Sabitlenmiş Tweet
nadya
280 posts
Grok 4.5 crushed OpenAI & Meta in this test!
Cost per run:
GPT Sol $1.63
Grok 4.5 $2.47
Meta Muse Spark 1.1 $1.08
The three prompts:
• Fruit Ninja – style slicing game
• Angry Birds – style fort collapse
• Crossy Road clone
Grok nailed all three: clean physics, smooth playback, good visuals. GPT Sol did fine until Crossy Road, where it froze. Meta Muse Spark was cheapest and it showed: its Crossy Road lagged badly.
The question isn't which model is cheapest, it's what a broken output costs you in reruns, wasted time, and things you can't ship. Cheap stops being cheap when it doesn't work.
English
@testingcatalog these comparisons are kind of dumb bc theres no clear way of telling the difference and deciding which did it better and the things they each make are basically the same and just as slop as each other
English
Grok 4.5 and Muse Spark 1.1 are now available on the AI/ML platform for testing.
What a week; all 3 models in the comparison dropped just recently. There will be a lot to experiment with.
AI/ML has tested the new models on prompts for playable mini-games, including a Fruit Ninja-style slicer and a Crossy Road clone. All three are live in the Playground and via API for side-by-side runs on output and cost.
AI/ML API@aimlapi
Grok 4.5 crushed OpenAI & Meta in this test! Cost per run: GPT Sol $1.63 Grok 4.5 $2.47 Meta Muse Spark 1.1 $1.08 The three prompts: • Fruit Ninja – style slicing game • Angry Birds – style fort collapse • Crossy Road clone Grok nailed all three: clean physics, smooth playback, good visuals. GPT Sol did fine until Crossy Road, where it froze. Meta Muse Spark was cheapest and it showed: its Crossy Road lagged badly. The question isn't which model is cheapest, it's what a broken output costs you in reruns, wasted time, and things you can't ship. Cheap stops being cheap when it doesn't work.
English
A YC Company knocked off and stole my work 1:1.
And this could happen to you next. Here's what happened 👇
2 days back @21st_dev launched an ASCII tool which was completely a ripoff of ascii-magic.com
Everything from properties, effects, features, presets and even backgrounds were literally scraped off and used exactly.
When I called out this mess, the founder got his ego hurt and unfollowed me instead of addressing the blatant copying.
I'd probably not have been this upset if it was a solo designer trying to learn, experiment, or make a quick buck on the side. People learn by rebuilding things all the time.
But this is a funded YC company.
A company with resources.
A company with a grown man as a founder.
A company that absolutely knew what it was doing.
And yes, before anyone jumps in to defend this, they knew exactly what they were doing. You can tell if you looked at their tool for 5 seconds.
The fact that a YC-backed company can use AI to rip off a free tool, launch it publicly, and then refuse to acknowledge or address it is seriously alarming.
Makes me think if this goes unchecked, they could (or have been doing this idk) do this to anyone in the future. So as a community, it is necessary we hold folks accountable.
Thanks,
Kailash
English
@testingcatalog its subjective taste between Fable and Sol for most of these But when you then introduce the cost consideration.. Sols nailed it 👏
English
AI/ML API has added OpenAI's new GPT-5.6 models, Sol, Terra, and Luna, to its catalog of 1000+ models, all under the same API key.
Users can run the new model in the Playground or via the API and test it against the rest of the stack without changing the setup.
Who is winning? 👀
AI/ML API@aimlapi
GPT 5.6 Sol & Terra just made Fable 5's pricing look like a joke! We gave OpenAI's top models (Sol, Terra) and Anthropic's top models (Fable 5, Opus 4.8) the same 3 prompts: • Supernova boom • Meteor hitting a city • Solar system model The bill: Sol: $4.77 Terra: $1.24 Fable 5: $9.94 Opus 4.8: $2.46 Outputs came out surprisingly close. The prices didn't. Fable 5 cost unreasonably more than everything else, with Sol not far behind. Considering latest Fable 5 nerf, it's hard to see what you're paying for.
English
GPT 5.6 Sol & Terra just made Fable 5's pricing look like a joke!
We gave OpenAI's top models (Sol, Terra) and Anthropic's top models (Fable 5, Opus 4.8) the same 3 prompts:
• Supernova boom
• Meteor hitting a city
• Solar system model
The bill:
Sol: $4.77
Terra: $1.24
Fable 5: $9.94
Opus 4.8: $2.46
Outputs came out surprisingly close. The prices didn't. Fable 5 cost unreasonably more than everything else, with Sol not far behind. Considering latest Fable 5 nerf, it's hard to see what you're paying for.
OpenAI@OpenAI
Sol, Terra, and Luna, our GPT‑5.6 family of models, are starting to roll out now in ChatGPT, Codex, and the API.
English
@made_by_keegan @aimlapi I think the person who generated these prompts also had such dreams
English
@aimlapi fable trained on the type of visuals i see in my dreams 🤣
English
Grok 4.5’s take.
Grok is the best at 3D.
Look at this solar system animation
AI/ML API@aimlapi
GPT 5.6 Sol & Terra just made Fable 5's pricing look like a joke! We gave OpenAI's top models (Sol, Terra) and Anthropic's top models (Fable 5, Opus 4.8) the same 3 prompts: • Supernova boom • Meteor hitting a city • Solar system model The bill: Sol: $4.77 Terra: $1.24 Fable 5: $9.94 Opus 4.8: $2.46 Outputs came out surprisingly close. The prices didn't. Fable 5 cost unreasonably more than everything else, with Sol not far behind. Considering latest Fable 5 nerf, it's hard to see what you're paying for.
English
@knowix_eth @testingcatalog honestly, i hate ChatGPT, but fable was awful in this comparing
English
@sosidudku atomic models -> atomic agent. i ve seen same sequence in nous research story :))
English
github.com/AtomicBot-ai/a…
i hate hermes and openclaw
i love atomic agent
English