OKLCH with ChatGPT-5

A universally accessible color triad that works in traditional & perceptually uniform color spaces.

Given the challenge that the Claude chatbot faced in specifying a perceptual uniform Triad color harmony that passes color deficiency, I decided to explore how ChatGPT-5 might handle this request. ChatGPT-5 provided a straightforward solution that works in both traditional and perceptual uniform color spaces. I describe this amazing solution here. Let’s begin our journey by first defining the concepts of a triad color harmony, perceptual uniformity and color deficiency. From there, the ChatGPT-5 color suggestion can be examined in detail.

The Triad Color Harmony:

Color harmony is the process of choosing colors on a color wheel that work well together in the composition of an image. Like concepts in music, these harmonies are based around color combinations on the color wheel that help to provide common guidelines for how color hues will work together. Isaac Newton is credited with creating the color wheel concept when he closed the linear color spectrum into a color circle in the early 1700s. An illustration of his concept is shown below. Artists and color scientists evolved and amplified his concept to include color harmonies.

Two color spaces frequently used to form the basis for color wheels are the traditional Red-Yellow-Blue (RYB) color space used by painters for centuries and the Red-Green-Blue (RGB) color space used for desktop and mobile display devices. The color spaces yield slightly different color harmony results when colorizing a data visualization. Three colors that are evenly spaced, at 120 degrees apart, on the color wheel form a triad color harmony. Below, I show a comparison of the two differing color spaces with a triad color harmony.

In a previous writing, I showed that many Generative AI systems default to defining color harmonies in terms of the RYB color space but when prompted will specify color harmonies in RGB color space. Hue Saturation Value (HSV) and Hue Saturation Lightness (HSL) are two cylindrical coordinate color spaces that build on the RGB color space and are used in computer graphics. For this particular ChatGPT color suggestion, the recommendation steps beyond RYB, RGB, HSV and HSL color spaces to consider perceptual uniformity.

Perceptual Uniformity:

A color space is perceptually uniform if a change of length in any direction X of the color space is perceived by a human as the same change. Unfortunately, Red-Yellow-Blue (RYB) and Red-Green-Blue (RGB) are not perceptually uniform color spaces. A non-uniform perceptual colormap can have stark contrasts when transitioning from one hue to another hue. In data visualization, these contrasts can be mistaken as changes in the data rather than as transitions in the color palette. As a result, many data visualization practitioners prefer to work in the perceptual uniform Lightness, Chroma, and Hue (LCH) or Hue Chroma Luminance (HCL) color space. Below, I show a comparison of non-perceptual uniform and perceptual uniform rainbow colormap example with color wheel diagrams of RGB and HCL color spaces. When the color wheel spectrums are converted to Grayscale, the non-uniformity of RGB and uniformity of HCL color spaces are clearly identifiable. In 2020, an improved perceptual uniform color space, entitled Oklab, was accepted as a World Wide Web consortium standard for use in developing digital content. As of April 25, 2025, Oklab and Oklch are now part of the World Wide Web Consortium’s color standard.

The HCL color space that is within the boundaries of the human visual spectrum is oddly shaped and far from geometrically regular. There are also some mapping challenges between HCL and RGB color spaces. It is possible to select an HCL color that cannot be displayed in RGB format. In a prior writing on Color in a Perceptual Uniform Way: Exploring the Hue Chroma Luminance (HCL) Color Space for Data Visualization, I discussed these issues in detail. Below I show my screenshots from Michael Horvath’s 3D implementations of the RGB gamut (color range) for two polar coordinate versions of HCL: polarized CIE Luv and polarize CIE Lab. These illustrations show the irregular geometric form of HCL that results in the mathematical challenge to locate and map a color triad within this color space.

In 2020, two perceptually uniform color spaces entitled Oklab and Oklch were introduced by Björn Ottosson. This color space was widely accepted and is now supported in Web browsers. As of April 25, 2025, Oklab is now part of the World Wide Web Consortium’s color standard.

It is possible that three colors spaced evenly apart in HCL color spaces will not visually map to a color Triad with a digital design tool like Adobe Color. This is because the color wheels in Adobe Color are based on the RGB and RYB color models that we described earlier.

