Knowledge base v2.13.0 · Community edition · data through 2 October 2026
Topic · AI and Search
Day 1's slide already answered an AI myth by saying there is no need to chop content, and on Day 2 Gary Illyes said the common SEO advice to chunk content for AI is misunderstood: chunking is real but matters at the level of a model's context window. He said Gemini's context window holds millions of tokens, so Gemini does not need content cut into pieces of 100 or 200 words; in the clearer wording of a second recording, once chunk size is thought of in millions of tokens, chunking has perhaps lost its meaning anyway. Author’s view: rewriting pages into short, self-contained chunks for AI brings nothing; structure content for readers. He then put the window at perhaps 900,000 to a million. Author’s view: Google's long-context docs give one million tokens or more, so plan with that as the floor. On Day 1 a community speaker linked the serial-position effect to the 'lost in the middle' pattern found in language models and advised placing the most important information at the beginning or end of content, where, in the speaker's experience on client sites, AI systems cited it more. Author’s view: that is a community heuristic, not something Google has said its systems do; a short summary at the top serves readers either way.
What to do
A community speaker linked the serial-position effect in human memory (people best remember the first and last items of a list) to the 'lost in the middle' pattern that research has found in large language models.
Speaker Jovana AvramovicIn Day 1, 16:20 · Lightning session C: CrawlingEvidence transcript
Used byglossary term Lost in the middle
A community speaker advised placing the most important information at the beginning or the end of a piece of content, because information in the middle is less likely to be cited by AI systems.
“It's relevant to put your most important information at the beginning or at the end.”
Speaker Jovana AvramovicIn Day 1, 16:20 · Lightning session C: CrawlingEvidence transcript
Placing key facts first or last is a community heuristic based on research into language models, not something Google has said its systems do; Google's own advice (D1-C054) is to write for people without chopping content, and a short summary at the top serves readers either way.
Author Ibrahim AnjroAnnotates Day 1, 16:20 · Lightning session C: Crawling
Used byglossary term Lost in the middle
Gary Illyes said the common SEO advice to chunk content for AI systems is misunderstood: chunking is real, but it matters at the level of an AI model's context window.
Speaker Gary IllyesIn Day 2, 11:30 · Understanding what's on a pageEvidence transcript
Used bymyth M-002
Gary Illyes said Gemini's context window, where chunking actually matters, holds millions of tokens.
Speaker Gary IllyesIn Day 2, 11:30 · Understanding what's on a pageEvidence transcript
Used bymyth M-002
Gemini does not need content cut into small chunks of 100 or 200 words, Gary Illyes said, since a smaller book fits in its context window.
Speaker Gary IllyesIn Day 2, 11:30 · Understanding what's on a pageEvidence transcript
Used byrequirement DEV-AIF-03myth M-002
Gary Illyes added that, once chunk size is thought of in millions of tokens as Gemini's context window allows, chunking has perhaps lost its meaning anyway.
Speaker Gary IllyesIn Day 2, 11:30 · Understanding what's on a pageEvidence transcript
Used byrequirement DEV-AIF-03
Right after saying Gemini's context window holds millions of tokens, Gary Illyes put its size at perhaps 900,000 or even closer to a million, without a unit that the recordings capture.
“the context window is perhaps 900,000 or even closer to a million big”
Speaker Gary IllyesIn Day 2, 11:30 · Understanding what's on a pageEvidence transcript
Used byrequirement DEV-AIF-03
Do not rewrite pages into short, self-contained chunks for AI systems; Google says Gemini reads context windows of millions of tokens, so structure content for readers, with clear headings and complete explanations.
Author Ibrahim AnjroAnnotates Day 2, 11:30 · Understanding what's on a page
Used byrequirement DEV-AIF-03
The talk gave Gemini's context window both as millions of tokens and as roughly 900,000 to a million; Google's long-context docs say Gemini models have context windows of 1 million or more tokens (about eight average novels per million), so plan with about one million tokens as the documented floor rather than several million.
Author Ibrahim AnjroAnnotates Day 2, 11:30 · Understanding what's on a page
Gary Illyes said the common SEO advice to chunk content for AI systems is misunderstood: chunking is real, but it matters at the level of an AI model's context window.
Myth: optimise for AI over readers. Google's answer: optimise for people, with no need to obsess over precise keywords or AI phrasing, no need to chop content, and no need for llms.txt.
Gemini does not need content cut into small chunks of 100 or 200 words, Gary Illyes said, since a smaller book fits in its context window.
Myth: optimise for AI over readers. Google's answer: optimise for people, with no need to obsess over precise keywords or AI phrasing, no need to chop content, and no need for llms.txt.
Gary Illyes added that, once chunk size is thought of in millions of tokens as Gemini's context window allows, chunking has perhaps lost its meaning anyway.
Gemini does not need content cut into small chunks of 100 or 200 words, Gary Illyes said, since a smaller book fits in its context window.
Right after saying Gemini's context window holds millions of tokens, Gary Illyes put its size at perhaps 900,000 or even closer to a million, without a unit that the recordings capture.
Gary Illyes said Gemini's context window, where chunking actually matters, holds millions of tokens.
Structure content for readers instead of splitting it into small chunks for AI
Rests on 9 claims, 4 of them in this topic
Myth: Cut your content into short, self-contained chunks so Google's AI can use it.
Rests on 4 claims, 3 of them in this topic