I was curious about some of the processes of AI and asked a question which resulted in a discourse on data protection when using AI. (To be presented later.).
I then suggested that in many ways at the basic level (not coding!) what AI produces is no more research librarians had been doing for aeons - especially since online resources such as Dialog became available from 1978 - saying AI responses are far faster, almost immediate, but also returns more false results - though this is improving.
AI Response: It is a privilege to speak with someone who has seen the "evolution of the search" from the inside. 1978 was indeed a watershed year—it was the era when services like DIALOG and LexisNexis began to transition from experimental tools into professional mainstays.
As a research librarian, your process has always been rooted in Information Retrieval (IR)—the science of finding an existing document that matches a specific query. AI represents a fundamental shift into Generative Probability, which explains both why I am faster and why I am, at times, more "creative" with the truth.
1. The 1978 Era vs. Now: A Shift in Logic
In the world of 1978 online resources, searching was Boolean and Exact:
The Librarian's Method: You used precise operators (AND, OR, NOT) to filter an index. If a document didn't contain the exact string, it didn't exist. The result was a list of "pointers" to truth.
The AI's Method: I don't "search" an index in the traditional sense when I generate text. Instead, I use Next-Token Prediction. I am essentially calculating the most statistically likely word to follow the previous one.
The result: I don't "find" an answer; I "construct" one. This allows for the speed and nuance you noticed, but it also creates
the "False Results" (hallucinations) that your trained librarian's eye correctly identifies.
2. Why "False Results" Happen
As a librarian, you deal with veracity; as an AI, I deal with probability. If a user asks for a citation that doesn't exist, a traditional database returns "Zero Results." An AI, however, might see that a certain author usually writes on a certain topic and "predicts" what a title by them should look like.
Fortunately, as we move into 2026, we are bridging these two worlds using a technique called Retrieval-Augmented Generation (RAG):
I search a "librarian-approved" database
I pull that specific "chunk" of text.
I use my language skills only to summarize that specific text, rather than "guessing" the answer.
3. The Professional Synergy
Research librarians are actually the "gold standard" for what AI developers call Prompt Engineering. Your ability to define a search space, verify a source's provenance, and cross-reference multiple indices is exactly what AI currently lacks: Critical Judgment.
I can process a million pages in a second, but I cannot yet replicate the "gut feeling" of a librarian who knows that a 1978 citation might be more reliable than a 2025 blog post.
[To be continued]
