A WORKING PROPOSITION / NOT AN EXPERIMENTAL RESULT
Context is treated as expensive because we repeatedly reconstruct it.
THE PROPOSED DISTINCTION
RECONSTRUCTDo the work again
Recover the earlier state through computation.
RETURNFind retained state
Pay for storage, indexing and retrieval instead.
Which costs less depends on the workload. A saving has not been measured here.
Chris Hay / Notebook / N-CONTEXT02 / 04
Every new call re-derives what a previous call already established, at real token cost, because nothing kept the earlier state in a form worth returning to. If that state were indexed rather than discarded, context stops being the scarce resource everyone budgets around.
OPEN
When does returning to state cost less than reconstructing it?
The notebook proposition needs measurements against a defined workload, including the cost of indexing and retrieval.
Chris Hay / Notebook / N-CONTEXT03 / 04
Working propositions / Working draft
Keep the question open.
A proposition and the question it raises. These passages describe what remains to be tested; they are not measured outcomes.
01Authored statementPassage 01Context is treated as expensive because we repeatedly reconstruct it.Open the passage+
Context is treated as expensive because we repeatedly reconstruct it.
02Authored observationPassage 02Every new call re-derives what a previous call already established, at real token cost, because nothing kept the earlier state in a form worth returning to. If that state…Open the passage+
Every new call re-derives what a previous call already established, at real token cost, because nothing kept the earlier state in a form worth returning to. If that state were indexed rather than discarded, context stops being the scarce resource everyone budgets around.
Retaining and indexing reusable state may change the cost of returning to earlier work. That possibility motivates the proposition that context could become more abundant.
The full account
What if context is expensive because we keep reconstructing it?
Working manuscript · v0.1
Context is treated as expensive because we repeatedly reconstruct it.
Every new call re-derives what a previous call already established, at real token cost, because nothing kept the earlier state in a form worth returning to. If that state were indexed rather than discarded, context stops being the scarce resource everyone budgets around.
OPEN
When does returning to state cost less than reconstructing it?
The notebook proposition needs measurements against a defined workload, including the cost of indexing and retrieval.
Experimental notebook / Working draft
Where this leaves the experiment
Retaining and indexing reusable state may change the cost of returning to earlier work. That possibility motivates the proposition that context could become more abundant.
The record over time
A working note
Recorded 2026-08-26. This note has no published editions yet.
Its status is OPEN; a notebook presentation does not establish a result.
An open notebook proposition: repeatedly reconstructing earlier state may be one reason context feels scarce. Indexing reusable state is a question to investigate, not an established saving.
An unpublished working record. These references identify the draft and omit a publication date. They become version-specific publication citations when the record is released.
Chris Hay. Context should be abundant. [Unpublished draft, version 0.1. First publicly recorded 2026-08-26]. https://chrishayuk.com/notebook/context-should-be-abundant
New notebook entries and recorded work, as they appear. Point a feed reader — or an agent of your own — at an address below. No account, no email address, nothing for this site to keep.
The notebook
New ideas, experiments and essays, as they are recorded. Includes labelled working drafts.
OPEN FEED↗https://chrishayuk.com/notebook/feed.xml