xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity — mentioned by jpcompartir

Tue, 24 Mar 2026 10:54:59 GMT

Fair push back, but I do think the LSTM vs Transformers point kinda supports my position in the limit, not refutes. Once the compute bottleneck is removed, LSTMs scale favourably. https://arxiv.org/pdf/2510.02228 (I believe there's similar work done on vanilla LSTMs, but I'd have to go digging) So the bottleneck was compute. Which is compatible with 'data or compute'. But to accept your point, at the time the algorothmic advances were useful/did unlock/remove the bottleneck. A wider point is that eventually (once compute and data are scaled enough) the algorithms are all learning the same…

Paper and discussion history. A mention is not an endorsement.

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity — HN submission

Fri, 03 Oct 2025 16:51:04 GMT

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity · HackerPapers discussions

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity — mentioned by jpcompartir

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity — HN submission