What are Color Deficiencies?

My earlier UX Collective and Nightingale writings on color highlighted that humans have three types of photoreceptors or cones. Each is sensitive to different parts of the visual spectrum of light to facilitate rich color vision. A color deficiency happens when one or more sets of cones does not function properly. A red cone deficiency is classified as Protanopia. A green cone deficiency is classified as Deuteranopia. A blue cone deficiency is classified as Tritanopia. Software is available that simulates color deficiencies. Color combinations or harmonies selected in a perceptual uniform color space might not pass color deficiency. Below, I show how the HCL color wheel appears to individuals with Protanopia, Deuteranopia and Tritanopia. The Color Blindness Simulator (Coblis) online app was used to create these results.

As a result, it is important to check a perceptual uniform color scheme suggestion for color deficiency.

A Brief Overview of Generative AI Chatbots:

Presently, there are five popular Generative AI chatbots in wide usage: OpenAI’s ChatGPT, Microsoft’s Copilot, Google’s Gemini, Anthropic’s Claude, and DeepSeek.. Users can ask these chatbots for assistance in tasks such as creating emails, essays, and code. For this writing, I am focusing on ChatGPT. The current version, GPT-5, was released on August 7, 2025. The latest version is defined as a unified system that can automatically switch between different models (including a reasoning model and a real-time router) depending on the complexity of a user’s query. Josh Howarth provides an excellent overview of the advances related to ChatGPT-5. The basic versions of these chatbots are free with the premium services costing around $20 per month. DeepSeek is currently providing one level of free access. For this writing, I am using the “free” version of ChatGPT.

Asking OpenAI’s ChatGPT for assistance in specifying a perceptual uniform triad color harmony that passes color deficiency:

As my first step, I asked ChatGPT-5 to “Specify a perceptual uniform Triad color harmony that passes color deficiency with color hex codes”. The chatbot responded with:

A perceptually uniform triadic color harmony involves selecting three colors that are evenly spaced (120° apart) on the color wheel, while maintaining perceptual uniformity (colors appear evenly spaced to the human eye) and color deficiency safety (accessible to people with color vision deficiencies such as Deuteranopia, Protanopia, and Tritanopia).

Here’s a Triadic Color Scheme based on the Oklch color space (perceptually uniform, better than HSL or HSV), adjusted to be colorblind safe:

🎨 Triadic Color Harmony (Colorblind-Safe)

Color Name

Hex Code

Description

Indigo Blue

#3B5BA0

Cool and deep, blue base

Fern Green

#5AA03B

Earthy and fresh, green balance

Flame Orange

#A05A3B

Warm and grounded, orange/red base

✅ Color Deficiency Tested:

• Accessible to: Protanopia, Deuteranopia, Tritanopia
• Tested with: Simulations (e.g., Coblis, color-blind checks)
• Contrast and distinction preserved across all major deficiencies

How to Use:

• These colors maintain contrast and distinctiveness in UIs, charts, infographics, or branding.
• For text on backgrounds, ensure contrast ratio ≥ 4.5:1 (adjust lightness if needed).

Would you like these colors shown in a visual chart or compared against a background for readability?

I responded to ChatGPT-5 with “yes” and received a “visual representation” of the perceptually uniform, colorblind-safe triadic color harmony that I show below with a snapshot of ChatGPT-5’s actual response. I named the color scheme ChatGPT-5 Perceptual Triad.

Verifying ChatGPT-5’s Perceptual Uniform Color Triad:

I decided to use the Adobe Color tool to visually map ChatGPT-5 Perceptual Triad and test it for color deficiency. As a reminder, the three (triad) colors ChatGPT specified are Indigo Blue — Fern Green — Flame Orange. These three elements clearly map and are verified as a triad on the traditional RGB color wheel. Additionally, individuals with Protanopia, Deuteranopia and Tritanopia deficiencies can distinguish between the set of three colors. This is a rather amazing result. As I noted earlier, it is very possible that a color Triad in HCL color spaces might not visually map to a color Triad with a digital design tool like Adobe Color. Using the Oklch perceptually uniform color space, ChatGPT-5 has been able to suggest an accessible perceptual color triad that maps to three colors equally spaced apart in traditional and perceptually uniform color spaces. I show these results below.

