They do this with GPT-4.5 too by the way, any time search is needed
— Matt Shumer (@mattshumer_) 26 septembre 2025
So annoying https://t.co/FC1kGu9T4j
They do this with GPT-4.5 too by the way, any time search is needed So annoying
@mattshumer_
-
GPT-4.5 Search Limitations Frustrate Users
By
–
-
AI UI Design Benchmark: Rork Dominates Mobile Interface Competition
By
–
AI is *dogshit* at designing UIs Now there's a benchmark measuring AI interface design capabilities! Unsurprisingly, @rork leads the mobile version, by far, beating Bolt by almost 20%
-
Flork Dominates Charts with New iPhone App Development Platform
By
–
Rork continues to top the charts! The team is shipping at an insane pace. And usage is now moving from web -> iPhone. The iPhone app to build iPhone apps is here!
-
Ray3 Struggles with Baseball Batter POV Video Generation
By
–
watching ray3 try to get this right is almost endearing…
— Matt Shumer (@mattshumer_) 19 septembre 2025
prompt: "Batter's POV at a MLB game. A pitch is thrown, but it's going to hit the batter, so he drops to the ground." pic.twitter.com/KAFwJZhvXawatching ray3 try to get this right is almost endearing… prompt: "Batter's POV at a MLB game. A pitch is thrown, but it's going to hit the batter, so he drops to the ground."
-
What is Luma Labs doing in their latest thumbnail?
By
–
what in the thumbnail is luma labs doing here?
-
Testing Ray3 Video Generation Model on Swordfight Physics
By
–
One of my favorite ways to test a video generation model is to ask it to generate a swordfight scene.
— Matt Shumer (@mattshumer_) 19 septembre 2025
The physics are *really* hard to get right.@LumaLabsAI's Ray3 still falls quite short of passable quality, but it's by far the best model I've tried. pic.twitter.com/B2Wl3DXGACOne of my favorite ways to test a video generation model is to ask it to generate a swordfight scene. The physics are *really* hard to get right. @LumaLabsAI
's Ray3 still falls quite short of passable quality, but it's by far the best model I've tried. -
Codex struggles with intent and requires explicit prompts
By
–
It’s honestly struggled with intent (and makes dumb mistakes) even on small tasks where the things I leave out of the prompt feel quite obvious. I really have to spell everything out every time, and it gets quite annoying haha I think if you could combine Codex’s raw horsepower
-
GPT-5-high versus Codex: Model Selection Strategy
By
–
To be clear, right now, GPT-5-high is my daily driver, but when I have a great spec and feel like I have a really great, bulletproof prompt, I switch to Codex.
-
GPT-5-Codex Performance: Mastering Detailed Prompt Techniques
By
–
I've been testing the new GPT-5-Codex model pretty heavily. Here's my current thinking: Is it better overall than regular GPT-5 high? Absolutely not. But if you use it right, it can outperform vanilla GPT-5 high. What I mean: If you write insanely detailed prompts
-
User requests access to test worldgen model
By
–
Hey @theworldlabs can I get access to test your worldgen model?