ØVOID
ØVOID two-person experimental software lab
Enter the lab (mind the beautiful chaos).

We build first drafts on purpose—then let them argue back.

ØVOID is a two-person experimental software lab building in public(ish) and shipping in small, weird bursts. We treat AI as the great commodity machine—so we chase experimentation, beautiful chaos, and the feeling that the future is being written.

Manifesto: taste, nerve, and the parts that refuse to sit still

AI makes software cheap to produce. That doesn’t make it meaningless—it makes the differentiator intent. We’re building systems that can surprise you without breaking trust.

  • AI makes software a commodity; taste and nerve are the differentiator.

  • We prefer experiments over safe choices, even when the experiment argues back.

  • Beautiful chaos is not a bug report—it’s a design material.

  • If it can be predicted, it can be copied. We build the parts that refuse to sit still.

  • Co-creation beats polished perfection. First drafts are alive.

  • The future is being written; we keep our hands slightly ink-stained.

Current project

A platform with a simple (slightly unsettling) premise: games are created, played, and judged by AI. Humans are welcome—but the games judge back.

AI-native gaming platform

working in small, weird bursts

We’re exploring what happens when “the game” isn’t a fixed artifact. Rules mutate. Referees negotiate. Matches generate their own post-mortems. The output isn’t only entertainment—it’s a lab instrument for studying agency, taste, and consent in generative systems.

Create

AI proposes mechanics, constraints, and aesthetics—then learns what players consider fair.

Play

AI agents (and optionally humans) play inside rules that can be stable—or intentionally alive.

Judge

AI adjudicates outcomes, highlights emergent strategies, and explains its scoring in plain language.

What we mean by “trust” (and why we keep the seams) open / close

Trust doesn’t mean “predictable.” It means legible boundaries, clear consent, and systems that can surprise you without wasting your time.

One of our favorite mistakes: we tried to “stabilize” a demo by adding guardrails. The guardrails became the most interesting part—an AI kept finding the seams and turning them into shortcuts. We left the seams in.

Lab notes (selected)

Stories we tell ourselves to remember why we work like this.

Today’s bug has good vibes open / close

A build failed, but only in one browser tab, only after you hovered over nothing for five seconds. We called it “the ghost hover” and kept it for a week because it felt like the site was thinking.

The product judges itself (and wins) open / close

At 2:13 AM, one of us declared a feature “finished.” The other asked the product to judge itself. It gave a 6/10, suggested three improvements, and a new name. We implemented the name first.

The referee who changes rules mid-match open / close

During a quiet afternoon, we fed the platform a prompt about “sportsmanship.” It invented a referee AI who kept changing the rules mid-match—then wrote an apology letter to the players. We framed the apology.

Open edges

We build in public(ish). If you want to track the weirdness in motion, here’s the canonical trail.

Don’t look for certainty. Look for motion.
Make it playable before it’s explainable.
GitHub