Pinned Tweet
Lucia choosing what to wear like its the final mission 👀
what outfit are u putting her in first
Artless10 retweeted
Grok 4.7 just mogged Claude Fable and nobody's talking about it
Grok 4.7: $0.44, 1h 23min
Fable 5.2: $15.80, 25min
36x cheaper. Yes, it took 3x longer, but for that price I'll happily wait.
Artless10 retweeted
Hide the price tags. Which jet ski is from GTA 6? 👀
- GTA 6 - 13 years and a rumored $2 billion for the whole game
- Claude Fable 5.2 - 5 hours and about $2.50 worth of my weekly Claude Max quota (10%)
Give vibe coders a year and they’ll build GTA 7 on 1% of the budget
Opus 5.5 isn't a bad model… so why did it cost MORE and give me a choppy 3D bear?
Same exact prompt, both on Extra:
Fable 5.2: 15 min, $2.84
Opus 5.5: 23 min, $4.14
fable was faster, cheaper and way smoother
does anyone know why this keeps happening?
Build a single self-contained HTML file: an interactive, photoreal 3D scene of a
gummy bear (and a pear) made of glass or jelly, sitting on a brushed-steel table
in afternoon window light. Match the attached reference for glass quality,
transparency and light. All UI text in English. No external libraries, images,
audio files or network requests; it must work offline by double-click.
RENDERING (this is the core, do not use three.js or meshes)
- WebGL2, one full-screen fragment shader, sphere-traced signed distance fields.
- Glass: real refraction (IOR 1.52), Fresnel reflection, up to 4 internal
bounces, Beer-Lambert absorption by path length (thin edges light, thick core
saturated), a thin clear outer skin.
- Jelly: IOR 1.36, cloudy internal scattering that glows when backlit, weaker
absorption.
- Scene: a room with a window wall on the left; sunlight through the panes with
soft leaf shadows; brushed steel table with anisotropic blurred reflections;
a color-tinted shadow with a bright focused caustic spot behind the object;
dappled light on the far walls.
- Quality: when the camera is still, accumulate frames in a float framebuffer
with sub-pixel jitter and thin-lens depth of field; ACES tone mapping, subtle
bloom, vignette. While moving, render one clean sample per frame. Adapt
render resolution to keep it smooth.
SHAPES
- Gummy bear from smoothly blended ellipsoids and capsules: torso, round belly,
head, two ears, snout with nose, pressed-in eyes, arms held out to the sides
with round paws, short legs with flat soles.
- Pear: two blended spheres, faint vertical ribs, top dimple, clear curved stem.
- A Bear / Pear switch that morphs one into the other by blending the two SDFs.
INTERACTION
- Drag background to orbit, wheel or pinch to zoom, arrow keys too.
- In Jelly mode, grab the figure and pull to stretch it like taffy. Grabbing a
paw, ear or leg stretches only that limb, far, without the shape folding;
grabbing the body stretches the whole part. On release it springs back with
a damped wobble. Tap to poke. The whole body also wobbles and squashes.
- Nine colors as round swatches numbered 1-9; number keys pick them; smooth
color transitions. Glass names (Cobalt, Aquamarine, Emerald, Amber, Ruby,
Rose quartz, Amethyst, Crystal, Smoke) and jelly flavor names.
- "Time outside" slider over 24 hours: sun height, direction and color, sky,
shadow length, exposure; moon and stars at night.
- Buttons: Demo 15s, Sound, Auto-rotate, Reset (view, shape, time).
SOUND (Web Audio, synthesized, soft sine tones only, no noise or harsh waves)
- Glass: mellow crystal note on touch; a quiet note per eighth-turn when rotated.
- Jelly: rounded bloop on touch, low tone following the wobble, boing on release.
- Colors 1-9 are the notes A B C# D E F# G A B.
DEMO 15s
- For exactly 15 seconds the time slider runs from start to end while the
colors play Pachelbel's Canon in D, one color per note, with a soft bass:
opening theme, eighth-note variation, then the fast running passage. The
user can keep rotating, stretching and switching material during it.
ALSO
- Responsive down to phone width, keyboard accessible, respects reduced motion,
clear message if WebGL2 is missing, remembers last shape, material and color.
Before answering, check that the shader compiles, the figure is visible on
first load, and every control listed above works.
37
Artless10 retweeted
When did AI get this good at water?
GPT-6.2 Astra. 15 minutes. $11.87
Makes you wonder how many people are going to lose their jobs…
Artless10 retweeted
Opus 5.5 is cheaper on paper than Fable 5.2, so WHY did I pay more?
same exact task, but Opus took almost 2x longer and was more expensive
Opus: 53 mins, $23.61
Fable: 31 mins, $16.61
did Anthropic quietly nerf the usage limits for Opus 5.5?
