Implement an LSTM cell from scratch: the four gates, the cell state, and why it beats a vanilla RNN.

A from-scratch test of gated recurrence. The signal is wiring the forget/input/output gates and candidate correctly, separating cell state from hidden state, and explaining why the additive cell path fixes vanishing gradients. Here is the implementation.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.