Acing AI — AI education, tutorials, research and datasets for data scientists
Your Skill Scanner Reads the File, Not the Execution
An agent skill scanner is an eval, and its leaderboard score is pass@1 against an adversary who rewrites the input. Why the eight-scanner bypass was inevitable.
Latest Intelligence
Curated technical papers and hands-on implementation guides for the modern AI engineer.
Ten Proofs, Zero Sorries: What an AI Proof Certificate Actually Settles
An AI proof certificate asks you to trust nothing. Using OpenAI's Astra Lean 4 proofs, how a machine-checkable certificate settles the claim and says nothing about the model.
Your LLM Serving Bottleneck Moved to the CPU
vLLM v0.27.0 and SGLang v0.5.17 rewrote their serving frontends in Rust. The real LLM serving bottleneck is often the CPU-bound Python frontend, not the GPU.
ArticleQwen3.8-Max Open Weights: The Checkpoint You Download Is Not the Model You Tested
ArticleAgent Plugin Security: What a Plugin Can Reach in an npm Agent Runtime
ArticleThe Harness Was the Closed Part: What an Open Agent Runtime Actually Buys You
Browse by Type
Tutorials
Step-by-step guides from neural network basics to advanced LLM fine-tuning.
Research Papers
Peer-reviewed insights and white papers defining the frontier of artificial intelligence.
Datasets
High-fidelity training sets for natural language processing and computer vision.
Start Learning
Guided sequences through our best content — structured to build understanding from the ground up.
Post-Training Modern LLMs
Pretraining produces a model that predicts text. Post-training is what turns it into something you can ship. This path walks the levers in the order you would actually reach for them: supervised fine-tuning and adapters, preference optimization without a reward model, the reinforcement-learning map from RLHF to verifiable rewards, RL against a verifier that cannot be talked out of its answer, and finally the inference-time compute that picks up where training leaves off. Every step names the ceiling it runs into.
Evaluating LLMs Honestly
A leaderboard number is a hypothesis, not a result. This path builds the habit of asking what a benchmark measured before quoting what it reported, starting with contamination and judge bias, moving through a case where the advertised figure and the measured one diverge, then to agents where a single passing run tells you almost nothing, and ending where the eval harness itself turns into attack surface.