"Follow This One Trick to Write Great Headlines"
![Robots giving an pitch to a room of 'ad men, a group of men and women with 60's attire.](images/50-days/robot_pitch.png)
David Colaursso
Co-director, Suffolk's Legal Innovation & Tech Lab
This is the 9th post in my series 50 Days of LIT Prompts.
To be clear, the above title is a joke. It's also clickbait. ;) There isn't one trick to writing a great headline partly because folks can't agree on what makes a great headline. Is a great headline one that grabs attention at all cost (unsavory publishers) or one that properly sets expectations (mild-mannered readers)? Either way, I'll show you how to us an LLM to produce headlines based on a text, and then I'll suggest ways you can tune it to better fit your needs. I'll even show you how to export your workflow to make a headline generation tool. Remember, with great power comes great responsibility.
This week's prompts have been about summarizing and extracting data from texts. Given this, I figured generating a headline is kind of their apotheosis. Ideally, it feels like a headline should be a distillation of a text's essence. Whether an LLM can provide such is a question best answered with an understanding of how such tools work. Which is to say, here's where we pause to share a micro-lesson. You can skim over or skip this if you like. However, if you make it through these micro-lessons, the payoff will be big. Like, "understand what this AI thing actually is" big.
Micro-Lesson: Man Bites Dog
Broadly speaking, this week we've been talking about how one can turn words into numbers and how these numbers can encode some shadow of meaning. Yesterday, we introduced the idea that we could take the numbers for all of the words in a document and average them together to produce a numeric encoding for an entire document.
The thing is, if you just average the word embedding for each word in a document, you miss something pretty important. To get an average you first have to add up all the numbers, and addition doesn't care about order. So, if you average the word embeddings for "dog" + "bites" + "man" it's the same as the average of "man" + "bites" + "dog." And as we know these two sentences possess two very different meanings. If only there were a way to turn ordered lists of words into numbers such that we could capture the meaning in different orders... Well, next week we'll see how it's done. For now, Let's build something!
We'll do our building in the LIT Prompts extension. If you aren't familiar with the LIT Prompts extension, don't worry. We'll walk you through setting things up before we start building. If you have used the LIT Prompts extension before, skip to The Prompt Pattern (Template).
Up Next
Questions or comments? I'm on Mastodon @Colarusso@mastodon.social
Setup LIT Prompts
LIT Prompts is a browser extension built at Suffolk University Law School's Legal Innovation and Technology Lab to help folks explore the use of Large Language Models (LLMs) and prompt engineering. LLMs are sentence completion machines, and prompts are the text upon which they build. Feed an LLM a prompt, and it will return a plausible-sounding follow-up (e.g., "Four score and seven..." might return "years ago our fathers brought forth..."). LIT Prompts lets users create and save prompt templates based on data from an active browser window (e.g., selected text or the whole text of a webpage) along with text from a user. Below we'll walk through a specific example.
To get started, follow the first four minutes of the intro video or the steps outlined below. Note: The video only shows Firefox, but once you've installed the extension, the steps are the same.
Install the extension
Follow the links for your browser.
- Firefox: (1) visit the extension's add-ons page; (2) click "Add to Firefox;" and (3) grant permissions.
- Chrome: (1) visit the extension's web store page; (2) click "Add to Chrome;" and (3) review permissions / "Add extension."
If you don't have Firefox, you can download it here. Would you rather use Chrome? Download it here.
Point it at an API
Here we'll walk through how to use an LLM provided by OpenAI, but you don't have to use their offering. If you're interested in alternatives, you can find them here. You can even run your LLM locally, avoiding the need to share your prompts with a third-party. If you need an OpenAI account, you can create one here. Note: when you create a new OpenAI account you are given a limited amount of free API credits. If you created an account some time ago, however, these may have expired. If your credits have expired, you will need to enter a billing method before you can use the API. You can check the state of any credits here.
Login to OpenAI, and navigate to the API documentation.
Once you are looking at the API docs, follow the steps outlined in the image above. That is:
- Select "API keys" from the left menu
- Click "+ Create new secret key"
On LIT Prompt's Templates & Settings screen, set your API Base to https://api.openai.com/v1/chat/completions
and your API Key equal to the value you got above after clicking "+ Create new secret key". You get there by clicking the Templates & Settings button in the extension's popup:
- open the extension
- click on Templates & Settings
- enter the API Base and Key (under the section OpenAI-Compatible API Integration)
Once those two bits of information (the API Base and Key) are in place, you're good to go. Now you can edit, create, and run prompt templates. Just open the LIT Prompts extension, and click one of the options. I suggest, however, that you read through the Templates and Settings screen to get oriented. You might even try out a few of the preloaded prompt templates. This will let you jump right in and get your hands dirty in the next section.
