Jevotron is a new command-line tool that scans files such as CSV, YAML, JSON, TOML and OBO for anomalies, producing field-level probability scores and a review queue. The tool caches results in SQLite so unchanged entries aren't reassessed on subsequent runs, and users can guide scans with text instructions or a local Python config. A pilot test on 24 public agent traces reported the tool matched 130 of 163 step-quality labels (79.8% accuracy), with 89.7% precision and 70.3% recall for identifying harmful steps.
cmungall.github.io
· 2026-10-01
The DataHaskell/Dataframe library now includes a writeParquet function that lets users export a dataframe directly to a Parquet file using default row group and page sizes. A writeParquetWithOptions variant is also provided for developers who want finer control over those settings.
datahaskell.org
· 2026-09-22
Almanac, a startup from Y Combinator's Summer 2026 batch, has launched an AI system designed to understand a company's internal operations, tools and communications rather than general web knowledge. In a demo, the assistant monitored a customer Slack channel, identified duplicate bug reports, and automatically filed GitHub issues with reproduction steps and linked conversation threads. The product positions itself as an operational AI layer that can act on a company's existing data and workflows rather than just answer questions about them.
usealmanac.com
· 2026-08-31
The creator of the posuto package describes how Japan Post's official postal code CSV file breaks basic data conventions, embedding human-readable parenthetical notes that reference row order and splitting overly long fields across multiple duplicated lines. These quirks stem from the file's origins as a printed reference rather than a machine-readable dataset, forcing developers to write extensive workaround logic just to extract clean address data.
dampfkraft.com
· 2026-08-29
GoKawiil