prompt engineering post small edits

lilianweng · Mar 20, 2023 · be66057 · be66057
1 parent 0986539
commit be66057
Show file tree

Hide file tree

Showing 16 changed files with 28 additions and 41 deletions.
diff --git a/index.html b/index.html
@@ -267,8 +267,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/index.json b/index.json
diff --git a/index.xml b/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>

diff --git a/posts/2023-03-15-prompt-engineering/index.html b/posts/2023-03-15-prompt-engineering/index.html
diff --git a/posts/index.html b/posts/index.html
@@ -202,8 +202,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/posts/index.xml b/posts/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>

diff --git a/tags/alignment/index.html b/tags/alignment/index.html
@@ -187,8 +187,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/tags/alignment/index.xml b/tags/alignment/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>

diff --git a/tags/language-model/index.html b/tags/language-model/index.html
@@ -187,8 +187,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/tags/language-model/index.xml b/tags/language-model/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>

diff --git a/tags/nlp/index.html b/tags/nlp/index.html
@@ -187,8 +187,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/tags/nlp/index.xml b/tags/nlp/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>

diff --git a/tags/prompting/index.html b/tags/prompting/index.html
@@ -187,8 +187,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/tags/prompting/index.xml b/tags/prompting/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
   </channel>

diff --git a/tags/steerability/index.html b/tags/steerability/index.html
@@ -187,8 +187,7 @@ <h2>Prompt Engineering
   </header>
   <section class="entry-content">
     <p>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering....</p>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models....</p>
   </section>
   <footer class="entry-footer"><span title='2023-03-15 00:00:00 +0000 UTC'>March 15, 2023</span>&nbsp;·&nbsp;21 min&nbsp;·&nbsp;Lilian Weng</footer>
   <a class="entry-link" aria-label="post link to Prompt Engineering" href="https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/"></a>

diff --git a/tags/steerability/index.xml b/tags/steerability/index.xml
@@ -14,8 +14,7 @@
 
       <guid>https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/</guid>
       <description>Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics.
-Useful resources:
- OpenAI Cookbook has many in-depth examples for how to utilize LLM efficiently. Prompt Engineering Guide repo contains a pretty comprehensive collection of education materials on prompt engineering.</description>
+This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models.</description>
     </item>
 
     <item>