Language Models Use Trigonometry to Do Addition · HackerPapers discussions

Language Models Use Trigonometry to Do Addition — mentioned by dvt

Fri, 02 Oct 2026 19:28:29 GMT

> So Jev does actually know which distributions are correct, it just fails to produce them Claims like this needs to be deeply analyized. Models do have some emergent capabilities[1], and I think there's a lot of evidence to show that semantics is actually learned (Word2Vec), and some math seems like it also might be learned (e.g. modular arithmetic). But it's hard to exactly say where there's some internal mechanism generating a true answer and where we're just getting lucky with some distribution so the answer just seems right. [1] https://arxiv.org/pdf/2502.00873

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

Language Models Use Trigonometry to Do Addition — mentioned by strangecasts

Sat, 19 Sep 2026 00:04:54 GMT

> If you look at the field of mechanistic interpretability, compared to “GOFAI” like learned decision trees, an LLM is completely opaque. I think the field deserves more credit than that, there are plenty of interpretability tools like * natural language autoencoders for explanations of activations: https://transformer-circuits.pub/2026/nla/index.html (demo at https://www.neuronpedia.org/llama3.3-70b-it/nla ) * easier-to-interpret language model families like Backpack models: https://aclanthology.org/2023.acl-long.506/ * attribution graphs to trace internal reasoning steps…

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

Language Models Use Trigonometry to Do Addition — mentioned by dist-epoch

Mon, 17 Aug 2026 06:47:00 GMT

There have been multiple studies on how LLMs add numbers. They use the "Clock" algorithm, the "Pizza" algorithm, a few other ones. > All networks we study implement the same simple neuron model in their first-layer MLPs: degree-1 sinusoidal fits in layer 1, with deeper layers combining into degree-2 sinusoidal interactions. https://neurips.cc/virtual/2025/loc/san-diego/133808 https://arxiv.org/abs/2502.00873 When you ask them they don't mention these at all, they give you high-school math: https://chatgpt.com/share/6a82afdd-872c-83eb-aad7-622d27f2dc... > did you use the "cos" or "sin"…

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

Language Models Use Trigonometry to Do Addition — mentioned by photonthug

Thu, 23 Oct 2025 22:59:56 GMT

Glad to see the pentagonal multiplication prism is just as weird as the addition helix https://arxiv.org/abs/2502.00873

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

Language Models Use Trigonometry to Do Addition — mentioned by EMIRELADERO

Sat, 12 Apr 2025 02:28:45 GMT

> The LLM can't describe it, it doesn't see inside itself, however, it has many textbooks in its training dataset, so it will grab an answer from these textbooks because that's how people answer. EDIT: I see now that you were referring to the answers it uses to justify the result, not the underlying computations. Sorry! You can disregard the actual comment. Leaving for completeness. ORIGINAL COMMENT: That's not how it works. Addition in LLMs is believed to function through different mechanisms depending on model size and architecture, but the single consistent finding across different models…

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

Language Models Use Trigonometry to Do Addition — mentioned by joelburget

Thu, 06 Feb 2025 21:41:56 GMT

And more recently, [Language Models Use Trigonometry to Do Addition](https://arxiv.org/abs/2502.00873)

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

Language Models Use Trigonometry to Do Addition — HN submission

Tue, 04 Feb 2025 14:41:12 GMT

Language Models Use Trigonometry to Do Addition

1 point; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.