← Feed

Posts

• Post #1300820

  [blogged] How Q&A/search systems based on large language models (eg GPT4) will change things if they become the dominant search paradigm - 9 implications for libraries https://musingsaboutlibrarianship.blogspot.com/2023/03/how-q-systems-based-on-large-language.html - me on just ONE use of large language models

• Post #460775

  [Last blog post of 2025] "AI-powered search" hides at least 4 different things—post-retrieval features, semantic search, LLM ranking, and synthesis. Your concerns about one may not apply to another. New post unpacking what's actually under the hood. https://aarontay.substack.com/p/what-do-we-actually-mean-by-ai-powered

• Post #460773

  Why Ghost References Still Haunt Us in 2025—And Why It's Not Just About LLMs https://aarontay.substack.com/p/why-ghost-references-still-haunt . I'm not too sure about this one , it's probably underplaying the role of LLMs in ghost references but still interesting.

• Post #460771

  [Blogged] Deep Research, Shallow Agency: What Academic Deep Research Can and Can't Do - The Agentic Illusion: Most Academic Deep Research runs fixed workflows and stumbles when given unfamiliar literature review tasks that do not fit them. https://aarontay.substack.com/p/how-agentic-are-academic-deep-research

• Post #460769

  [Blogged]Model Context Servers - Wiley AI Gateway & PubMed - How Claude can now pilot test search strategies using PubMed https://aarontay.substack.com/p/mcp-servers-and-academic-search-the

• Post #460767

  [Blogged] Scholar Labs Early Review: Google Scholar Finally Enters the AI Era https://open.substack.com/pub/aarontay/p/scholar-labs-early-review-google?l

• Post #460766

  [Blogged] A 2025 Deep Dive of Consensus: Promises and Pitfalls in AI-Powered Academic Search https://aarontay.substack.com/p/a-2025-deep-dive-of-consensus-promises

• Post #460765

  [Blogged] Why It's Harder Than Ever to Know What to Type Into an AI Search Bar. https://open.substack.com/pub/aarontay/p/the-blank-box-problem-why-its-harder Edit: An earlier version of this included a NotebookLM generated image with 2 text sections with minor issues. I've fixed it. Sorry about that. This is a good reminder to check properly even for low-stakes situations.

• Post #460764

  [Blogged] Are AI Tools Killing Review Articles? Two Failure Modes Suggest Otherwise https://aarontay.substack.com/p/are-ai-tools-killing-review-articles

• Post #460761

  [Blogged] The Sycophancy Fallacy: Why You May be Worried About the Wrong Bias with Search https://open.substack.com/pub/aarontay/p/the-sycophancy-fallacy-why-you-may