Day 125 of the Daily · New Technology & Superintelligence

Bring Your Own Evidence

5 min read · 4 principles · apply it by lunch

Good morning. Ask it what your contract says and it’ll tell you what contracts usually say. Today you hand it yours.

The question

The last time you asked a model something that mattered, did you hand it the document or ask from memory? And if it was memory, what exactly were you checking the answer against?

The idea

In 2020 Patrick Lewis and his co-authors at Facebook AI Research, University College London and New York University published Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, and the architecture it describes is now the ordinary way a business puts a model anywhere near its own material. Their observation was structural. What a model knows is baked into its weights during training: it cannot easily be updated, it offers little insight into its own predictions, and it cannot tell you where any particular claim came from. So they attached a second memory — a searchable index of documents, retrieved at the moment of the question and handed to the model as part of the input. Answers built that way came back more specific and more factual than the same model working from its weights alone, and the passages behind each one could be opened and checked. The lesson outlives every model release, because it was never about capability. The trap is the resemblance: a recollection and a reading arrive looking exactly alike, same length, same certainty, same tidy paragraphs. Ungrounded, you’re asking for a recollection. Grounded, you’re asking for a reading, and a reading can be checked.

In the Daily · 4 principles and a template

Bring Your Own Evidence is Day 125 of 365.

In the Daily, each of its four principles is explained in full, with a one-page template to apply it the same day. A new framework arrives every morning at 7am for a year, across all fifteen courses of the FutureMBA curriculum.

$29 a month · cancel any time · 7-day money-back guarantee