Generated by Nano-Banana Pro from text of this blog post

The recent addition of Consensus Deep Search mode is a great boost to its retrieval capabilities. On top of that, it has one of the most appealing interfaces out there, with color-coded references, and the Consensus Meter, for all its methodological faults, is likely to appeal to undergraduates and less advanced users.

ResearchRabbit shipped its biggest update in years: a cleaner iterative “rabbit hole” flow, a more configurable citation graph, and an optional premium tier.The company now “partners’ with Litmaps, which shows up in features and business model

I might be exaggerating slightly, but if you look at the few new evaluation matrices for AI-powered search circulating, “relevancy” is often just one of several categories, evaluated in a highly subjective and “I-know-it-when-I-see-it” manner. This is baffling, given that a search engine (AI-powered or not) lives and dies on its ability to retrieve relevant results.

Also call for Sponsors!

Quick catch-up to what I have been writing and thinking about

Elicit.com, Consensus, and Undermind.ai are among the new leading comprehensive cross-disciplinary “AI-powered academic search engines” today. Thanks for reading Aaron Tay's Musings about Librarianship! Subscribe for free to receive new posts and support my work.

Introduction

Introduction In my last post, I argued that Deep Search—iterative retrieval that blends keyword, semantic, and citation chasing with LLM-based relevance judgments—is the real breakthrough behind today’s “Deep Research” tools. It consistently beats one-shot embedding search in recall/precision, and in hindsight, it’s what I loved all along (the “generation” step just came bundled). The price?

Back in 2022, I was hyped about Retrieval-Augmented Generation (RAG).The novelty of seeing a search engine spit out a direct answer — with citations! — in tools like Elicit and Perplexity felt like the future. I even predicted that this “answers-with-citations” model could become the prominent paradigm for academic search. Three years later, that prediction has partly come true.

I recently gave a 30-minute talk at the Librarian Futures Virtual Summit, and for the topic of "AI-powered search," I decided to play devil's advocate.