add_bos);
 
         std::vector<llama_token> original_inp = ::llama_tokenize(ctx, params.prompt, add_bos);
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 615801fe5..e13bf76e6 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -286,7 +286,6 @@ struct llama_server_context
                     std::vector<llama_token> p;
                     if (first)
                     {
-                        s.insert(0, 1, ' '); // add a space if it's the first
                         p = ::llama_tokenize(ctx, s, add_bos);
                         first = false;
                     }
@@ -309,7 +308,6 @@ struct llama_server_context
         else
         {
             auto s = json_prompt.template get<std::string>();
-            s.insert(0, 1, ' '); // always add a first space
             prompt_tokens = ::llama_tokenize(ctx, s, add_bos);
         }