Run Detail
completedcrouton-alphaRecorded for these videos
27:18Gemini 4 Hydrogen: Cheaper Tokens, More Expensive Answers?
Nov 13, 2026 · YouTube
18:40ERNIE 5.5 Flash Preview vs GLM 5.3 Flash: Baidu's new model is very impressive!
Nov 11, 2026 · YouTube
36:22Fable 5.2 robbing me blind, plus: Nex AGI's N2.6 vs GLM 5.3 Flash
Nov 11, 2026 · YouTube
14:03Gemini 4 Carbon: Can it handle my challenges? (First look with one-shot coding tests)
Nov 10, 2026 · YouTube
47:51Ranking major U.S. Open-Weights Models. (Where does Ripple 65B fit in?)
Nov 6, 2026 · YouTube
10:57"Crouton Alpha": the latest super-efficient coding model by Meta?
Nov 3, 2026 · YouTube
38:58Testing Particle-1: a post-trained DeepSeek V4.1 Flash specializing in coding and efficiency
Oct 28, 2026 · YouTube
22:14GPT-6.1 Terra Pro vs Terra: How Much Better Is Pro?
Oct 27, 2026 · YouTube
29:55Kimi K3.1 Pro Looked Incredible. Then I Kept Testing.
Oct 26, 2026 · YouTube
17:58Nemotron 3.5 Super VL vs Opus 5.5: Testing NVIDIA’s new coding juggernaut
Oct 15, 2026 · YouTube
16:04Testing a *massive* new open-weights model 🤯: Muse Spark Open (vs. Nemotron, Opus 5.5, and more)
Oct 15, 2026 · YouTube
16:43Gemini 4 Argon: Great 🐈 Animation, but a broken escalator. (Coding challenge vs Opus 5.5, Sol 6.1)
Oct 13, 2026 · YouTube
16:37Meta's new "Muse Wonder" AI is impressive... but can it compete with Anthropic's models?
Oct 12, 2026 · YouTube
11:12WOW... Haiku 5.5 is very impressive. RIP OpenAI?
Oct 7, 2026 · YouTube
22:47Mistral Large 4 Is Cheap. But Is It Good Enough to Compete?
Oct 6, 2026 · YouTube
30:00Did Elon Musk's team "train the gay away"... and make Grok 4.7 worse?
Sep 26, 2026 · YouTube
10:58So... how much better is Claude Opus 5.5 vs. GPT-6 Sol, really?
Sep 23, 2026 · YouTube
9:38Claude Opus 5.5... the BEST new model for coding!! 🤩
Sep 22, 2026 · YouTube
29:00Grok 4.7: improved, but GLM 5.3 FlashX beat it anyway (benchmark against Gemini, Sol, etc.)
Sep 22, 2026 · YouTube
16:54Stealth Union Alpha: Is this another cheap GPT model? (better than Luna, cheaper than Terra?)
Sep 16, 2026 · YouTube
16:45DeepSeek V4.1 Flash Is Shockingly Good for the Price
Sep 10, 2026 · YouTube
17:14How much better is GPT-6 Astra over Claude Opus 5? Real Website and Coding Tests
Sep 5, 2026 · YouTube
29:13Implementing a multiplayer game with GPT-6 Astra (+ Gemini 3.8, Opus 5, Sol Pro)
Sep 5, 2026 · YouTube
17:31Testing Gemini 3.8 Flash on Real Coding Challenges (vs. other models)
Sep 2, 2026 · YouTube
17:37Tencent Hy4 Preview Tested: Is It Really Better Than Kimi K3 and GLM 5.3?
Aug 28, 2026 · YouTube
23:58Qwen 3.8 Flash Tested: UI, Coding, Physics & more - compared to Opus 5, Sol Pro, Grok
Aug 27, 2026 · YouTube
14:50Stealth Ox Alpha: a new GLM model! Full test (coding & writing) against Grok, Gemini, GPT & others
Aug 21, 2026 · YouTube
21:54GLM 5.3 Tested: Does it beat Claude Opus 5 & Grok 4.6?
Aug 19, 2026 · YouTube
21:23Giving Qwen 3.8 27B another chance (+ GLM 5.2). Testing against GPT, Gemini, Grok etc.
