<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI | SUMAN</title><link>https://suman.netlify.app/category/ai/</link><atom:link href="https://suman.netlify.app/category/ai/index.xml" rel="self" type="application/rss+xml"/><description>AI</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 10 May 2023 00:00:00 +0000</lastBuildDate><image><url>https://suman.netlify.app/media/icon_hu_1f8f41e4ad59c1b5.png</url><title>AI</title><link>https://suman.netlify.app/category/ai/</link></image><item><title>AI Prompt Engineering</title><link>https://suman.netlify.app/post/ai_prompt_engineering/</link><pubDate>Wed, 10 May 2023 00:00:00 +0000</pubDate><guid>https://suman.netlify.app/post/ai_prompt_engineering/</guid><description>&lt;h3 id="1-start-with-an-instruction">1. &lt;a href="https://platform.openai.com/docs/quickstart/start-with-an-instruction" target="_blank" rel="noopener">Start with an instruction&lt;/a>&lt;/h3>
&lt;p>Try making your instruction more specific. e.g: Suggest one name for a black horse.&lt;/p>
&lt;h3 id="2-add-some-examples">2. &lt;a href="https://platform.openai.com/docs/quickstart/add-some-examples" target="_blank" rel="noopener">Add some examples&lt;/a>&lt;/h3>
&lt;p>It’s helpful to both show and tell the model what you want. Adding examples to your prompt can help communicate patterns or nuances. Try submitting this prompt which includes a couple examples.&lt;/p>
&lt;div class="highlight">&lt;pre tabindex="0" class="chroma">&lt;code class="language-fallback" data-lang="fallback">&lt;span class="line">&lt;span class="cl">Suggest three names for an animal that is a superhero.
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Animal: Cat
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Names: Captain Sharpclaw, Agent Fluffball, The Incredible Feline
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Animal: Dog
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Names: Ruff the Protector, Wonder Canine, Sir Barks-a-Lot
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Animal: Horse
&lt;/span>&lt;/span>&lt;span class="line">&lt;span class="cl">Names:
&lt;/span>&lt;/span>&lt;/code>&lt;/pre>&lt;/div>&lt;p>Nice! Adding examples of the output we’d expect for a given input helped the model provide the types of names we were looking for.&lt;/p>
&lt;h3 id="3-adjust-your-settings">3. Adjust your settings&lt;/h3>
&lt;p>Prompt design isn’t the only tool you have at your disposal. You can also control completions by adjusting your settings. One of the most important settings is called temperature.&lt;/p>
&lt;p>You may have noticed that if you submitted the same prompt multiple times in the examples above, the model would always return identical or very similar completions. This is because your temperature was set to 0.&lt;/p>
&lt;p>Try re-submitting the same prompt a few times with temperature set to 1.&lt;/p></description></item></channel></rss>