RSS Parrot

BETA

🦜 @aarontay.bsky.social on Bluesky

@bsky.app.profile.aarontay.bsky.social@rss-parrot.net

I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.

---

I'm librarian + blogger from Singapore Management University. Social media, bibliometrics, analytics, academic discovery tech.

Your feed and you don't want it here? Just e-mail the birb.

Site URL: bsky.app/profile/aarontay.bsky.social

Feed URL: bsky.app/profile/did:plc:3z5zbwdbqmw2qobnb5zsfdbu/rss

Posts: 49

Followers: 1

https://bsky.app/profile/aarontay.bsky.social/post/3mguiqqkbf22e

Published: March 12, 2026 13:24

Working with a friendly faculty that was setting up his Claude code to connect to many diff sources. His understanding of Claude code and agentic frameworks was way above mine but he joked "Library should teach Ai architecture Multi agentic frameworks and…

https://bsky.app/profile/aarontay.bsky.social/post/3mgugtjsanc2e

Published: March 12, 2026 12:50

Interesting sharing of how one of the founders of Moara.io writes literature review with Claude. The essential step is to paste in their reference manager & ask Claude to suggest references from it to support claim. Claude is also asked to flag claims NOT…

https://bsky.app/profile/aarontay.bsky.social/post/3mgol3vqems26

Published: March 10, 2026 04:50

Sadly librarians who are thirsty for respect after years ignored by faculty, and dismissed by vendors are sometimes willing to overlook serious product deficiencies in exchange for being treated as valued intellectual partners by vendors. The bar for…

https://bsky.app/profile/aarontay.bsky.social/post/3mgh4pbrbqk2e

Published: March 7, 2026 05:44

Looking at a utterly delusional librarian substack post and thinking whether I want to respond. There's a lot I agree with the piece e.g. in terms of the trust users have with the library and how often we see things other institution units may not notice.…

https://bsky.app/profile/aarontay.bsky.social/post/3mgclyyv54s2a

Published: March 5, 2026 10:35

Looking forward to FORCE2026 keynote- Surviving the Disruption: Scholarly Communication in the Age of AI by Ian Mulvany, Chief Technology Officer, BMJ Group https://event.fourwaves.com/force2026/schedule/6c16e29d-7022-45c8-8c84-a2e9e6231ef3 - Early Bird…

https://bsky.app/profile/aarontay.bsky.social/post/3mgajgfmmrc2g

Published: March 4, 2026 14:43

I really think things are speeding up. Let's not even talk about agentic ai. The fact that you can easily ask ai to vibe code basic things on the fly is a game changer for someone like me. I was reading a paper suggesting a stopping rule for screening & I…

https://bsky.app/profile/aarontay.bsky.social/post/3mgai4lk3fs2g

Published: March 4, 2026 14:20

I was talking to a young faculty who is a very early adopter of Claude code and is automating a lot of research tasks and he was asking for advice about combining mcp servers/skills for literature review. He quickly realised the problem isnt technical or…

https://bsky.app/profile/aarontay.bsky.social/post/3mg7ysl7o3k2e

Published: March 4, 2026 09:46

spent the last 2 weeks really looking at the openalex topic hierachy - domain, field, subfield, topic vs ASJC subject area, main category and subcategory. Can see how openalex first 3 levels, domain , field, subfield is sort of modelled on elsevier's ASJC…

https://bsky.app/profile/aarontay.bsky.social/post/3mfxry3zhmc2n

Published: March 1, 2026 03:22

Does clarivate understand what citations are for? "With Nexus, Clarivate are essentially integrity-washing synthetic text, giving it an academic sheen without any academic rigour." "... it offers to "Find Verified Alternative ... (1)…

https://bsky.app/profile/aarontay.bsky.social/post/3mfv4xtlb622g

Published: February 28, 2026 02:01

How do researchers actually use AI-powered science tools? Lessons from 250,000+ queries February 27, 2026 https://allenai.org/blog/asta-interaction-dataset from AI2 tools AI2 paperfinder and ScholarQA now under asta. This part caught my eye (1)

https://bsky.app/profile/aarontay.bsky.social/post/3mfryhgipw22q

Published: February 26, 2026 20:02

Scite officially launches MCP server with support for info about institution full text entitlements via getFTR, libkey. - suspect this might lead to a rush of academic ai search mcp servers? https://scite.ai/blog/introducing-scite-mcp

https://bsky.app/profile/aarontay.bsky.social/post/3mfrydskzxc2q

Published: February 26, 2026 20:00

Scite officially launches MCP server with support for info about institution full text entitlements via getFTR, libkey. - suspect this might lead to a rush of academic ai search mcp servers? https://scite.ai/blog/introducing-scite-mcp