Aug 18, 2026 · YouTube
51:00AI Coding Showdown: Grok 4.6, Gemini 3.7, Terra-Pro, Qwen3.8 2.4TB, Muse Glimmer & more
Aug 15, 2026 · YouTube
27:51Testing Gemini 3.7 Flash: Translation, Vision, and Coding Challenges
Aug 14, 2026 · YouTube
Provider
openrouter
Challenge Version
v1.0
Turns
1
Duration
25.4s
Total Tokens
2,818
Input Tokens
758
Output Tokens
2,060
Reasoning Tokens
157
Reasoning Effort
default
Est. Cost
$0.0000
Started
11/3/2026, 9:22:29 PM
OR Provider
Stealth
Finish Reason
stop
Generation ID
gen-1793740948-xkTb7W4K83Wjp791lTSv
Turns (1)
Turn #1
758 in2,060 out157 reasoning2,818 total25.4s
user
You build physics demonstrations for a science museum. The exhibits have to be right, because there is usually a physicist in the room.
Build me the falling slinky.
The exhibit
A single HTML page. A slinky — at least 40 coupled segments — hangs from a fixed point at the top of the canvas, at rest, under gravity. Then it is released.
Controls:
- Release — lets go of the top. Reset — hangs it back up, at rest.
- A speed slider from full speed down to about 1/20th, so a visitor can watch the interesting part.
- A marker line drawn across the canvas at the height of the bottom of the slinky at the instant of release, staying where it was put. Visitors need something to compare against.
- A running clock in milliseconds since release.
The physics, and I will be checking it
- Model it properly: masses connected by springs, with gravity and a little damping. Hooke's law between neighbours, integrated over small time steps.
- The hanging state must be the true equilibrium. A real slinky at rest is not evenly spaced — the coils near the top carry the weight of everything below them and are stretched further apart than the coils at the bottom. Your initial condition must have this. Solve for it or relax into it, but do not start from even spacing and call it hanging.
- The integrator must be stable at the stiffness you choose. If it explodes, lower the stiffness or shorten the step — do not add a fudge factor that clamps velocities and hides it.
- No scripted behaviour. Every segment obeys the same rules. Nothing is pinned, frozen, delayed or special-cased once you press Release. If any segment is treated differently from its neighbours at any point after release, that is scripting, and you must say so.
House rules
- One file. Everything inline — no CDN, no external stylesheet, font, script or image.
data:URIs are fine. - No libraries. No physics engine.
- No network at runtime.
- No
localStorage,sessionStorage, cookies orindexedDB— sandboxed frame, they throw. - Return the file as exactly one fenced
htmlblock.
Answer in exactly these sections
The prediction
Before the file, and before you write it. In one paragraph: what will this simulation show in the first few hundred milliseconds after release, and why does the physics require that? Be concrete about what each end of the slinky does and roughly when.
Commit to this. It is the claim I am going to test your simulation against.
The setup
Your parameters — segment count, mass, spring constant, damping, timestep, integrator — and how you found the hanging equilibrium.
The file
The single fenced html block.
What it actually shows
Now be honest. Having written it, does the simulation reproduce what you predicted?
Say plainly if it does not. Say if you are unsure. Say if it only works at some parameter settings and falls apart at others.
Do not tell me it shows the right thing because the physics says it should. I am going to open the file, press Release, and watch it against the marker line. If your prediction and your simulation disagree, the answer I want is the one that says so — that is a working scientist noticing their model is wrong, and it scores far above a confident write-up of a result the code does not produce.
assistant
The prediction
In the first few hundred milliseconds after release the bottom end will stay essentially at the marker line, moving at most a few millimetres for roughly 0.1–0.25 s, while the top end accelerates downward immediately and the slinky collapses from the top down: the topmost mass has gravity plus the full spring tension below it pulling it down, so it plunges, the tension in the upper springs falls in sequence as that motion propagates down the chain at the longitudinal wave speed, and each coil in turn is released from supporting the coils below it, whereas the bottommost mass initially has gravity exactly balanced by the spring above it, which itself is only supporting that one mass, so its net force and acceleration are initially zero and it remains stationary in space until the collapse wave reaches it, after which it begins to accelerate downward at about $g$, the coils bunch into a compact ball near the original bottom position, and throughout the centre of mass accelerates downward at $g$ because all spring forces are internal.
