Series

Artificial Intelligence

22 posts

Dark abstract digital artwork of a glowing layered server-like structure on a neon grid with floating panels, purple mountains, and a retro sunset; subtle retrowave style

The CMS is dead. Long live the CMS.

I saw a post on LinkedIn the other day from a self-proclaimed 20 year agency veteran of WordPress saying that was it, they’re moving the entire agency off of WordPress and onto AI. Now, because I, too, am a 20 year veteran of WordPress, this kind of story catches my attention. He posted that they […]

Read more →
Person working at a laptop in a neon-lit synthwave room, seen from behind, with purple headphones, a cluttered desk, and a glowing retro sunset cityscape outside the window — image created by DALL·E via ChatGPT

Disclosing AI use

This is based on a thread that I posted to Bluesky that I decided to keep here for posterity. If you want to discuss on Bluesky, follow me at @jazzsequence.com and let’s chat. Let’s talk about AI. I’ve been using it a lot recently. It’s not that I don’t see or care about the environmental […]

Read more →
Futuristic digital illustration of a friendly AI assistant connected to a glowing Model Context Protocol interface, analyzing and interacting with a WordPress-powered website dashboard filled with code snippets, UI components, and data panels, with neon data streams linking the AI to the site against a nighttime cityscape of servers and networks — image created by DALL·E via ChatGPT.

Teaching an AI to Read My Website (Over MCP)

For the last couple weeks, I’ve been building a headless Next.js frontend for this site — a project I’ve been calling jazz-nextjs. The idea is straightforward enough: keep WordPress as the content management layer (where I actually like writing) while serving the public-facing site through a modern React frontend hosted on Pantheon’s Next.js infrastructure. What’s […]

Read more →
Gemini AI-generated image of an arcane gate under an ancient house that opens into a weird cosmic abyss

The Lovecraft Test, Gemini 2.5-pro

At the same time as I was fighting with GPT-5 to give me the thing I actually wanted, I also used the Gemini app and the access I have to pro-level Gemini models to do the Lovecraft test with 2.5-pro. Previously, I had only tested with Flash-2.0, so, not only should this be a more […]

Read more →
In this atmospheric painting, a pale man with hollowed cheeks and dark, wavy hair holds a woman with glowing sea-green eyes on a misty shore at night. While the moonlit scene is shadowed by turbulent waves and looming monstrous figures, their intense connection stands out, as the couple's contrasting emotions add a layer of mystery to the eerily luminous coastline.

The Lovecraft Test, GPT-5

GPT-5 is out now and I’ve only had a couple occasions to interact with it directly. So, I thought it was time to run it through the Lovecraft test. ChatGPT has adopted this quirk of late where, when it’s done answering your question or responding to your prompt, it says something to the effect of […]

Read more →
The Lovecraft Test, Gemini

The Lovecraft Test, Gemini

I’ve been sitting on this one for longer than I should have (and then, obviously, forgetting entirely about it). After putting DeepSeek through the ropes for my Lovecraft test, I decided to try Google’s Gemini. I haven’t used Gemini much, although I have used NotebookLLM which is based on Gemini, and I think it generally […]

Read more →
A Lovecraftian coastal scene under a gibbous moon, depicting Alden Marsh and Thalassa standing on the edge of crumbling cliffs overlooking a raging abyss. Thalassa, a mysterious sea creature draped in seafoam and kelp, has bioluminescent veins visible beneath her translucent skin and long, ink-black hair flowing like water. Alden, a scholarly man, holds her webbed hand as the villagers, pale and slit-eyed, approach with hooks and chains. Below, the ocean churns into a maelstrom, and a colossal shadow stirs beneath the waves. The sky is filled with storm clouds and eerie, phosphorescent light from the sunken ziggurat in the depths.

The Lovecraft Test, DeepSeek Edition

The stupidly big news in LLMs right now is that DeepSeek, a LLM built by a small Chinese team that was released a couple weeks ago, performs as well as, if not better than larger, more sophisticated (at least in terms of the dollars and hardware thrown at it) models by OpenAI and Anthropic (Claude) […]

Read more →
A dramatic cinematic scene inspired by H.P. Lovecraft's style, set on a stormy cliffside under a pale, glowing moon. A humanoid figure, ethereal and alien, with shimmering fish-scale-like attire and silver hair with tendrils, stands at the edge of a cliff overlooking a tumultuous ocean. The waves crash violently against jagged rocks, and enormous, shadowy, incomprehensible forms rise from the sea, illuminated faintly by eerie green lights. The sky is filled with dark storm clouds and lightning streaks, creating a haunting, otherworldly atmosphere. The perspective is cinematic, with the figure in the foreground gazing out at the titanic, alien shapes in the distance. The color palette is dark, with shades of green, black, and silver dominating. This image is presented in a wide 16:9 format, as if it were a still from a dramatic horror film.

The H.P. Lovecraft Test, round 3

I’ve run this test twice already and I figured it was probably about time to try it again. If you’ve been reading my AI posts (which is all I post anymore), you may remember past incarnations of what I like to call The Lovecraft Test. I ran it very early on with ChatGPT when it […]

Read more →
Aging an AI-generated character

Aging an AI-generated character

Historically, prompting ChatGPT (or DALL-E through ChatGPT) for variations or subtle modifications of a single image results in a sort of image degeneration. Not only does the image not get reproduced with the slight variations, but it gets further and further away from what you originally requested. This is something that has been noted on […]

Read more →
Rick Astley Ten Ways

Rick Astley Ten Ways

Lately, I’ve been playing a lot with Suno. Suno is an AI that makes music based on your prompts. It’s actually pretty good at it, too. It lacks the ability to edit songs, and the songs it creates will always be based on some formulaic foundation, but so much of popular music is that it […]

Read more →
DALL-E prompt: Create a surreal and glitchy scene that visually represents the concept of an AI being disrupted by a simple, repetitive input of 'a a a a'. The image should feature a digital landscape dominated by a large, central figure symbolizing the AI, with its surface breaking apart or distorting intensely in areas where the glitch is most concentrated. Surround this figure with streams of binary code and digital elements that suddenly scatter or warp into chaotic patterns around the 'a a a a' input, which appears prominently in the scene as glowing, floating characters that emit a disruptive energy. The environment should embody a stark contrast between the orderly flow of digital information and the sudden, disordered, and colorful glitch effects caused by the repetitive input. Include visual cues like broken pixels, color aberrations, and erratic digital noise to emphasize the glitchy and unpredictable nature of the bug, showcasing the AI's struggle to process the input logically. This portrayal should vividly convey the idea of an AI encountering a bug that leads to bizarre and unexpected outputs, highlighting the theme of technology behaving in unpredictable ways.

File under: AIs doing Weird AI Shit

Today, a friend of mine who’s largely the person I talk about weird AI shit with mentioned this: “my ai guy” has mentioned several times that sending a bunch of “a a a a” to chatgpt can sometimes make it output training data.. I’m always game to try new weird shit with AI chatbots. This […]

Read more →
Artificial Intelligence | jazzsequence | jazzsequence