corpus.blog
41554 blogs · 4,756,248 posts Claim your blog
Record · corpus.blog/posts/01a08763-8470-73b2-8a20-38f0f019f9c5

Perception, intention, and poetic license: What is the attention mechanism that powers LLMs?

The Content Technologist | Content strategy newsletter & website, publishing since 2019. · published 7 September 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at content-technologist.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
14
Words captured
2,430

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
How does AI make sense of language? Read at the source ↗
content-technologist.com
Disambiguation, sliding doors, hallucinations, and madeleines: How transformers process, clarify, and produce language Read at the source ↗
content-technologist.com
https://arxiv.org/abs/1706.03762?ref=content-technologist.com
arxiv.org
https://arxiv.org/abs/1409.0473?ref=content-technologist.com
arxiv.org
https://www.wired.com/story/eight-google-employees-invented-modern-ai-transformers-paper/?ref=content-technologist.com
wired.com
https://www.google.com/books/edition/The_Attention_Economy/j6z-MiUKgosC?hl=en&ref=content-technologist.com
google.com
https://youtu.be/SYKpbC2Ur1Y?si=TKIZtx_IY0GbwFwQ&t=32&ref=content-technologist.com
youtu.be
https://www.nytimes.com/2024/11/29/podcasts/hardfork-iconic-100-technologies.html?ref=content-technologist.com
nytimes.com
https://www.newyorker.com/tech/annals-of-technology/chatgpt-is-a-blurry-jpeg-of-the-web?ref=content-technologist.com
newyorker.com
https://maxread.substack.com/p/studio-ghibli-in-the-age-of-ai-reproduction
maxread.substack.com
https://en.wikipedia.org/wiki/Grokking_(machine_learning
en.wikipedia.org
https://www.theatlantic.com/technology/archive/2025/08/gpt-5-launch/683791/?ref=content-technologist.com
theatlantic.com
When words and math collide: Old-school tried and true language processing algorithms Read at the source ↗
content-technologist.com
Tokens and vector embeddings: The first steps in calculating semantics for LLMs Read at the source ↗
content-technologist.com