New and improved content moderation tooling

OpenAI Blog2022-08-10 15:000 views

We are introducing a new and improved content moderation tool. The Moderation endpoint improves upon our previous content filter, and is available for free today to OpenAI API developers.

Source：https://openai.com/index/new-and-improved-content-moderation-tooling

My favorites

PreviousOur approach to alignment research NextEfficient training of language models to fill in the middle

Five AI Models Said the Idea Was Real. A €1,879 Kickstarter Said Otherwise.

Last week a video put a phrase in my head: element cards . A chemistry card game — draw element cards, build molecules,

0dev.to Discuss

One line at 11 p.m., a test link by Wednesday morning

Friday, 11 p.m. Someone types one line on a phone and sends it: "I want to build a car-wash booking app. I only have the

0dev.to Productivity

How to Use AI for Notes on iPhone in 2026

0dev.to Productivity

Retraining on a schedule is easy. Promoting on a schedule is how models quietly get worse

A lot of teams get to the same place with their first production model: a cron job retrains it every week, and every wee

0dev.to Machine Learning

三个公式，让 Excel 自己算出月度汇总：SUMIFS、COUNTIFS、SUMIF 实测手记

做上面三张表的时候，真正干活的就三个公式。下面是我实测时用的数据和结果，照着抄就能用在自己的表上。一、SUMIFS：按月份和类型求和（记账表）记账表的月度汇总是 SUMIFS：金额列求和，条件是日期在当月内、类型等于要算的那一项。测试

0dev.to Tutorial

排班表实测：同一周里，连班、超时、节假日三处是怎么被抓出来的

排班最容易错的不是把班排上去，而是排完之后没人发现问题：同一个人一天早晚连轴转、一周工时悄悄超了、节假日当天还按平时排班。下面是我实测一整周排班时抓出来的三处，用的都是同一张表、同一组测试数据。测试场景是 2026 年 11 月 16 日