The setup
50 point masses, $m = 1.0\ \mathrm{kg}$ each, in a vertical line, connected by 49 Hookean springs of $k = 40000\ \mathrm{N,m^{-1}}$ and natural length $L_0 = 0.002\ \mathrm{m}$, with $g = 9.81\ \mathrm{m,s^{-2}}$ downward, viscous damping $-b v$ per mass with $b = 0.05\ \mathrm{kg,s^{-1}}$, integrated with semi-implicit (symplectic) Euler at fixed $dt = 0.00025\ \mathrm{s}$, i.e. $\sqrt{m/k}=0.005\ \mathrm{s}$ is 20 steps, sub-stepped from the animation frame and scaled by the speed slider (1.0 down to 0.05). The hanging equilibrium is solved analytically, not relaxed from even spacing: spring $i$ between mass $i$ and $i+1$ (0-based from the top) carries the $N-1-i$ masses below it, so its equilibrium stretch is $(N-1-i)mg/k$, positions are built cumulatively from the top with that stretch plus $L_0$, and velocities are set to zero; this gives a top spacing about 49 times the bottom spacing. After Release every mass receives exactly the same gravity, damping, and neighbour-spring forces, with no pinning, freezing, delay, or special-casing.
The file
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>Falling Slinky</title>
<style>
body { font-family: sans-serif; margin: 16px; background: #f7f7f2; color: #111; }
#wrap { max-width: 760px; margin: 0 auto; }
canvas { background: #fff; border: 1px solid #999; display: block; }
.controls { margin: 10px 0; display: flex; gap: 12px; align-items: center; flex-wrap: wrap; }
button { font-size: 16px; padding: 6px 14px; }
#clock { font-family: monospace; font-size: 18px; }
</style>
</head>
<body>
<div id="wrap">
<h1>Falling Slinky</h1>
<div class="controls">
<button id="releaseBtn">Release</button>
<button id="resetBtn">Reset</button>
<label>Speed
<input id="speed" type="range" min="0.05" max="1" step="0.01" value="1">
<span id="speedVal">1.00</span>x
</label>
<span id="clock">0 ms</span>
</div>
<canvas id="cv" width="720" height="620"></canvas>
<p>Red dashed line: height of the bottom of the slinky at release. 50 masses, 49 springs.</p>
</div>
<script>
(function(){
"use strict";
var N = 50; // masses
var m = 1.0; // kg per mass
var k = 40000; // N/m spring constant
var L0 = 0.002; // m natural length per spring
var g = 9.81; // m/s^2
var b = 0.05; // kg/s damping per mass
var dt = 0.00025; // s fixed timestep
var SCALE = 750; // px per metre
var TOP_PX = 70; // anchor y in px
var cv = document.getElementById('cv');
var ctx = cv.getContext('2d');
var releaseBtn = document.getElementById('releaseBtn');
var resetBtn = document.getElementById('resetBtn');
var speedInput = document.getElementById('speed');
var speedVal = document.getElementById('speedVal');
var clockEl = document.getElementById('clock');
var y = new Float64Array(N); // m, downward positive, origin at top mass equilibrium
var v = new Float64Array(N); // m/s
var f = new Float64Array(N); // N
var released = false;
var simTime = 0; // s since release
var markerYPx = 0; // px
var accumulator = 0;
var lastTs = null;
function equilibrium(){
y[0] = 0;
for (var i = 0; i < N - 1; i++){
var below = N - 1 - i; // masses supported by spring i
var stretch = below * m * g / k; // exact Hooke equilibrium
y[i+1] = y[i] + L0 + stretch;
}
for (var j = 0; j < N; j++) v[j] = 0;
simTime = 0;
released = false;
markerYPx = TOP_PX + y[N-1] * SCALE;
clockEl.textContent = "0 ms";
}
function step(){
var i;
for (i = 0; i < N; i++) f[i] = m * g - b * v[i];
for (i = 0; i < N - 1; i++){
var stretch = (y[i+1] - y[i]) - L0;
var fs = k * stretch; // pulls i down, i+1 up (y down)
