Looking back · SecondSource call, July 14

Enterprises can teach a general model their business through retrieval or fine-tuning; SecondSource's reading is that the two split the work rather than one replacing the other.

Concept illustration: a long white table spans the scene with an open laptop at its centre, its screen showing a speech bubble filled with lines, set in front of a pale pink rectangle. On the left, a person in black stands beside a white shelf of binders topped by a sign lettered RETRIEVAL and leans over the table to open a red-covered file with a lined page; on the right, a person in a brown jacket sits at the table with one hand on the keys at the laptop's right edge and the other holding a lined sheet of paper above a tall stack of paper at the table's right end, labelled FINE-TUNING. Printed on the image: Retrieval, fine-tuning.

Our inference: knowledge that goes stale or needs source-checking goes through retrieval, while behavior and style get trained into the model. The test is whether over 60% of enterprises in annual surveys rely on retrieval. The two routes are retrieving relevant documents at question time and handing them to the model, or training the model further on the data, which is fine-tuning.

SecondSource split the call into two checkable conditions, both read from named annual enterprise AI surveys such as a16z's. One: enterprises that use retrieval or prompting as their main way of injecting knowledge are more than 60%. Two: "injecting knowledge" is under 30% of fine-tuning uses. A share that low would mean most fine-tuning shapes behavior and style rather than teaching facts. Both thresholds and the deadline are ones SecondSource set on July 14.

This reading changes if the approach from Stanford's Cartridges work, which pre-trains a whole document set and loads it at inference time, is independently reproduced in enterprise settings at a lower total cost than retrieval. The deadline is July 14, 2027 (card, card). How we checked →

Source and checks

This item ran in the brief of Nov 5, 2026, alongside 13 other items. How we checked it, the quote checks and what was still missing that day are on that issue's How we checked page.

Cite this item

SecondSource (2026). "Enterprises can teach a general model their business through retrieval or fine-tuning; SecondSource's reading is that the two split the work rather than one replacing the other.." https://secondsource.io/en/news/2026-11-05-4/. Accessed access date.