GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks.
The agent can produce detailed, factual and unbiased research reports, with customization options for focusing on relevant resources, outlines, and lessons. Inspired by the recent Plan-and-Solve and RAG papers, GPT Researcher addresses issues of speed, determinism and reliability, offering a more stable performance and increased speed through parallelized agent work, as opposed to synchronous operations.
I’ve been tinkering around with this tool for doing deeper topic research. It uses the ChatGPT API and GPT-4o to conduct multi-phase agent-based research. Adds sources, citations,...
Stuart Buck with a fascinating piece on the seemingly simple but deceivingly hard process of replicating studies. Two labs were collaborating on a breast cancer study, and ran into surprising challenges getting the same results with (what they thought were) the same inputs:
They were frustrated: “Despite using seemingly identical methods, reagents, and specimens, our two laboratories quite reproducibly were unable to replicate each other’s fluorescence-activated cell sorting (FACS) profiles of primary breast cells.”
They tried everything: The instrumentation. The “specific sources of tissues…, media composition, source of serum and additives, tissue...
In his piece “Why Books Don’t Work,” Andy Matuschak made a strong case that books are a poor medium for knowledge transfer. Even with the most advanced book experiences today (like digital ebook downloads to a Kindle), if you took away the digital e-ink screen, a reader from the 16th century would still recognize books as no different than what they had. We’ve added digital on-demand access, dictionary lookups, and the ability to have a library in your pocket1, but the fundamental model for conveying...
J.C.R. Licklider’s seminal 1960 paper on what would eventually become the personal computer.
Man-computer symbiosis is a subclass of man-machine systems. There are many man-machine systems. At present, however, there are no man-computer symbioses. The purposes of this paper are to present the concept and, hopefully, to foster the development of man-computer symbiosis by analyzing some problems of interaction between men and computing machines, calling attention to applicable principles of man-machine engineering, and pointing out a few questions to which research answers are needed. The hope is that, in not too many years, human...
An interesting technical breakdown on how Figma built their multiplayer tech (the collaboration capability where you can see other users’ mouse cursors and highlights in the same document, in real time).
A fascinating paper. This research suggests the possibility that group-conforming versus individualistic cultures may have roots in diet and agricultural practices. From the abstract:
Cross-cultural psychologists have mostly contrasted East...
A beautiful visualization project from Nature converts 150 years of scientific papers into a 3-dimensional network diagram, making concrete the network of citations and references linking together the history of discoveries.
A few weeks back, Tyler Cowen and Patrick Collison co-authored this piece for The Atlantic calling for research into the study of progress1. From the thesis of the piece:
Progress itself is understudied. By “progress,” we mean the combination of economic, technological, scientific, cultural, and organizational advancement that has transformed our lives and raised standards of living over the past couple of centuries. For a number of reasons, there is no broad-based intellectual movement focused on understanding the dynamics of progress, or targeting the deeper goal...
This group is building some interesting tools to expose and enable sharing and collaboration on academic papers.
We develop software to help illuminate academic papers. Just as Pierre de Fermat scribbled his famous last theorem in the margins, professional scientists, academics and citizen scientists can annotate equations, figures, ideas and write in the margins.
They have a tool called Margins, which allows researchers to upload, annotate, and share academic papers, and another neat one called Librarian, a Chrome extension for comments and annotations for arXiv papers.
The Khan Academy’s Long-term Research group studies new strategies for teaching and learning. This paper presents a method for freeform response and feedback on open-ended The dynamism and interactivity of these tools for teaching are fantastic. I haven’t seen some of these modern e-learning platforms in a long time, things like Blackboard or Canvas. I have used Khan Academy extensively and am always impressed. My childhood self would’ve really taken to the engaging presentation style of the content.
Students shouldn’t have to wait until their adulthood to pursue open-ended problems and improve their...
Paul Romer has an interesting take on this piece from the Atlantic:
Jupyter rewards transparency; Mathematica rationalizes secrecy. Jupyter encourages individual integrity; Mathematica lets individuals hide behind corporate evasion. Jupyter exemplifies the social systems that emerged from the Scientific Revolution and the Enlightenment, systems that make it possible for people to cooperate by committing to objective truth; Mathematica exemplifies the horde of new Vandals whose pursuit of private gain threatens a far greater public loss–the collapse of social systems that took centuries to build.