Methods · Support & cognitive load
A15
Reading-level laddering
Meet a hard source at a simpler level first, then return to the original and notice exactly what the simplification removed, so difficulty becomes a ladder, not a wall.
When to use it
- You are meeting this idea for the first time and need a way in.
- The reading feels dense and you want a first map before the details.
- You know the finished idea but not why anyone fought over it, so it will not stick.
What to ask AI
Type something like: “I need to read this source but I'm bouncing off it. Rewrite at roughly”.
Tell it your current level and ask it to stay one step harder than comfortable.
Keep the hard part on your side: you retrieve, attempt, explain, or decide before you ask for help.
How it helps
Some texts are hard because the ideas are hard.
Some are hard because the prose, notation, or assumed vocabulary is hostile.
Students often quit at the second kind and conclude they can't handle the first.
Read a calibrated simpler version to get the shape, then climb back to the original with that shape in hand. The learning is not in the easy version, staying there is the misuse.
The learning is in the return: what was compressed, what was hedged, what precision you can now see.
AI makes on-demand intermediate rungs possible.
A textbook either had a "for beginners" chapter or it didn't.
You can now ask for a rung, then another, then the primary source.
How to run it
- Name the hard source (paper, chapter, judgment, proof).
- Ask for one rung down, not five. Specify audience carefully.
- Read the simpler version actively: outline its claims (Works well alongside Advance organisers).
- Return to the original immediately. Same sitting if possible.
- Next: annotate differences: vocabulary, hedges, quantitative precision, omitted objections.
- Next: optional second rung only if the original still won't parse, then climb again. Do not collect easy versions as a substitute library.
Example exchange
I'm bouncing off this abstract on CRISPR. Rewrite it for a strong high-school reader, then list what you removed. Don't add new claims.
Simpler version: researchers use a bacterial cutting system to edit DNA at chosen sites. I removed the hedges about off-target rates and the named enzyme variants. What do you want to restore first when you return to the original?
The off-target part, that's what my seminar keeps arguing about.
Good. Read only that section of the original next, with the simple version still in mind.
Copyable prompt
I need to read this source but I'm bouncing off it. Rewrite at roughly
[AUDIENCE] level, preserving the main claims and structure. After the rewrite,
list what you simplified or omitted, especially hedges, numbers, and
counterarguments. Do not add new claims.
SOURCE: [paste or citation]The Tell
Here is how you know this method has flipped: you can explain the topic fluently from the rewrite and freeze on a quoted sentence of the original.
In that moment the AI (or the schedule, or the story) did the thinking, and you only recognised a finished product.
Tighten the prompt for reading-level laddering so you attempt, decide, or retrieve before anything is handed to you.
Principle evidence
Strength of the underlying learning idea, not a claim about AI products.
The underlying learning idea is rated moderate. Simplified-then-original reading relates to comprehensible input (Krashen, contested as a full theory), text simplification research, and scaffolding toward authentic sources. Returning to the hard text is the load-bearing step for transfer. Principle moderate; AI simplification fidelity speculative.
AI delivery evidence
Whether an AI tutor delivers this method well is a separate question.
The learning principle may be moderate, but that does not prove an AI session delivers it well. Treat AI delivery as speculative unless a study of tutoring with this method is named, and none is claimed here.