Using Generative AI to Check for Spam

/ / No Comments
A few days ago I wrote up an exploration I did in Spam APIs, "Spam APIs in 2024". After working on those demos and writing up my findings, I thought it might be interesting to see how a generative AI tool, like Googele’s Gemini would handle such a task. Initial Tests # So – once again – I’m a broken record on this – but I fired up AI Studio first to give it some quick tests. I began with this prompt: Given the following text, rate how much it appears to be spam by giving it a score between 1 and 10, with 10 being the most likely the content is spam. For my first test, I used a ‘bad’ sample (see my last post for a full listing of my sample data): 💪... more →
Posted in: JavaScript Tagged with: , , ,

Using PDF Content with Google Gemini

/ / No Comments
Back in February Google announced Gemini 1.5, their latest, most powerful language model, and while access has been open via AI Studio, API access has only been available in the past few days. I thought I’d try out the new model and specifically make use of the larger context window to do prompts on PDF documents. I discussed something similar earlier this year(("Using AI and PDF Services to Automate Document Summaries")[https://www.raymondcamden.com/2024/01/08/using-ai-and-pdf-services-to-automate-document-summaries]) which made use of Diffbot, so I thought it would be interesting to build a similar experience with the Gemini API. At a high level, it’s not too difficult: Begin... more →
Posted in: JavaScript Tagged with: , , ,

Using Intl.RelativeTimeFormat for Localized Relative Timings

/ / No Comments
I’ve been singing the praises of the web platform’s Intl object for years now, but it still continues to impress me. While I’ve seen it before, today I came across the RelativeTimeFormat API which looks absolutely fabulous. I played with it a bit and thought I’d share some tips. The Basics # The RelativeTimeFormat API works like so: Given a locale… Given a difference (in either a positive or negative value)… And given a unit of time, like ‘hour’ (or ‘hours’) Report the difference in the user’s desired language. So for example: 3 and day, "in 3 days" -1 and day, "one day ago" 18 and hour, "in 18 hours" Also,... more →
Posted in: JavaScript Tagged with: , , , ,

Using Generative AI to Organize Video Game Screenshots

/ / No Comments
Way back in January (remember January), I wrote a blog post describing how to use gen ai to improve image filenames. This worked by uploading the image to Google Gemini, asking for a short description, and using that description for a new filename. Recently I was thinking about that demo and was curious how well it would work for video games. As always, I did a few quick tests in Google AI Studio. I did some quick Googling for various games and screenshots, and the results were pretty impressive. Here are three mostly modern examples: And here’s a first failure, identifying this as Final Fantasy 14, not 16. It did well for one really old game, although to be fair the name is in the picture: Although... more →
Posted in: JavaScript Tagged with: , , , , ,

Using Generative AI as Your Content Assistant

/ / No Comments
Last week I had the honor of presenting one at TheJam.dev. This was my first presentation on generative AI and I got to share what I thought was an interesting use case – helping with the writing process. Now to be clear, I don’t mean using GenAI to write blog posts, that would be a horrible idea. (IMO!) Instead, I looked at how it could help with some of the process. Let me back up a bit and give some background. I’ve been a fan of John Birmingham for many years now. He’s an author who writes in the military/sci-fi/etc genre and has some pretty fascinating ideas. I initially discovered him via his "Axis of Time" trilogy which dealt with the idea of a modern... more →
Posted in: JavaScript Tagged with: , , ,

Using AI to Age OSM Maps

/ / No Comments
The screenshot above, from the SynthMap Demo, shows a side-by-side view of an Open Street Map and an AI generated map of the same OSM data changed to look like a 19th Century era Ordnance Survey map. This Victorian cosplaying map (on the right) was developed by Zekun Li, of the University of Minnesota, who trained an AI to transform OpenStreetMap data into images that resemble the Maps Mania… more →
Posted in: Interactive Maps Tagged with: ,

Using Generative AI to Improve Image Filenames

/ / No Comments
Last night I had an interesting thought. Many times I work with images that have vague filenames. For example, screenshot_1_24_12_23.jpg. Given that there are many APIs out there that can look at an image and provide a summary, what if we could use that to provide a better file name based on the content of the image? Here’s what I was able to find. As always, I began by prototyping in Google AI Studio. I apologize for stating this in basically every post on the topic, but I really want to stress how useful that is for development. I used a very simple prompt: Write a one sentence short summary of this image. The sentence should be no more than five words. And then did a quick test: If... more →
Posted in: JavaScript Tagged with: , , , ,

Using GenAI to Classify an Image as a Photo, Screenshot, or Meme

/ / No Comments
File this under the "I wasn’t sure if it would work and it did" category. Recently, a friend on Facebook wondered if there was some way to take a collection of photos and figure out which were ‘real’ photos versus memes. I thought it could possibly be a good exercise for GenAI and decided to take a shot at it. As usual, I opened up Google’s AI Studio and did a few initial tests: I then simply removed that image and pasted more info to test. From what I could see, it worked well enough. I then took the source code from AI Studio and began working. The Code # First, I grabbed some pictures from my collection, eleven of them, and tried to get a few photos, memes,... more →
Posted in: JavaScript Tagged with: , , , , , ,
1 2 3 4 5 6 … 9