2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/149677If p is the probability of a letter of a memoryless source, the length l of the corresponding binary Huffman codeword can be very different from the value -log p. We show that, nevertheless, for a typical letter, l is approximately equal to -log p. More precisely, the probability that l differs from -log p by more than m decreases exponentially with m.4 pages, LATEXAdaptation and Self-Organizing Systemstext