Oh great move! Thanks for supporting /llms.txt 😀
RESEARCH
-
Overfitting Criticism: The AI Model Performance Paradox
By
–
if they did well, you’d be complaining that they overfit
-
Advanced Reasoning Capabilities in AI Systems and Problem-Solving
By
–
Reasoning as in science, math, and hard problem-solving capabilities.
-
Visual AI Benchmark Scale From Popular Benchmarks
By
–
My experience, triangulated with all the most popular benchmarks, turned into a scale that makes sense visually.
-
LLM Model Selection Guide Based on Capabilities
By
–
The biggest question people always ask me is what model to use based on the application.
— Pietro Schirano (@skirano) 18 juillet 2025
So I made this website to give a visual representation of LLM capabilities based on my experience and benchmarks. 👇 pic.twitter.com/cdkHBLwrxIThe biggest question people always ask me is what model to use based on the application. So I made this website to give a visual representation of LLM capabilities based on my experience and benchmarks.
-
Basecamp Research Uses AI to Accelerate Drug Discovery Innovation
By
–
🍃 🧬 Basecamp Research is unlocking nature’s blueprint to accelerate breakthroughs in drug discovery, R&D, and beyond.
— NVIDIA AI (@NVIDIAAI) 18 juillet 2025
With #AI accelerated by Microsoft Azure and NVIDIA, they’re creating one of the world’s largest biological databases—fueling scientific innovation across… pic.twitter.com/iEyAwRRSNOBasecamp Research is unlocking nature’s blueprint to accelerate breakthroughs in drug discovery, R&D, and beyond. With #AI accelerated by Microsoft Azure and NVIDIA, they’re creating one of the world’s largest biological databases—fueling scientific innovation across
-
Pushing AI Into Unconventional Territories for Discovery
By
–
You've got to push AI into the weird places, because that's where the interesting stuff is
-
Wish for Technical Report on GPT-4O Attention Deficiencies
By
–
man i wish i had a technical report that specifically documented how badly gpt 4o is deficient in attention
-
Fast Vibes vs Rigorous Proof in AI Development
By
–
Vibes are fast (but not always right), proving something takes a lot longer!
