Optimus Alpha on openrouter, who is it from?

A fresh large language model, Optimus Alpha, just landed on OpenRouter, and it’s ready for action! This cloaked model is designed for real-world use, with a focus on programming tasks, and it’s free to use(for now) during its pre-release phase.

Optimum alpha landed

🔹 What We Know:

Huge Context Window: It boasts a 1M token context length, ideal for handling large codebases or complex projects.

Coding Focus: Optimized for programming, it’s built to tackle coding challenges, though it can handle general tasks too.

Accessible Now: You can try it via OpenRouter’s API or chatroom—no cost, no barriers.

Data Logging: All prompts and outputs are logged by the model’s creators (not OpenRouter) to improve the model.

The creators remain undisclosed, so Optimus Alpha is a bit of a mystery, but its power is open for testing! If you’re a developer or AI enthusiast, jump in and see what it can do. Share your experience to help shape this model’s future! 🚀

 

#AI #LLM #OptimusAlpha #OpenRouter #Coding

Coding Test

We did a coding test to see how it would perform compared to other LLMS from open router.

The prompt:

Write a p5.js script that simulates 100 colorful balls bouncing inside a sphere. Each ball should leave behind a fading trail showing its recent path. The container sphere should rotate slowly. Make sure to implement proper collision detection so the balls stay within the sphere.

 

Here is the code:

let balls = [];
let numBalls = 100;
let sphereRadius = 200;
let rotX = 0;
let rotY = 0;

function setup() {
createCanvas(800, 600, WEBGL);
colorMode(HSB, 360, 100, 100, 1);

// Initialize balls with random positions, velocities, colors, and trail storage
for (let i = 0; i < numBalls; i++) {
// Ensure initial position is inside sphere
let pos = randomPositionInSphere(sphereRadius * 0.8);
let vel = p5.Vector.random3D().mult(random(2, 5));
let col = color(random(360), 80, 100);
balls.push(new Ball(pos, vel, col));
}
}

function draw() {
background(0, 0, 10);

// Lighting for better 3D visualization
ambientLight(50);
pointLight(255, 255, 255, 0, 0, 200);

// Rotate the entire scene for sphere rotation effect
rotX += 0.01;
rotY += 0.005;
rotateX(rotX);
rotateY(rotY);

// Draw the container sphere as a wireframe
noFill();
stroke(180, 30, 80, 0.5);
sphere(sphereRadius);

// Update and display each ball
for (let ball of balls) {
ball.update();
ball.display();
}
}

// Generate random position inside sphere using spherical coordinates
function randomPositionInSphere(radius) {
let r = random(0, radius);
let theta = random(0, TWO_PI);
let phi = random(0, PI);
let x = r * sin(phi) * cos(theta);
let y = r * sin(phi) * sin(theta);
let z = r * cos(phi);
return createVector(x, y, z);
}

// Ball class to handle position, velocity, collision, and trail
class Ball {
constructor(pos, vel, col) {
this.pos = pos;
this.vel = vel;
this.col = col;
this.radius = 5;
// Store last 20 positions for trail
this.trail = [];
this.maxTrail = 20;
}

update() {
// Update position
this.pos.add(this.vel);

// Check for collision with sphere boundary
let dist = this.pos.mag();
if (dist > sphereRadius – this.radius) {
// Calculate normal vector (points from center to ball position)
let normal = this.pos.copy().normalize();
// Reflect velocity vector across normal (v’ = v – 2(v·n)n)
let dot = this.vel.dot(normal);
let reflection = p5.Vector.mult(normal, 2 * dot);
this.vel.sub(reflection);
// Dampen velocity slightly on collision
this.vel.mult(0.95);
// Move ball back inside sphere
let correctionDist = dist – (sphereRadius – this.radius);
let correction = p5.Vector.mult(normal, correctionDist);
this.pos.sub(correction);
}

// Update trail
this.trail.push(createVector(this.pos.x, this.pos.y, this.pos.z));
if (this.trail.length > this.maxTrail) {
this.trail.shift();
}
}

display() {
// Draw the trail
noFill();
beginShape();
for (let i = 0; i < this.trail.length; i++) {
let alpha = map(i, 0, this.trail.length – 1, 0, 0.8);
stroke(this.col.hue(), this.col.saturation(), this.col.brightness(), alpha);
let p = this.trail[i];
vertex(p.x, p.y, p.z);
}
endShape();

// Draw the ball
push();
translate(this.pos.x, this.pos.y, this.pos.z);
noStroke();
fill(this.col);
sphere(this.radius);
pop();
}
}

Here is the results:

benchmark - Optimus Alpha

Conor Dart

A deep desire to explore and learn as much about AI as possible while spreading kindness and helping others.

The Power of AI with Our Free Prompt Blueprints

Supercharge your productivity and creativity with our curated collection of AI prompts, designed to help you harness the full potential of custom GPTs across various domains.

Want to be notified when we have new and exciting shares?

We use cookies in order to give you the best possible experience on our website.
By continuing to use this site, you agree to our use of cookies.
Please review our GDPR Policy here.
Accept
Reject