Attention Is All You Need by Vaswani et al.
Hacker ApprovedTied for most recommended of 7 research papers
Foundational paper introducing the transformer behind modern LLMs; essential reading. Critics find the presentation hard and the encoder-decoder design dated.
Foundational paper introducing the transformer behind modern LLMs; essential reading. Critics find the presentation hard and the encoder-decoder design dated.
16 people gave an opinion
- recommend it
- 14
- criticize it
- 2
- approval share
- 88%
Recommended in 7 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 14 people recommend itNeeds 10 or more, met.
- 7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Foundational work behind modern LLMs
“it would be the publishing of Attention is All You Need and subsequent documentation of the transformer architecture”
Comment from 30 Nov 2025 in “Tell HN: Happy LLM Day” “Transformers and their attention mechanism was the major breakthrough for modern LLMs.”
Comment from 3 Jun 2026 in “Ask HN: A Brief History of LLMs” “This seminal work, more than any other single advance, birthed modern AI”
Comment from 14 Mar 2026 in “John Carmack about open source and anti-AI activists” - Comment from 6 Jun 2026 in “How LLMs Work”
- Comment from 4 Oct 2026 in “LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents”
Essential reading for AI practitioners
“if you read the foundational paper 'All you need is Attention', review the full stack trace of any LLM system call”
Comment from 12 Jul 2026 in “Can We Understand How Large Language Models Reason?” “landmark papers which anyone interested in the field would benefit from reading”
Comment from 8 Jul 2026 in “30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format” “It's well worth a read if you haven't gone over it yet.”
Comment from 19 Sep 2026 in “US Military had close call after using AI for hallucinated intelligence report” - Comment from 26 Jul 2026 in “The new rules of context engineering for Claude 5 generation models”
Excellent original paper, highly regarded
“I have seen maybe four papers with similar impact in the AI/ML space”
Comment from 1 Nov 2025 in “Updated practice for review articles and position papers in ArXiv CS category” “I found the original paper to be excellent”
Comment from 11 Jul 2026 in “Apple Sues OpenAI for Stealing Trade Secrets to Build AI Hardware”
Other research papers people recommend
The four most recommended other research papers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Attention Is All You Need by Vaswani et al.This page | 14 | 2 | 88% | 7 | — | Approved |
| The Ironies of Automation by Lisanne Bainbridge | 14 | 0 | 100% | 7 | — | Approved |
| Structured Programming with go to Statementsby Donald Knuth | 7 | 1 | 88% | 4 | — | — |
| MapReduce: Simplified Data Processing on Large Clusters by Dean and Ghemawat | 6 | 1 | 86% | 5 | — | — |
| The Windows 95 User Interface: A Case Study in Usability Engineering by Microsoft | 6 | 0 | 100% | 2 | — | — |
What people said
15 of the 17 comments that mention it, newest first. Each links to the original comment.
“how much "Attention Is All You Need" changed things”
“It's well worth a read if you haven't gone over it yet.”
“Otherwise you won't learn anything from it.”
“if you read the foundational paper 'All you need is Attention', review the full stack trace of any LLM system call”
“I found the original paper to be excellent”
“landmark papers which anyone interested in the field would benefit from reading”
“The true ground breaking papers are the first two you mentioned”
“it describes a more complicated encoder-decoder architecture while modern LLMs are decoder only”
“Transformers and their attention mechanism was the major breakthrough for modern LLMs.”
“This seminal work, more than any other single advance, birthed modern AI”
“it would be the publishing of Attention is All You Need and subsequent documentation of the transformer architecture”
“The paper, Attention Is All You Need, solved this drawback.”
“very interesting publication that is a key for understanding the self-attention mechanism”
“the presentation is so horrible”
“I have seen maybe four papers with similar impact in the AI/ML space”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.