Using Viz Palette to Explore the ChatGPT-5 Perceptual Triad for Data Visualization:

Viz Palette is a free color assessment tool for exploring how color scheme designs might appear when applied to generic data visualization examples. As Elijah Meeks notes, it was designed to interface with several data color scheme research efforts. The app also includes color deficiency tests for Red cone (e.g. protanopia) and Green cone (e.g. deuteranopia) color deficiencies since this represents 99% of this population. I have found that entering the color Hex codes of a test color scheme directly into Viz Palette is one of the most effective ways to use the tool. Let’s explore the results for the ChatGPT-5 suggestion.

Below, I show ChatGPT-5 Perceptual Triad applied to the Viz Palette app, The color scheme suggestion passed Viz Palette’s color deficiency tests for protanopia and deuteranopia.

A Recap of ChatGPT-5’s efforts to specify a perceptual uniform Triad color harmony that passes color deficiency:

In the writing, I have explored how ChatGPT-5, a Generative AI chatbot, responds to the request to specify a perceptual uniform Triad color harmony that passes color deficiency. Three colors that are evenly spaced, at 120 degrees apart, on the color wheel form a triad color harmony. A color space is perceptually uniform if a change of length in any direction X of the color space is perceived by a human as the same change. Non-uniform perceptual color spaces like RGB and RYB can have stark contrasts when transitioning from one hue to another hue. In data visualization, these contrasts can be mistaken as changes in the data rather than as transitions in the color palette. As a result, many data visualization practitioners prefer to work in the perceptual uniform Lightness, Chroma, and Hue (LCH) or Hue Chroma Luminance (HCL) color space. A key issue with working in HCL space is that it is geometrically irregular and finding a color triad becomes a challenge to locate. ChatGPT-5 was able to smoothly address the required numerical challenges involved by using the recently released Oklch standard. The Generative AI system produced a valid color scheme suggestion that is a color triad in both traditional and perceptually uniform color spaces.

Humans have three types of photoreceptors or cones that support color vision. A color deficiency happens when one or more sets of cones does not function properly. A red cone deficiency is classified as Protanopia. A green cone deficiency is classified as Deuteranopia. A blue cone deficiency is classified as Tritanopia. Software is available that simulates color deficiencies. Here, I used the Adobe Color tool and Viz Palette to check for color deficiency in ChatGPT-5’s color scheme suggestion.

Using Oklch perceptual uniformity, ChatGPT -5 addressed these parameters by recommending a color triad harmony of Indigo Blue #3B5BA0; Fern Green #5AA03B, and Flame Orange #A05A3B. I then used the Adobe Color tool to successfully verify that ChatGPT-5’s color scheme is a color triad that passed color deficiency. I also explored generic data visualization examples with Viz Palette . This is indeed a amazingly universal and accessible color triad recommendation made by ChatGPT-5.

For additional discussions on my explorations with various Gen AI and color suggestion tools, please see my prior UX Collective and Nightingale writings as well as the 2nd Edition of my book on Applying Color Theory to Digital Media and Visualization, published December 19, 2024, by CRC Press.

Author Profile:

Theresa-Marie Rhyne is a Visualization Consultant with extensive experience in producing and colorizing digital media and visualizations. She has consulted with the Stanford University Visualization Group on a Color Suggestion Prototype System, the Center for Visualization at the University of California at Davis and the Scientific Computing and Imaging Institute at the University of Utah on applying color theory to Ensemble Data Visualization. Prior to her consulting work, she founded two visualization centers: (a) the United States Environmental Protection Agency’s Scientific Visualization Center and (b) the Center for Visualization and Analytics at North Carolina State University.

OKLCH with ChatGPT-5 was originally published in UX Collective on Medium, where people are continuing the conversation by highlighting and responding to this story.

This post first appeared on Read More