Next Newsletter

Convert any URL to Markdown for better grounding LLMs.

Comparing how long-context embedding models perform with different chunking strategies to find the optimal approach for your needs.

FlowingData

I don't think that AI models (by which I mean: large language models) are over-hyped. In this post I will list 50 ways I've used them.

Discover amazing ML apps made by the community

The American worker divide: Those who sit, and those who stand

Visualize the negative space of literary works

Gender indicators for India

The bluesky firehose visualised in 3D

Bluesky firehose fun continues. Jared Short shows emoji usage as rain drops that fall down the screen. Larger drops represent longer posts. Or, if the Matrix aesthetic is your thing, Short did that…

Access, explore, and contribute to Foursquare's open source point of interest dataset for geospatial projects and location-based apps.

We can see the changing scales of who works and for how long through employment rates by age and time.

We report the existence of multimodal neurons in artificial neural networks, similar to those found in the human brain.

Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term, hallucination has been somewhat generalized to cases when the model makes mistakes. Here, I would like to narrow down the problem of hallucination to cases where the model output is fabricated and not grounded by either the provided context or world knowledge. There are two types of hallucination: In-context hallucination: The model output should be consistent with the source content in context.

To illustrate how difficult it is to get abortion care in the United States, we built a maze for each state where the difficulty is calculated by the state’s abortion policies.

In just three years, the share of U.S. adults who say they regularly get news from TikTok has more than quadrupled, from 3% in 2020 to 14% in 2023.

Google DeepMind's "Habermas Machine" is an AI-driven mediation tool designed to foster inclusive dialogue and consensus in group discussions by integrating...

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git. - marimo-team/marimo: A reactive notebook for Python — run reproducible ...

An analysis of the top fanfic relationship pairings on Archive of Our Own from 2013–2024.

Open-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.

It’s not always the song you’d expect.

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks. - sebastianruder/NLP-progress

Open-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.

Movies and TV Shows listings on Amazon Prime Video

What topics does Wikipedia cover? Has the coverage changed over time? These and similar questions are examined using 1001 random articles sampled in December, 2015. The 18 categories and subcategories are dominated by biographies (27.8% of all articles), with biographies of men (23.8%) being 5.8 times as common as women (4.1%). Sports biographies (9.5%) form over a third of all biographies. All articles on sports total 16.0% of the sample. Geography (17.8%) and Culture & Arts (15.8%) are other major categories, with Science & Math (3.5%) having the lowest proportion of the categories in the sample. These proportions are fairly stable over time. Almost 90% of page views go to the 20% of articles with the highest page views.

China recently increased their retirement age to 63 for men and 55 for women. Even with the adjustment, the country is still on the lower end when compared to other countries.