Aaron Tay

The Blank Box Problem: Why It's Harder Than Ever to Know What to Type Into an AI Search Bar

We’ve traded keyword constraints for infinite potential, and created a massive usability crisis in the process.

Deep Research, Shallow Agency: What Academic Deep Research Can and Can't Do"

The Agentic Illusion: Most Academic Deep Research runs fixed workflows and stumble when given unfamiliar literature review tasks that do not fit them.

What Do We Actually Mean by "AI-Powered Search"?

When we say "AI-powered search engine," we're conflating at least four different things—and your concerns about one may not apply to another.

Are AI Tools Killing Review Articles? Two Failure Modes Suggest Otherwise

arXiv recently restricted review article submissions in computer science, requiring journal or conference acceptance before deposit. They noted specifically that the change was driven by an “unmanageable influx” and that LLMs made review/position papers “fast and easy to write,” and that many were “little more than annotated bibliographies.”

A 2025 Deep Dive of Consensus: Promises and Pitfalls in AI-Powered Academic Search

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. Add advanced pre-filters and LibKey integration to institutional full-text, and it is easy to guess this will be a hit for many users doing narrative literature reviews.

Why Ghost References Still Haunt Us in 2025—And Why It's Not Just About LLMs

Ghost references existed long before LLMs. This post examines how Google Scholar's [CITATION] mechanism and web pollution may undermine RAG verification.

Aaron Tay's Musings about librarianship : How Q&A systems based on large language models (eg GPT4) will change things if they become the dominant search paradigm - 9 implications for libraries

The Sycophancy Fallacy: Why You May be Worried About the Wrong Bias with Search

AI search tools aren't "agreeing" with users—they are retrieval systems. Confusing the two is a category error that obscures the real risks.

Scholar Labs Early Review: Google Scholar Finally Enters the AI Era

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

Model Context Servers - Wiley AI Gateway & PubMed - How Claude can now pilot test search strategies using PubMed

The Model Context Protocol may fundamentally change how AI tools access academic content. Rather than AI powered search engines building massive centralised indexes, MCP allows AI models to connect directly to publisher content in a real-time federated search model. This post demostrates the use of Wiley AI Gateway and PubMed connectors when connected to Claude, showing how Claude can now pilot test search strategies for evidence synthesis using Pubmed.