Mamba-3: Improved Sequence Modeling using State Space Principles · HackerPapers discussions

Mamba-3: Improved Sequence Modeling using State Space Principles — mentioned by imtringued

Mon, 26 Oct 2026 12:08:36 GMT

No my point is more general. The headline promises me that I don't need attention based transformers, then you see the benchmarks and they tell you they got 10% worse perplexity. How is that going to convince me that I don't need attention? I mean if you look at e.g Mamba 3 [0] (see page 12 and 14 for benchmarks), the perplexity is roughly the same and the benchmark scores are roughly the same. If you tell me attention doesn't matter you have to convince me by showing that you can get the same performance with a variety of architectures. In short, I would have expected the paper to be a…

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

Mamba-3: Improved Sequence Modeling using State Space Principles — mentioned by anentropic

Sat, 21 Mar 2026 15:27:12 GMT

More here https://news.ycombinator.com/item?id=47423208 https://arxiv.org/abs/2603.15569

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

Mamba-3: Improved Sequence Modeling using State Space Principles — HN submission

Wed, 18 Mar 2026 08:44:19 GMT

Mamba-3: Improved Sequence Modeling Using State Space Principles

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.