Levenshtein distance
String edit distance metric used for alignment
Episodes
-
#6305: Why Terminal Fuzzy Finders Forgive Different MistakesFred Damerau found that over eighty percent of spelling errors in retrieval systems were a single insertion, deletion, substitution, or transposition. -
#4958: Multi-Model Transcription with LLM ReconciliationUsing multiple transcription engines and an LLM judge to catch errors in voice-to-text — especially tricky technical terms. -
#4603: The Hidden ID System Behind Every FlightPNRs, e-ticket numbers, and the name match that decides if you fly. Here's how airline booking records actually work. -
#109: Beating Context Bloat with Dynamic DictionariesTired of AI mishearing brand names? Learn how to build efficient custom dictionaries for Gemini 1.5 without breaking the bank.