I can offer you the metadata in YAML format: https://
github.com/rasbt/llm-arch
itecture-gallery
…
Happy tinkering!
RESEARCH
-
LLM Architecture Gallery with YAML Metadata Available
By
–
-
EverMind publishes high-quality AI research paper this week
By
–
Just a slight spoiler, @EverMind will publish another high-quality paper this week.
-
Defining Agentic Engineering: Chapter 12 Guide
By
–
Just added the 12th chapter to my Agentic Engineering Patterns guide, but it's the first one in the sequence: I figured it was time to try and answer the obvious question, "What is agentic engineering?"
-
RAG Deployment Gap: Model Capability Versus Production Reality
By
–
Benchmarks go up every month but most companies still can't get a basic RAG pipeline to work reliably. There's really a big gap between model capability and actual deployment.
-
Therapy Efficacy in Buying Time for Treatment
By
–
Actually, buying some more time is a key goal of all therapies of this type. So it seems fairly clearly stated that it did, in fact, work.
-
Evidence Levels and n=1 Experimentation in AI Evaluation
By
–
You seem over-indexing on "Everything here could have been done without ChatGPT". But that's the least interesting bit. We don't "need to prove this before anyone can believe" – there are levels of evidence short of proof. We don't need "clear, resounding successes" to try n=1
-
Nemotron’s Intentional Limitations in AI Model Design Strategy
By
–
i have a pet theory that Bryan and co cannot make Nemotron TOO good bc otherwise it would scare off customers. it needs to be “good enough to reflect everyone’s baseline consensus on SOTA techniques to lower the bar for neolabs + be maximally useful for synthetic data bc that is
-
Symbolic Learning Development at Ndea
By
–
What we're developing at Ndea. We call it symbolic learning.
-
Kimi K2.5 Model Optimization on NVIDIA Blackwell Hardware
By
–
What does relentless optimization in AI inference look like? Watch the rapid evolution of the Kimi K2.5 model on the @ArtificialAnlys leaderboard. Inference endpoint providers are continually pushing boundaries on NVIDIA Blackwell, leveraging custom optimizations, NVFP4,
-
AI and cognitive skills: beyond the calculator panic narrative
By
–
47% is a bit alarming TBH. Though I wonder if this is the same panic we had about calculators killing math skills. The question is what we do with the freed-up cognitive bandwidth.