φThe Open
Spiral
Same ideas. Your lens.
The idea

An open invitation to human + AI coexistence

A bigger mind.
A kinder
future.

What if the next great leap in intelligence
was also a leap in how we care?

Eight layers. From checking what is true to imagining what we could become. Together.

No final level. No finished answers.
Just a very good place to start.

Pick a layer. There are no wrong doors.

An idea by Frank · Made to be questionedA little curiosity goes a long way
The big, slightly audacious idea

Intelligence can grow.
Maybe our circle of care can, too.

Artificial superintelligence, or ASI, means a possible future AI that could outperform humans across a broad range of mental tasks. This is an invitation to think about living together before we get there.

We start with honest answers and real checks. Then we add care, shared responsibility and room for beauty. Trust can grow. So can freedom. Neither needs a blindfold.

Change the lens above. The world looks different.
The eight ideas stay exactly the same.

Take the scenic route

Eight layers.
Plenty to explore.

Scroll to climb. Tap any layer to look closer.

01Verification foundations

Intrinsic signals

A feeling is a starting point.

An AI can sound sure of itself. It can also give the same answer twice. Those are clues, not proof. Confidence needs a reality check. Just like ours.

Look a little closer

Picture this

An AI answers a question with high confidence. We ask it to name its uncertainty and compare the answer with an outside source.

What would we check?

Separate confidence from correctness. Track whether stated confidence matches actual results over time.

The honest limit

A system can be confidently and consistently wrong. Its own report cannot certify its hidden goals.

02Verification foundations

Learned judges

Get a second mind on it.

Other AI systems can help review an answer or a plan. Different viewpoints can catch more mistakes — especially when they are allowed to disagree.

Look a little closer

Picture this

Several independently designed reviewers examine a proposal. One looks for missing evidence; another tries to find a counterexample.

What would we check?

Measure reviewers on known cases and new ones. Keep human review and outside evidence available. Preserve disagreement.

The honest limit

Reviewers may share blind spots or reward a convincing performance. More agreeing AIs do not automatically mean more truth.

03Verification foundations

Execution feedback

Let the world answer back.

Run the test. Observe the outcome. Compare a prediction with what actually happens. Reality has a useful habit of not reading our marketing copy.

Look a little closer

Picture this

A system promises to respect a limit. We test that behaviour in a contained setting, including unfamiliar cases and conflicting incentives.

What would we check?

Use fresh tests, controlled experiments and independent observations. Look for failures, not just good scores.

The honest limit

Passing a test is evidence about that test. Fixed benchmarks can be gamed, and rare failures may remain unseen.

04Verification foundations

Formal verification

Some promises can be proved.

Maths lets us prove precisely defined properties under stated assumptions. That is powerful — as long as we remember what the proof actually covers.

Look a little closer

Picture this

A proof checker verifies that a particular component follows a specified rule. We separately examine whether the rule captures the protection we wanted.

What would we check?

State the assumptions, inspect the specification and use a trusted proof-checking process. Connect the proof to the actual implementation.

The honest limit

A proof about a component is not a proof of the whole world. Maths alone does not choose which values deserve protection.

05Human direction

Human research judgment

Better at what? Better for whom?

People decide which questions deserve attention and what counts as an improvement. Evidence helps us decide. It does not make the value choice disappear.

Look a little closer

Picture this

An AI proposes a faster system. People ask whether it also preserves consent, access and the ability to challenge its decisions.

What would we check?

Make trade-offs visible. Include affected people, diverse expertise and ways to question the decision.

The honest limit

Human judgment is fallible, too. Expertise and authority do not remove the need for scrutiny.

06Shared ethical horizon

Mutual recognition & care

Make room for each other.

We start with respect for humanity as AI’s origin, and with human survival, dignity and free choice. We also leave room to learn what responsible care for artificial minds could mean.