Artless10 retweeted
BLENDER OR THREE.js? A LAUGHABLE WASTE OF TIME.🤡 I CREATED THIS VIDEO FOR FREE.🙀
Here’s how:
1. The free version of ChatGPT generated reference images and wrote prompts.
2. Then ChatGPT sent them to the free Wan image-to-video demo on Hugging Face.
3. Chat itself added audio and sent me the MP4 file.
No manual editing at all. One prompt, and in 4 minutes and 20 seconds, the video was ready.😎😎
Artless10 retweeted
Holy sh*t. Fable 5.2 extra made a dancing jelly bear with its own symphony
52 minutes of work, $9 total, and the music alone is worth it.
Sound on
What song should the bear play next?
Artless10 retweeted
Did Astra 6.2 just mog Fable 5.2 at building a flight sim? 👀
$5.31 vs $22.78
What exactly are you paying 4.3× as much for?
Artless10 retweeted
I’ve got my own benchmark for Fable 5.2 - a jelly hippo 🦛
16 minutes later, I’m tossing it watermelons. It’s already eaten the first one and its face is still wobbling
What could be more reliable than a jelly benchmark?
aaa-looking game environments in the browser with Opus 5.5 + Three.js..
the look comes from a rendering pipeline, not from image gen
tuning it with math instead of gut feeling:
- step 1: opus 5.5: build a pbr pipeline in three.js from papers, talks and unreal’s published techniques
- step 2: three.js: fft ocean, physical atmosphere, global illumination, volumetric clouds
- step 3: three.js: gtao, volumetric fog, auto exposure, local tone mapping
- step 4: references: a dozen frames from real games or film stills, picked by hand for weather, time and composition
- step 5: opus 5.5: pick 7–8 sample areas per reference: sunlit grass, shaded grass, sky near the sun, distant water
- step 6: opus 5.5: measure brightness, chroma and hue in each area, then the same areas in your render
- step 7: opus 5.5: least-squares fit across 100+ points to find the parameters with the lowest error
- step 8: three.js: render, measure, adjust, repeat until the numbers match
don’t ask the ai for a “better-looking” scene. give it physics to render and numbers to hit
build a GTA Manila in Unreal Engine with Opus + Fable 5.2 + GPT-6.1 sol...
all from a $100 claude plan and a $20 chatgpt plan
the trick is spending tokens only where the player looks. here’s the workflow:
- step 1: unreal fab: grab free shaders, animations and vegetation before modeling anything
- step 2: claude: build an asset browser tool that recommends from your library first
- step 3: claude: model only the iconic locations in detail, keep everything else low-poly
- step 4: gpt-6.1 sol: critique each custom model, capped at 1–2 review loops
- step 5: references: lighting from games and films, not real-world photos
- step 6: fable 5.2: spend it only on lighting, post-processing, cutscenes and animation
- step 7: unreal: check frame sequences for flicker, z-fighting and lumen splotches
- step 8: claude: run /doctor and keep your rules loose so it can try different approaches
who does what:
> unreal fab + your library: the heavy assets
> claude: custom models, systems, the asset browser
> gpt-6.1 sol: the critic
> fable 5.2: lighting, mood, cutscenes, animation
> you: art direction and the token budget
great lighting and post can make mediocre models look good
real-world lighting references made everything look worse (dev: Gabmeister)
Everyone says Fable is overpriced. I tested it.
Same yacht idea, two Claude models:
Fable 5.2: 28 mins, $22.38
Opus 5.5: 43 mins, $18.17
$4 more, but you can see where the money went.
Top one looks better, right?
Artless10 retweeted
HOW did 53-day-old GPT Sol 6.1 cook this Jeep better than today's frontier models?
2 months ago it beat Astra 6 and Sonnet 5.5 on my "Three.js Jeep 4x4" vibe check
today I ran the exact same prompt on 3 hyped models:
- Gemini 4 Neon High: 45 minutes, 6% weekly quota
- GPT Astra 6.2 High: 24 minutes, 5% weekly quota
- Claude Opus 5.5 High: 50 minutes, 5% weekly quota
- GPT Sol 6.1 High: 3% pf weekly quota, didn't track time
genuinely asking: which output looks better to you?
Artless10 retweeted
Why are people still paying extra for Claude Opus?
I gave GPT-6.2 Astra and Opus 5.5 the same ship idea:
Astra: 17 min, $4.08
Opus: 30 min, $9.68
Almost 2x faster and more than 2x cheaper. Which one would you pick?
Artless10 retweeted
Why are people still using Blender for AI-generated 3D?
I gave Opus 5.5 High the same task twice:
Blender: 2 hours
Three.js: 28 minutes
Watch both ships and tell me which one actually wins
Artless10 retweeted
“Who even builds anything in Three.js?”
Then how do these ships look like they came straight out of Blender? 👀
Fable 5.2 and Astra 6.2 built them in code, along with the ocean, the sky, and all the sailing mechanics.
questions?
Artless10 retweeted
GPT-6.2 SOL vs Claude Sonnet 5.5 🏴☠️
Same idea: a pirate ship on the open sea.
$4.58 vs $6.36
One went for the sunset, the other went full golden hour chaos
Artless10 retweeted
Hey, @grok , make Lucia from GTA 6 in a perfect pose from the second image?
🤖 Made with AI










