Perplexity and Cross-Entropy: Measuring a Language Model
← Back to Blog & Articles Perplexity is the standard intrinsic metric for language models. It is a simple transformation of cross-entropy, and it […]
LLMs Derived, Uncategorized
LLMs Derived, Uncategorized
Rotary Position Embeddings: Encoding Position as Rotation
← Back to Blog & Articles Attention by itself has no sense of word order. Rotary position embeddings, or RoPE, add order by rotating […]
The AI Algorithms Compendium, Uncategorized
STRIPS Planning: Describing Actions by Preconditions and Effects
← Back to Blog & Articles Automated planning needs a way to describe what actions do. STRIPS gives a compact answer: each action lists […]
The AI Algorithms Compendium, Uncategorized
Designing Admissible Heuristics for A*
← Back to Blog & Articles A* is only as good as its heuristic. Understanding what makes a heuristic safe, and how to build […]
The AI Algorithms Compendium, Uncategorized
Constraint Satisfaction: Why Backtracking Needs Inference
← Back to Blog & Articles Many puzzles, such as Sudoku and N-Queens, are constraint satisfaction problems. Plain backtracking can solve them, but adding […]
The AI Algorithms Compendium, Uncategorized
Minimax and Alpha-Beta Pruning: Searching Games Without Visiting Every Move
← Back to Blog & Articles Minimax lets a program choose moves in two-player games by assuming both sides play as well as they […]
Algorithmic Edge, Uncategorized
Amortized Analysis: Why Dynamic Arrays Still Append in O(1)
← Back to Blog & Articles A dynamic array sometimes has to copy all its elements, yet we say appending is O(1). Amortized analysis […]
Algorithmic Edge, Uncategorized
Merge Intervals: Sort First, Then Sweep
← Back to Blog & Articles Interval problems look varied, but many reduce to one idea: sort by start time, then sweep through once […]
Algorithmic Edge, Uncategorized
Fast and Slow Pointers: Detecting Cycles Without Extra Memory
← Back to Blog & Articles The fast and slow pointer pattern uses two pointers that move through a sequence at different speeds. It […]
Algorithmic Edge, Uncategorized
The C.L.E.A.R. Framework: A Repeatable Way to Start Any Interview Problem
← Back to Blog & Articles Interviewers reward a visible process, not just a final answer. The C.L.E.A.R. framework in Algorithmic Edge gives you […]