Skip to content

Nothing Happened Today

Letting AI decide what a day looks like, without inventing what happened.

Every evening at 19:38:38 UTC, Nothing Happened Today reads the day’s news, decides what mattered, and creates a single work of art.

Nothing Happened Today: drop 40, “Pressure Above Ground,” a charcoal painting beside the statement written by the model, with medium, palette and composition listed below

Nobody chooses the subject, the medium, or what the finished piece should look like.

I wanted to see what happens when an AI artist is given the world as inspiration and the freedom to interpret it.

My job was to design the system, establish its boundaries, and stay out of the creative decisions.

nothinghappenedtoday.com
Role
Product designer, builder, first customer
Timeline
September - October 2026
Models
Claude (development), OpenAI (news interpretation, image generation, voice)
Status
Live. 40 daily drops and counting. Prints, wallpapers, and books built but not yet available

01 / ORIGIN

Giving an AI artist the world as its inspiration

The project started as SloppyGen, a joke about the endless stream of AI-generated content. But I was curious about something more interesting: what would a day look like if AI interpreted the world’s events and created a single piece of art without anyone directing it?

About half an hour into the first build, the model was already inventing its own influences. Autumn, airport carpets, a particular Friday in September. None of it came from the actual news.

That changed the direction of the project. If AI was going to interpret the day, its inspiration needed to come from things that actually happened.

02 / EXPERIENCE

One day. One interpretation.

Every evening at 19:38:38 UTC, Nothing Happened Today creates one artwork inspired by the day’s events.

The system gathers information from 33 sources covering news, markets, culture, science, sports, and the planet. It identifies themes, evaluates the day’s mood and intensity, and considers recent events before deciding what to create.

The first version produced seven images a day, one for each category. It felt comprehensive, but missed the point.

I reduced it to a single daily artwork. One artist, one interpretation of the day.

03 / DECISIONS

When the artist wasn’t really making the decisions

In October, I requested an audit to see whether the artwork was genuinely influenced by the day’s events.

The audit uncovered something I hadn’t expected. Of the first 28 pieces, 21 had quietly fallen back to a human-written template when the model failed. The site was presenting them as authentic AI interpretations.

I stopped production and removed the fallback. If the model fails, the product needs to acknowledge it.

Another audit revealed that predefined rules were choosing artistic styles for the model. I removed those too.

Both discoveries forced me to reconsider what creative independence actually meant.

Nothing Happened Today is live, with 40 daily drops and counting. Prints, wallpapers, and monthly books have also been built, although those features remain unavailable to the public.

It’s an ongoing experiment in what happens when AI is given creative independence.

And perhaps the most important lesson has been that creative freedom and accountability aren’t opposites.

The model can decide what to create. The system still has to be honest about how it got there.

From idea to production, with AI as a collaborator.

Glossy black robot character with glowing eyes

Discover

Understand the problem

  1. Step 1: Frame the idea

    Problem, audience, desired outcome

  2. Step 2: Explore together

    Questions, alternatives, tradeoffs

  3. Step 3: Validate assumptions

    Research, feasibility, evidence (AI research - I decide)

Define

Set the direction

  1. Step 4: Define the product

    Requirements and success criteria

  2. Step 5: Plan the work

    Milestones, tasks, acceptance tests. AI drafts

  3. Step 6: Approve the plan

    I revise scope before work begins. My approval.

Deliver

Build, verify, release

  1. Step 7: Build + review loop

    Implement, agent audit, fix, recheck (AI and agents)

  2. Step 8: Connect + test

    Services, env setup, staging QA

  3. Step 9: Ship + learn

    I approve release; we iterate. My approval

I use AI throughout the product development process, from exploring an idea and challenging assumptions to defining requirements, building, and reviewing the implementation.

But I don’t want a model that simply agrees with me. I expect it to question decisions, identify tradeoffs, and provide evidence that the work actually functions.

I review the plan, direct the experience, and use independent agents to help verify the implementation. Before release, I test the product and make the final call.

AI makes it possible to move much faster. My responsibility is making sure we’re moving in the right direction.