Data Formulator

Data

ai data visualization

SHOW HN2024

Data Formulator

Data Formulator – AI-powered data visualization from Microsoft Research

github.com

#data visualization#ai charts#natural language#python data analysis

212points
34comments
#369of 3,515 in 2024
Top 11%of 2024 by points

How HN took it

RoastedHalf or more of the comments are critical

3 positive, 5 neutral or asking, 0 mixed, 9 critical, out of 17 comments about the project. Thread score -0.22.

Performance: 0 for, 4 againstExecution: 0 for, 3 againstDocs: 0 for, 1 againstIdea: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful for saving time on data tasks

    From 2 comments
    • Definitely looks like something that could save me, and others, allot of time. Thanks for sharing!
      marktl on HN
    • Thanks for sharing and provide open source version! This is great!
      donq1xote1 on HN
  • Data threads and UI-plus-natural-language approach are interesting

    From 2 comments
    • Some of the metaphors for interacting with the models, and visualizing as threads are interesting. Definitely does a good combination of ease of prompting + interogatability of…
      d_watt on HN
    • I just tried this out on a bunch of log files that were lying around. Excellent! I would love to connect this to a SQL database through ODBC/ JDBC and ask questions about the…
      gourabmi on HN

Objections

  • AI output may be wrong; hard to verify transformations

    From 3 comments
    • Since Data Formulator performs data transformation on your behalf to get the desired visualization, how can we verify those transformations are not contaminated by LLM…
      goose- on HN
    • The problem with AI is still, how confident can we be the result isn’t wrong?
      croes on HN
    • We still really should not be confident. We have seen this time and time again that the output cannot be relied on. People keep trying to downplay the problem as "not a big deal"…
      nerdjon on HN
  • Less consistent results than prompting GPT-4o directly

    From 1 comment
    • After giving it a whirl I'm a little underwhelmed, but maybe I'm using it wrong. I'm getting less consistent results than if I prompted GPT4-o for a Vega graph after providing it…
      matt3D on HN

Requests

  • Connect to SQL databases via ODBC/JDBC

    From 1 comment
    • I just tried this out on a bunch of log files that were lying around. Excellent! I would love to connect this to a SQL database through ODBC/ JDBC and ask questions about the…
      gourabmi on HN
  • Jupyter extension

    From 1 comment
    • This looks good, especially the data ingest. A couple of questions: What type of data person are you aiming this tool to be useful for, data analyst, data scientist, or data…
      paddy_m on HN

Questions

  • How to verify transformations and avoid hallucinations

    From 2 comments
    • Since Data Formulator performs data transformation on your behalf to get the desired visualization, how can we verify those transformations are not contaminated by LLM…
      goose- on HN
    • This looks good, especially the data ingest. A couple of questions: What type of data person are you aiming this tool to be useful for, data analyst, data scientist, or data…
      paddy_m on HN
  • Handling missing Python libraries like ARIMA

    From 1 comment
    • Some of the metaphors for interacting with the models, and visualizing as threads are interesting. Definitely does a good combination of ease of prompting + interogatability of…
      d_watt on HN

Alternatives named

  • Buckaroo

    From 1 comment
    • I have a tool [1] that is tackling some of the same problems in a different way. I had some core views that shaped what I built. 1. When doing data manipulation, especially…
      paddy_m on HN
  • Chat-based LLMs such as GPT-4o and Anthropic's tool

    From 2 comments
    • Anthropic recently released something that looks more polished but follows the chat paradigm. [1] As a builder of something like that [2], I believe the future is a mix, where…
      zurfer on HN
    • potentially! I myself as an experienced programmer finds directly chatting with GPT-4o much easier, since I have full control. But Data Formulator only transforms data in the…
      chenglong-hn on HN
  • Hex's Vega-lite DSL approach

    From 1 comment
    • way cool! I hope to take it for a spin tomorrow! Q: Does your team see potential value in a DSL for succinctly describing visualizations to an LLM as Hex did with their DSL for…
      data_ders on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/41907719)