1/n Can LLMs perform scientific research? And, can they do so while enhancing key scientific values including transparency, traceability & verifiability? Check out our preprint on the "data-to-paper" platform. w the amazing @TalIfargan @LostInTranscrip https://t.co/60Go3TR5tn

Our data-to-paper AI is officially out! https://t.co/wpKcdAElKr Autonomously analyzes data and writes human-verifiable papers! Fun AI-human copiloting! Papers are "data-chained": click-traced to the raw code. Try it out: https://t.co/yhqDfTj4aB @TalIfargan @LostInTranscrip

עדכון תחזית: תמונת המכ"ם מציגה מטחים כבדים בצפון הארץ ומרכזה. עיון במפת הלחצים מראה על התחממות במזרח הנעה במהירות לאיזורנו. תחזית לשבוע הבא: התחממות קלה עד בינונית, עם סיכוי למבול באיזור המרכז ושיטפונות בדרום. @Eretz_Nehederet

ביבי מאשר את החיסול ואז הולך לאו"ם ואומר "נצח ישראל לא ישקר" הפסוק נאמר על ידי שמואל רגע לפני ששסף את אגג העמלקי אני מניח שזה לא במקרה @amit_segal

with the amazing! @TalIfargan @LostInTranscrip

AI-Science: New features! - Human-AI copilot app: Much more powerful (and fun) than the AI agents doing it all. - Fully annotated figures! - “Data Chaining”: All results (inc Figures) are click-traced to the specific code lines that created them! pip install data-to-paper

thanks to @TalIfargan and @LostInTranscrip

Mind-blowing: AI agents podcasting about AI-agent-driven science, crazy! The AI podcast: https://t.co/8ddI81N3YZ Google did an amazing job with NotebookLM! https://t.co/yhqDfTj4aB

Kind of a déjà vu of "GPT-1 of AI science” moment though... https://t.co/xfattJb62j

Amusing you use a "self-assessed novelty checker", while failing to mention *a ton* of work. Here, "AI Scientist", some data to improve your novelty checker: https://t.co/gEBdiKxRVZ https://t.co/B8wjlz1Baw https://t.co/mKbUiqbWhQ https://t.co/M4QLHCD75z https://t.co/ld8emg1fu8

our thoughts on the place of AI in Science... And a getting-started guide to "data-to-paper" https://t.co/LZcvcaQ4S9

what amazes me the most is just how well the camera tracking works

Try out data-to-paper with your own data! Repo is now open. We are looking for feedback as well as help developing and extending. https://t.co/yhqDfTj4aB

Is there necessarily a tradeoff between AI-driven science and scientific verifiability? “Data-chaining” by our AI driven platform enables traceability and verifiability which imo *exceeds* the standard of human driven research.

Our preprint describing data-to-paper is now out: https://t.co/60Go3TR5tn Repo: https://t.co/yhqDfTjC09 New thread: https://t.co/R2VV9Z1t6I

9/9 LLMs have a huge potential for accelerating science. We hope our project stimulates discussions on how to harness AI for science, while fostering, not jeopardizing, accountability, transparency and verifiability.

8/n LLMs are here to stay and are already used extensively in science doing (sadly sometimes undisclosed https://t.co/u1cLZCHLXW). Our approach is designed to provide ways to use LLMs powerfully, yet also transparently and responsibly.

7/n Repo is now open. We invite people to try it out. Currently most suitable for fairly simple datasets with simple research goals, where we want to raise and test a statistical hypothesis. Help in developing and extending is also very much welcome.

6/n Not (yet?) as novel as high-end research but does reach de novo results in different fields. We tested it in epidemiology, social networks, ML modeling & clinical datasets. Can autonomously tackle simple research questions. Human copiloting becomes critical for complex goals.

5/n Co-pilot: A human-AI co-pilot app allows users to oversee and direct the process by providing human reviews at each research step.

4/n “Data-Chaining": by tracing information flow through the steps, data-to-paper creates “data-chained” manuscripts, where results, methodology and data are *programmatically* linked. See video above, or try out "click-tracing" results in this example ms: