Artless10 (@PromptRumble) header
Artless10 (@PromptRumble) profile picture

Testing AI models so you don't have to. Real prompts, side-by-side results, honest takes on what actually works.

France
Joined May 2023
Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)Photo by Artless10 (@PromptRumble)
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.
9
6
20
906
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
11
12
1
22
932
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…
31
12
152
5,257
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?
10
4
20
1,412
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.😎😎
4
4
6
307
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?
4
4
11
560
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?
36
32
6
326
19,978
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?
14
13
2
85
3,586
Artless10 retweeted
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)
44
34
5
649
54,891
HERE'S HOW Astra 6.2 Draws Valentina from GTA 6
2
2
4
309
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?
17
8
94
5,637
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?
10
5
44
3,212
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
123
17
7
744
114,746
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?
24
12
96
3,512
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
2
3
16
639
Hey, @grok , make Lucia from GTA 6 in a perfect pose from the second image?
🤖 Made with AI
4
1
2
309
Artless10 retweeted
holy sh*t, this snow globe just gave me Christmas vibes in November 🎄❄️ Sonnet or Opus? 👇
4
5
13
628
Artless10 retweeted
I asked ChatGPT-6.2 Astra for a robot that saves the last plant on Earth 🤖 It gave me this. For $24.69. Pixar should be nervous? 👀
4
5
16
911
Artless10 retweeted
Lucia’s booty is straight fire 🔥 GTA 6 looks incredible
5
82
11,790
Artless10 retweeted
Be honest, who noticed Mandy from GTA 6 was holding a watering can on the first swipe? 👀
4
7
1
23
3,758