Paperpile

Coming soon: Paperpile’s first AI-native integration ✨️ Send papers from your library straight to NotebookLM, ChatGPT, or your preferred AI assistant.

Strict reproducible pipelines that always run from raw data can slow down analysis and break over time. 📊 A more practical approach is to save the final processed dataset before plotting, which speeds up iteration and makes results easier to access in the future, via Claus Wilke blog.genesmindsmachines.com/p/creating-rep…

@RKouzyMD @jryckman3 @OncBrothers @Dr_RShatsky @DrSheilaSahni @BijoyTelivala @NiuSanford Happy to hear you are enjoying our new AI assistant integration, Ramez! We're glad you find the prompts useful 😊

@jryckman3 @OncBrothers @Dr_RShatsky @DrSheilaSahni @BijoyTelivala @NiuSanford Thanks for sharing Jeff! Agree need continuous experimentation. One new tool I have been playing with is @paperpile AI features and how it integrates with your fav models you already access. The prompts are top notch! Write up coming soon on beampath.org

A lot of buzz around AI (particularly LLMs). Are you actively using this in your clinical practice? #OncTiwtter #MedTwitter #HemeTwitter @BijoyTelivala @RenoHemonc @PTarantinoMD @NVijayvergiaMD @Papa_Heme @ErikaHamilton9 @CathyEngMD @hoperugo @Dr_RShatsky @NiuSanford @GIMedOnc

Filler transitions, em dashes on every line, self-answered rhetorical questions...all classic tells of AI writing. A Claude skill can remove these patterns, which is especially useful for paperwork like budget justifications you’d rather not write in the first place, via @strnr blog.stephenturner.us/p/deslop

@arjunrajlab 🧮 Check things that should add up ⚠️ Never ignore code warnings 📊 Track datapoints like the number of rows 🔍 Investigate outliers 🧠 If something doesn’t make sense, keep digging arjunrajlab.substack.com/p/transitionin…

AI is pushing computational biology into analytic abundance. The bottleneck is no longer generating results: It’s deciding whether to trust them. 📊 5 habits for sense-checking outputs, via @arjunrajlab

@drrobcincotta Happy to hear this! It's already available in beta.

@paperpile This is looking promising. Hopefully we can access it on @paperpile soon

Coming soon: Paperpile’s first AI-native integration ✨️ Send papers from your library straight to NotebookLM, ChatGPT, or your preferred AI assistant.

@Faheem_uh Glad to hear that 🙂 That’s what we’re aiming for—making research a bit easier.

@paperpile This seems very useful for researchers

@M_Torasawa This looks great! Thank you for recommending us 😊

📄Still storing papers as PDFs and leaving them untouched? 📚Practical workflow: #Paperpile (PDFs) → Google Drive → #Docling → Markdown → #Obsidian 📦 Docling: an open-source tool that turns PDFs into AI-friendly Markdown github.com/docling-projec… ✅ Now your entire paper library has become an AI-searchable knowledge base. 🔓What this unlocks: 🔍 Compare Methods across multiple papers instantly 💻 Ask AI to implement a paper’s pipeline in Python/R 🏷️ Search the whole library with auto-generated tags from abstracts 🧠 Turn years of papers into something AI can actually use 🤔Why Markdown instead of PDF? PDFs are great for humans. Markdown is better for AI. It’s easier to search, parse, cross-reference, and reuse. 💻 Fully local 💸 Free 🚫 No API cost Your paper collection stops being a static archive and becomes a research knowledge base you can query instantly.

AI is making it easier to analyze and stress-test scientific work at scale, which could improve rigor and reproducibility. But there’s a risk: more data and better predictions don’t necessarily lead to paradigm shifts. The challenge ahead is not just building more powerful AI, but designing systems and scientific environments that support genuine breakthroughs, not just better predictions, via @adjajadikerta @AsimovPress asimov.press/p/ai-science

I'm excited to be putting the finishing touches on this with the team – you can throw 50 PDFs into NotebookLM with one click

@hmap01337406 Thank you for reporting. Can you try restarting your browser? If that fails, please contact our support team at support@paperpile.com and they will be happy to help you.

app.paperpile.com seems not working since Yesterday...? #paperpile

Fascinating work on LLMS and writing. My guiding principles have been: (1) Use AI to help read, not write; (2) Re-evaluate this stance often, as models improve quickly. But I am curious why LLMs are still "bad" writers! Even today's best models still have an AI smell.

2/2 But it also risks pushing science toward “checklist” thinking, where easily measurable robustness is prioritized over judgment, creativity, and meaningful questions, via Jessica Hullman jessicahullman.substack.com/p/living-the-m…

AI is making it easy to run large-scale robustness checks like multiverse analyses on research papers, potentially transforming peer review and scientific scrutiny. This could make it harder for fragile results to be published. 1/2

An analysis of submissions to bioRxiv shows steady growth in the number of scientists uploading their work. In 2025, more than 4,000 papers are posted each month, alongside millions of views and downloads, via @Nature nature.com/articles/d4158…

AI can speed up parts of research, but when data are messy and fragmented, careful human verification is still essential, via @adamjkucharski kucharski.substack.com/p/how-much-tim…

Compiling research datasets from scattered reports can take months of manual work. When the same task was attempted with an AI agent, it produced results quickly, but missed many cases and data sources. 1/2