AimPapers
The Journal
Why AI Fabricates Citations (and How to Verify Every One)
A fabricated citation looks exactly like a real one: same format, same confident tone, same plausible journal name. Understanding why models invent sources — and what real verification actually costs in time — is what keeps a fake reference out of your bibliography.
What an AI Research Workflow Actually Costs in Tokens
Providers bill by the token, not by the request, and input and output are priced separately. Here is how to turn a realistic writing workflow into an actual token-and-cost estimate — using your own numbers, not a headline price that will be out of date by the time you read this.
What Readability Scores Actually Measure — and What They Miss
A Flesch score is precisely defined arithmetic on sentence length and syllable count, nothing more. Run it on three real passages and the numbers make the formula's real behavior obvious — including exactly where it stops being useful advice.
Words to Pages, Honestly: Why the Question Is Underspecified
"How many pages is 2,500 words?" has no single answer until you say what font, spacing, and margins you mean. Here is the actual arithmetic behind a page-count estimate, worked both directions, and why every number it gives you is a starting point rather than a promise.
Planning Writing Time Realistically (Not Optimistically)
Typing speed and writing speed are different numbers, and the gap between them is where most schedule failures come from. Here is the arithmetic for turning a word-count target into an honest hours-and-days plan — worked at three different paces so you can see how much the assumption matters.
Summarization Ratios: What a Compression Number Actually Tells You
A summary that keeps 8% of a source's words is a fundamentally different object from one that keeps 50%. Working the actual ratios for a few compression levels makes it obvious what kind of loss is happening at each one — and why a smooth read is not evidence that nothing important was cut.
Use AI for Structure and Stuck Points, Not for Prose
The most defensible way to use AI in serious writing has nothing to do with having it write sentences for you. Outlining, unsticking, and pressure-testing are where it earns its keep — and, worked through the actual token arithmetic, the case for going further is weaker than the sticker price suggests.
Disclosing AI Use to Your Institution, Honestly and Specifically
"I used AI a little" tells a reader nothing they can act on. A disclosure statement that names what you used it for, and what proportion of your final document it touched, is both more defensible and considerably easier to write than a vague one.
Using AI to Draft, Not to Cheat
AI can accelerate a first draft or help you think through a hard paragraph, but the moment you stop engaging with the ideas, it becomes a shortcut that hurts you. Here is where the line sits.
How to Check the Citations an AI Gives You
Language models are notorious for producing citations that look perfect and do not exist. Here is a practical, repeatable process for verifying every reference before it reaches your bibliography.
Prompt Patterns for Serious Research
Vague prompts get vague, confident, and often wrong answers. These reusable prompt patterns keep an AI honest and useful during real research, while leaving the judgment where it belongs — with you.
Summarizing Long Papers Without Losing the Argument
AI summaries are great at compressing text and terrible at preserving nuance. Here is how to use them to read faster without flattening the argument, dropping the caveats, or trusting a distortion.