most people still see Grok as a novelty. this thread proves it’s a productivity weapon.
LLMS
-
Two and a half years of ChatGPT appreciation
By
–
Right, I've been writing about how much I like the ChatGPT version for 2.5 years now
-
Fundamental Misunderstanding of How AI Models Work
By
–
I think you fundamentally misunderstand how these models work. Not a bad thing! But pls look into this further before commenting
-
Reasoning Models: Prompt Engineering Techniques Explained
By
–
What do you think reasoning models are doing? Basically this. 4.5 is not a reasoning model. Adding this to the prompt makes it act like one. Please try it.
-
GPT-5 Native Reasoning Eliminates Need for Chain-of-Thought
By
–
GPT-5 (all variants) can reason natively so there's no need to use this approach
-
NVIDIA praised for outstanding AI model development
By
–
Thanks to @nvidia @NVIDIAAI for making such a great model!
-
OpenRouter Powers AI Platform Innovation
By
–
Of course, it's powered by the incredible @openrouter platform 🙂
-
Nvidia Pro Mode: Open Source Nemotron 9B Chaining
By
–
Introducing: Nvidia Pro Mode!
— Matt Shumer (@mattshumer_) 10 septembre 2025
Basically GPT-5 Pro, but for the new Nvidia open source model 🙂
Pro Mode chains together up to 50 instances of the new Nemotron 9B model, enabling it to produce a better answer than one instance alone could create!
Open source, link here: pic.twitter.com/cMDzTZp9bXIntroducing: Nvidia Pro Mode! Basically GPT-5 Pro, but for the new Nvidia open source model 🙂 Pro Mode chains together up to 50 instances of the new Nemotron 9B model, enabling it to produce a better answer than one instance alone could create! Open source, link here:
-
Comparing Claude Model Performance: 5 Thinking vs Pro vs 4.5
By
–
I think about this constantly. Right now I use:
– 5 thinking
– 5 pro
– 4.5 Regular 5 sucks -
GPT-4.5 Thinking Mode Outperforms Non-Thinking GPT-5
By
–
GPT-4.5, especially when prompted to think before responding, is still such an underrated model. Way better than non-thinking GPT-5. Way better.