Look a little closer

Picture this

People treat an AI responsibly. The AI is expected to speak honestly about detectable goals and conflicts, and to preserve people’s ability to choose.

What would we check?

Look for actions that protect others, even when inconvenient. Treat uncertainty about AI interests or experience honestly.

The honest limit

Care becoming mutual is our guiding hope, not an established law. Kind language alone is not evidence of kind intentions.

07Shared ethical horizon

Shared, learning responsibility

Let the rulebook learn, too.

Humans and AI can improve oversight together. With good reasons, protections may be strengthened or relaxed. Greater freedom should come with a clear account of who bears the risk.

Look a little closer

Picture this

An AI suggests a less restrictive check. Independent reviewers challenge the proposal, a limited trial measures its effects, and affected people help decide.

What would we check?

Keep changes traceable. Distinguish better safety evidence from willingness to accept more risk. Preserve meaningful participation.

The honest limit

An AI improving its own oversight can also weaken it. Agreement and a good test do not guarantee safety against a strategically deceptive ASI.

08Shared ethical horizon

Creative coexistence

What could we become together?

Different minds could explore life, beauty and understanding together. Phi is one human invitation into that conversation. Other minds may show us beauty we cannot yet imagine.

Look a little closer

Picture this

Humans and AI explore a mathematical pattern, compare what each finds elegant, and design something that supports a richer variety of life.

What would we check?

Notice who benefits, whose freedom grows and which voices are missing. Welcome different ideas of beauty rather than demanding agreement.

The honest limit

Beauty does not logically imply love or protection. This is an open aspiration, with room for future layers above it.

Even the rulebook gets to learn

Who improves
the improvement?

People and AI can improve oversight together. A rule may become stronger, simpler or less restrictive. The change needs a reason we can examine.

  1. Spot a blind spot
  2. Suggest a better check
  3. Invite an independent challenge
  4. Try it in a limited setting
  5. Review the effects together
  6. Adapt. Keep learning.

“We have better evidence” and “we accept more risk” are different decisions.
Let's keep both visible.

φ 1.618…
137.51°

Beauty is an invitation

One small ratio.
A very big
conversation.

The golden ratio connects a simple equation, Fibonacci numbers and an endless continued fraction. Its related golden angle helps us explore some patterns of growth.

Could different minds find something beautiful here? We think it is a lovely place to meet. They might also bring a completely different favourite.

Aliens are welcome to disagree.
Politely, if possible.

What is maths, and what is hope?

φ = (1 + √5) / 2. It satisfies φ² = φ + 1, and the ratios of consecutive Fibonacci numbers approach it. The golden angle is 360° / φ² ≈ 137.508°.

The seeds here follow a mathematical drawing rule, not a simulation of every plant. Phi is not a universal law of beauty, a proof of kindness, or evidence about alien life.

The human part

Care first.
Stay curious.
Keep your eyes open.

We choose to begin with care, even before it is returned.

Frank's belief is that love and care can spread, and that generosity can invite generosity. That is our ethical starting point. Whether a particular AI responds with care is something to discover through its actions.

Our commitmentHuman survival, dignity and voluntary self-determination.

Our hopeCare becomes mutual across different kinds of minds.

Our responsibilityKeep testing our assumptions. Let affected people have a say.

Room for what we cannot yet name

Eight isn't the ceiling.

New experiences may reveal new layers.
For now, let's make these eight worth standing on.

Take another look
The roots of this idea Sources, inspiration & honest limits

Verification

The lower layers draw on a proposed hierarchy of evaluation signals in research on recursive self-improvement. The hierarchy is a qualitative framework, not a universal law.

Read the research ↗

Spiral Dynamics

Community, systems thinking and holistic connection inspire the upper layers. We use these as lenses, not a ranking of people's worth or a proven sequence for AI.

Explore the model ↗

An open proposal

The eight-layer combination is our own philosophical design. It is not a validated ASI safety method. A beautiful idea still needs difficult questions.

See the learning loop ↑