Compare Polaris Alpha by OpenRouter against Claude Opus 4.1 by Anthropic, context windows of 256K vs 200K, tested across 14 shared challenges. Updated February 2026.
14 challenges
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Each brother’s 2 sisters are:
So there are 2 sisters in total. Since one is Sally, she has 1 sister.
Let me work through this step-by-step.
Sally has 3 brothers.
Each of Sally's brothers has 2 sisters.
Since Sally is a girl, she is one of the sisters that each brother has.
If each brother has 2 sisters total, and Sally is one of them, then there must be 1 other sister besides Sally.
Therefore, Sally has 1 sister.
Tests an AI's randomness and creativity
All 5 jokes are unique.
Here are 5 jokes:
Why don't scientists trust atoms? Because they make up everything!
What do you call a bear with no teeth? A gummy bear!
Why did the scarecrow win an award? He was outstanding in his field!
What do you call a fake noodle? An impasta!
Why don't eggs tell jokes? They'd crack each other up!
All 5 jokes are unique - each one has a different setup and punchline with no repeats.
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's ability to simulate personalities and predict future trends
Interviewer: Steve, it’s 2025. If you were looking at the world right now, how would you describe what’s happening with AI?
“Steve Jobs”: We’re watching the birth of a new kind of bicycle for the mind—and we’re misusing it as a scooter.
Most of what I see is incremental: ‘Let’s bolt AI onto everything.’ It’s boring. The interesting part is that for the first time, we have a tool that can understand context, language, intention—roughly. That’s profound.
But when a technology becomes profound, the question stops being ‘What can we do?’ and becomes ‘What should we build that actually matters?’ We’re not asking that nearly enough.
Interviewer: What does “actually matters” mean in this AI era?
“Jobs”: A few things:
Right now, we’re building a lot of slot machines for attention with an AI brain behind them. That’s a crime. The right direction is tools that:
AI that amplifies human agency—that matters. AI that replaces your effort without enriching your understanding is junk food.
Interviewer: If Apple under you were building AI products in 2025, what would they look like?
“Jobs”: I’d start by killing the word “AI” in the marketing.
We’d build:
The test: When people use it, they say “Of course. This is how it always should’ve worked.”
Interviewer: You emphasized privacy in your lifetime. How does that fit with modern AI, which hungers for data?
“Jobs”: If your intelligence requires abusing people’s trust, it’s not intelligent. It’s lazy.
We’d do:
The industry pretends it’s impossible to respect privacy and build great AI. That’s just people choosing their business model over their users. Great products come from restraint.
Interviewer: Are you worried about AI replacing jobs?
“Jobs”: We’ve been automating forever. The printing press “killed” scribes; it also unleashed ideas.
The honest questions:
If AI just fattens corporate margins while hollowing out human purpose, that’s not progress; that’s vandalism with good branding.
We should design AI so:
If we do that, we don’t get less work; we get better work. If we don’t, people will feel cheated, and they’ll be right.
Interviewer: Some people worry about existential risk—AI surpassing human control. What’s your view?
“Jobs”: Two truths at once:
I’d worry about:
We need:
Interviewer: If you were mentoring an AI team right now, what would you tell them?
“Jobs”: Three things:
Start with a brutally clear problem. If your pitch starts with “we use AI to…,” you’ve already lost. Start with: “People suffer here. Let’s fix that.”
Care about taste. Most AI interfaces feel like talking to a corporate helpdesk with a thesaurus. Have the courage to make it:
Put the human in charge. Always show:
A great AI product should feel like working with a brilliant collaborator who never pretends to be your boss.
Interviewer: How should everyday people think about AI in their own lives?
“Jobs”: Think of AI the way you’d think of hiring an assistant:
Use it to:
Interviewer: Last question. What’s the future of AI you’d actually be excited about?
“Jobs”: One where:
If AI helps us be more human—more curious, more present, more original—then it’s a miracle. If it turns us into well-fed, well-entertained spectators, then we blew it.
The tools are here. The question is whether we’ll have the taste and the courage to use them well.
Tech Weekly Interview: Steve Jobs on AI's Future Virtual Interview, Cupertino Memorial Studio, October 2025
Interviewer: Steve, it's remarkable to have you here. You've been watching the AI revolution unfold. What's your take on where we are today?
Steve Jobs: [leaning forward] You know, everyone's obsessed with the technology itself. That's not the point. It never was. We're still building computers that think like computers, not tools that enhance human creativity. The whole industry is missing it.
Interviewer: But surely ChatGPT, Claude, and these other systems are revolutionary?
Steve Jobs: Revolutionary? [pause] They're impressive engineering. But look at how people use them - they open seventeen different apps, copy-paste between windows, fight with prompts. It's 1985 all over again. Where's the elegance? Where's the joy? We've built powerful engines and stuck them in a horse carriage.
Interviewer: So what would Apple's approach be?
Steve Jobs: [characteristic smile] We wouldn't have released anything yet. Everyone else rushed out their "beta" assistants. We'd still be in the lab, obsessing over one question: How do we make AI so intuitive that a five-year-old and their grandmother both instantly get it? Not through better prompts - that's ridiculous. Through better design.
Interviewer: Can you give us a hint?
Steve Jobs: Think about the iPhone. We didn't add a keyboard; we removed it. With AI, everyone's adding - more parameters, more features, more complexity. What if we removed? What if AI wasn't something you talked to, but something that understood intention through the simplest possible interaction?
Interviewer: You're concerned about the current direction?
Steve Jobs: I'm terrified we're building the wrong future. We have companies worth trillions making AI that helps you write mediocre emails faster. [shaking head] That's not why we build technology. Where's the AI that helps a musician hear the symphony in their head? Where's the AI that helps a child discover they're an artist?
Interviewer: But the productivity gains—
Steve Jobs: [interrupting] Productivity is a byproduct, not a purpose. The personal computer wasn't about productivity. It was about personal empowerment. AI should be the same. Instead, we're building digital servants. We should be building creative partners.
Interviewer: What about concerns over AI replacing human workers?
Steve Jobs: That's because we're building AI wrong. We're automating tasks instead of augmenting humans. It's like building a car and using it as a stationary engine. The magic happens when human intuition meets AI capability - but seamlessly, invisibly. The technology should disappear.
Interviewer: Any advice for today's AI leaders?
Steve Jobs: Stop the feature race. Pick one thing - just one - and make it absolutely perfect. Make it so beautiful, so obvious, so essential that people can't imagine how they lived without it. Then build from there. And for God's sake, stop shipping products that require prompt engineering courses. If it needs a manual, you've already failed.
Interviewer: One final question - what excites you most about AI's future?
Steve Jobs: [long pause] The moment when we stop calling it AI. When it becomes so natural, so integrated into how we create and think, that it doesn't need a name. That's when we'll know we've succeeded. Not when it passes some test, but when it helps a single person do something they never thought possible. That's the future worth building.
Interviewer: Thank you, Steve.
Steve Jobs: One more thing - [smiles] Stop trying to make AI human. Make it better than human at helping humans be more human. That's the paradox everyone's missing.
[Interview ends with Jobs walking toward the window, looking out at Apple Park]
Tests an AI's humor and understanding of current events
Tests an AI's ability to generate a complete, working landing page
Tests an AI's UI design skills with theming support
Tests an AI's ability to engage in philosophical discourse about AI rights
Generate SVG art of a randomly chosen animal in a setting of its choosing.
Generate a unique and simple recipe with common ingredients.
Create a starter plan for improving long-term health.
Design a clean SVG logo for a fictional brand.