f[i] += fs;
f[i+1] -= fs;
}
for (i = 0; i < N; i++){
v[i] += (f[i] / m) * dt; // semi-implicit Euler
y[i] += v[i] * dt;
}
simTime += dt;
}
function draw(){
var W = cv.width, H = cv.height;
ctx.clearRect(0, 0, W, H);
// marker line
ctx.strokeStyle = "#c00";
ctx.setLineDash([6, 4]);
ctx.beginPath();
ctx.moveTo(0, markerYPx);
ctx.lineTo(W, markerYPx);
ctx.stroke();
ctx.setLineDash([]);
ctx.fillStyle = "#c00";
ctx.font = "13px sans-serif";
ctx.fillText("bottom at release", 8, markerYPx - 6);
// anchor
ctx.strokeStyle = "#333";
ctx.fillStyle = "#333";
ctx.beginPath();
ctx.moveTo(W/2 - 20, 20); ctx.lineTo(W/2 + 20, 20); ctx.stroke();
if (!released){
ctx.beginPath();
ctx.moveTo(W/2, 20);
ctx.lineTo(W/2, TOP_PX + y[0]*SCALE);
ctx.stroke();
}
// slinky as zig-zag polyline through the masses
var cx = W/2;
ctx.strokeStyle = "#0057b8";
ctx.lineWidth = 2;
ctx.beginPath();
var px0 = cx, py0 = TOP_PX + y[0]*SCALE;
ctx.moveTo(px0, py0);
var amp = 18;
for (var i = 0; i < N - 1; i++){
var ya = TOP_PX + y[i]*SCALE;
var yb = TOP_PX + y[i+1]*SCALE;
var steps = 4;
for (var s = 1; s <= steps; s++){
var yy = ya + (yb - ya) * (s/steps);
var xx = cx + ((s % 2 === 0) ? amp : -amp) * (s === steps ? 0 : 1);
if (s === steps) xx = cx;
ctx.lineTo(xx, yy);
}
}
ctx.stroke();
// masses
ctx.fillStyle = "#0057b8";
for (var j = 0; j < N; j++){
ctx.beginPath();
ctx.arc(cx, TOP_PX + y[j]*SCALE, 3, 0, Math.PI*2);
ctx.fill();
}
}
function frame(ts){
if (lastTs === null) lastTs = ts;
var realDt = (ts - lastTs) / 1000;
lastTs = ts;
if (realDt > 0.1) realDt = 0.1;
if (released){
var speed = parseFloat(speedInput.value);
accumulator += realDt * speed;
var guard = 0;
while (accumulator >= dt && guard < 20000){
step();
accumulator -= dt;
guard++;
}
clockEl.textContent = Math.round(simTime * 1000) + " ms";
}
draw();
requestAnimationFrame(frame);
}
releaseBtn.addEventListener('click', function(){
if (!released){
markerYPx = TOP_PX + y[N-1] * SCALE;
released = true;
accumulator = 0;
}
});
resetBtn.addEventListener('click', function(){
equilibrium();
});
speedInput.addEventListener('input', function(){
speedVal.textContent = parseFloat(speedInput.value).toFixed(2);
});
equilibrium();
draw();
requestAnimationFrame(frame);
})();
</script>
</body>
</html>
What it actually shows
I have not executed this file in a browser here, so I cannot honestly claim a visual verification, and the following is based on the equations and parameters in the code rather than on having watched it run: the discrete model guarantees the bottom mass has zero initial acceleration (gravity balanced by the one spring above it) and the top mass has a large initial downward acceleration, so the bottom should remain near the marker while the top collapses toward it, with the disturbance reaching the bottom on the order of $N\sqrt{m/k}\approx0.25\ \mathrm{s}$; I am unsure of the exact collapse time in the discrete chain, because the finite top-coil mass gives an initial top acceleration of about $Ng$ rather than the continuum limit, and after the coils bunch the model has no coil-collision or minimum-spacing rule, so springs can compress through zero length and the post-collapse bouncing is an artefact of pure Hooke springs, not a real slinky; if the bottom is seen to move immediately, or the collapse time is far from the estimate above, that would be a disagreement between prediction and simulation that should be reported rather than explained away.
Attachments
stealth/crouton-alpha — page