While in the past several decades the trend to go towards increasing error-correcting code lengths was predominant to get closer to the Shannon limit, applications that require short block length are developing. Therefore, decoding techniques that can achieve near-maximum-likelihood (near-ML) are gaining momentum. This overview paper surveys recent progress in this emerging field by reviewing the GRAND algorithm, linear programming decoding, machine-learning aided decoding and the recursive projection-aggregation decoding algorithm. For each of the decoding algorithms, both algorithmic and hardware implementations are considered, and future research directions are outlined.