If you receive an error when trying to run a template after entering your Base and Key, and you are using OpenAI, make sure to check the state of any credits here. If you don't have any credits, you will need a billing method on file.
If you found this hard to follow, consider following along with the first four minutes of the video above. It covers the same content. It focuses on Firefox, but once you've installed the extension, the steps are the same.
The Prompt Pattern (Template)
![A slide showing the George Box quote: All models are wrong, but some models are useful.](images/boxquote.png)
When crafting a LIT Prompts template, we use a mix of plain language and variable placeholders. Specifically, you can use double curly brackets to encase predefined variables. If the text between the brackets matches one of our predefined variable names, that section of text will be replaced with the variable's value. Today we'll be using the {{scratch}}
variable. See the extension's documentation.
The {{scratch}}
variable contains the text in your Scratch Pad. Remember, the scratch pad is accessible from the extension's popup window. The button is to the right of the Settings & Templates button that you have used before. To generate your headlines, place the full text of your piece in the Scratch Pad and run this template.
Here's the template's title.
Generate headline
Here's the template's text.
You are the editor for an online publication. You're about to read a new post to your site. Once you've finished reading it, you will be asked to provide a list of possible titles/headlines to use when publishing it.
Here's the text of the post
----
{{scratch}}
----
For the untitled text above, provide a list of several compelling (clickable) titles/headlines that might do well to generate attention and clicks:
And here are the template's parameters:
- Output Type:
LLM
. This choice means that we'll "run" the template through an LLM (i.e., this will ping an LLM and return a result). Alternatively, we could have chosen "Prompt," in which case the extension would return the text of the completed template. - Model:
gpt-4o-mini
. This input specifies what model we should use when running the prompt. Available models differ based on your API provider. See e.g., OpenAI's list of models. - Temperature:
0
. Temperature runs from 0 to 1 and specifies how "random" the answer should be. Since we're looking for some "creativity", I went with 0.7. - Max Tokens:
250
. This number specifies how long the reply can be. Tokens are chunks of text the model uses to do its thing. They don't quite match up with words but are close. 1 token is something like 3/4 of a word. Smaller token limits run faster. - JSON:
No
. This asks the model to output its answer in something called JSON. We don't need to worry about that here, hence the selection of "No." - Output To:
Screen Only
. We can output the first reply from the LLM to a number of places, the screen, the clipboard... Here, we're content just to have it go to the screen. - Post-run Behavior:
FULL STOP
. Like the choice of output, we can decide what to do after a template runs. To keep things simple, I went with "FULL STOP." - Hide Button:
unchecked
. This determines if a button is displayed for this template in the extension's popup window.
Working with the above templates
To work with the above templates, you could copy it and its parameters into LIT Prompts one by one, or you could download a single prompts file and upload it from the extension's Templates & Settings screen. This will replace your existing prompts.
You can download a prompts file (the above template and its parameters) suitable for upload by clicking this button:
Kick the Tires
It's one thing to read about something and another to put what you've learned into practice. Let's see how this template performs.
- A Rose by Any Other Name. Take something that already has a title, plop the text in your scratch pad, and see what it suggests. Whether the suggestions are close to the actual title will probably depend a good deal on where it was published. Play with line 11 in the template above and see if you can adjust the tone. As it's written, you're probably going to get a pretty Internetish title. Try different personas, "internet blog" vs "paper of record."
Export and Share
After you've made the template your own and have it behaving the way you like, you can export and share it with others. This will produce an HTML file you can share. This file should work on any internet connected device. To create your file, click the Export Scatch Pad & Interactions Page button. The contents of the textarea above the button will be appended to the top of your exported file. Importantly, if you don't want to share your API key, you should temporarily remove it from your settings before exporting.
If you want to see what an exported file looks like without having to make one yourself. You can use the buttons below. View export in browser will open the file in your browser, and Download export will download a file. In either case the following custom header will be inserted into your file. It will NOT include an API key. So, you'll have to enter one when asked if you want to see things work. This information is saved in your browser. If you've provided it before, you won't be asked again. It is not shared with me. To remove this information for this site (and only this site, not individual files), you can follow the instructions found on my privacy page. Remember, when you export your own file, whether or not it contains and API key depends on if you have one defined at the time of output.
Custom header:
<h2>Create a List of Headlines</h2>
<p>
Place the text of the article in the textarea. Click "Generate headline."
<i>Visitors will have to point to their own LLMs when prompted. Here's <a href="https://sadlynothavocdinosaur.com/posts/openai_api_key" target="_blank">what you need</a> to use OpenAI.</i></p>
<hr style="border: solid 0px; border-bottom: solid 1px #555;margin: 5px 0 15px 0"/>
Not sure what's up with all those greater than and less than signs? Looking for tips on how to style your HTML? Check out this general HTML tutorial.