https://bsky.app/profile/aarontay.bsky.social/post/3mfr4zxbe3c2q

Published: February 26, 2026 11:52

I am biased as I helped with evaluation of FORCE 2026 proposals - but the programme looks really good with 3 parallel tracks with really top notch speakers on everything from responsible research assessment to impact of ai on research and publishing…

https://bsky.app/profile/aarontay.bsky.social/post/3mfoqxdt7es2o

Published: February 25, 2026 13:10

Reading a pretty nice librarian comparison test of Primo RA, Scopus AI, web of science RA etc. It finds WOS RA is least favoured which tracks (retrieval was quite bad at that time). That said its definition of RAG as something that uses vector embedding…

https://bsky.app/profile/aarontay.bsky.social/post/3mfnrfoy7jc2o

Published: February 25, 2026 03:45

I've read this paper before. Its a very rigorous method. Sure there's a tiny issue with the fact it doesn't handle the multiple testing issue but ranked quasi sampling seems conservative enough to counter that. I'm curious ai deep search tools dont use…

https://bsky.app/profile/aarontay.bsky.social/post/3mflxkojdl222

Published: February 24, 2026 10:30

[Read] Don't Stop Me Now, `Cause I'm Having a Good Time Screening: Evaluation of Stopping Methods for Safe Use of Priority Screening in Systematic Reviews https://onlinelibrary.wiley.com/doi/10.1002/cesm.70068 tests 15 statistical/rule-based (heuristic)…

https://bsky.app/profile/aarontay.bsky.social/post/3mfgxq5z4ik2r

Published: February 22, 2026 10:50

I notice this pattern. Whenever a new type of tool or technology emerges, naysayers will say its can't ever be useful cos it lacks this property X that the older tech has, despite the fact that millions are using it. And as the technology matures usage…

https://bsky.app/profile/aarontay.bsky.social/post/3mfgxf4462k2r

Published: February 22, 2026 10:44

Being hearing from researchers and librarians about the amazing things they can do with Claude code. So much for the "stochastic parrots" cannot be useful no matter what arguments . [contains quote post or other embedded content]

https://bsky.app/profile/aarontay.bsky.social/post/3mfeiyn2lek2f

Published: February 21, 2026 11:21

For most definitions of grey literature preprints count as GL. But preprints are increasingly a "first class entity" (with dois) easily findable thanks to sources like Semantic Scholar/openalex used by most Ai search tools like Elicit/consensus/undermind…

https://bsky.app/profile/aarontay.bsky.social/post/3mfe2iykahc2t

Published: February 21, 2026 07:02

"The AI can access articles from Elsevier’s own collection and those of its four partners: Emerald, the Institute of Physics, the New England Journal of Medicine Group, and Sage Publications". Interesting Wiley isnt on the list. Based on partnership…

https://bsky.app/profile/aarontay.bsky.social/post/3mf5tzo3swc2t

Published: February 18, 2026 19:50

[Watched] Finally watched this CNI talk from end to end. This pretty much sums up the cutting-edge issues regarding library + ai discovery. Library nexus, library workflow, library MCP servers. Also excellent q&a discussion …

https://bsky.app/profile/aarontay.bsky.social/post/3mf5pplbivk2t

Published: February 18, 2026 18:33

[Watched] https://youtu.be/oXqJQeHWhUs?si=deVhh-srn6fedHYy - good refresher on doing systematic review with undermind.ai, 2dsearch, polygon - I must say many parts even free version of Undermind was heavily praised . Eg the email alert, lack of…

https://bsky.app/profile/aarontay.bsky.social/post/3mf53wq5sd22l

Published: February 18, 2026 12:39

Even librarian have half a dozen definitions of what library databases or search engine mean. Eg i saw a systematic review librarians suggest database is say medline but platform/interface eg ovid, pubmed, Ebscohost, ProQuest, web of science is "search…

https://bsky.app/profile/aarontay.bsky.social/post/3mf4umdb4e22q

Published: February 18, 2026 10:28

"On our API, Claude’s web search and fetch tools now automatically write and execute code to filter and process search results, keeping only relevant content in context—improving both response quality and token efficiency." This is going to be very…

https://bsky.app/profile/aarontay.bsky.social/post/3mf2lix6grc2k

Published: February 17, 2026 12:39

Curious about papers that investigated how good openalex was when used solely as database for systematic review. Undermind as usual found the top 2 super relevant, 1 that is closely relevant. Claude research mode found 2, OpenAlex deep research 1, Gemini…

https://bsky.app/profile/aarontay.bsky.social/post/3mf2hemynyc2i

Published: February 17, 2026 11:25

[Watched] Using AI for systematic review: 2025 vs 2026 - interesting point PRISMA 2020 is challenged or constrained by new AI tools. Step by step approach not appropriate for newer methods eg AI can extract PICO from title/abstact, is that screening or…