Go to Homepage
Home
About
Hiring
Careers
Blog
Contact
Sign In
Schedule Demo
Menu
Close
Back to blog
Engineering
Are the Spammers winning? Failures in Gmail Spam Detection
Edwin Chen
Engineering
May 24, 2022
The average number of ads on a Google Search recipe? 8.7
Bradley Webb
Engineering
Apr 29, 2022
Google Search is Falling Behind
Edwin Chen
Engineering
Apr 12, 2022
Building a No-Code Machine Learning Model by Chatting with GitHub Copilot
Andrew Mauboussin
Engineering
Mar 24, 2022
Surge AI Achieves SOC 2 Compliance
Andrew Mauboussin
Engineering
Feb 25, 2022
Writing a Super Bowl Worthy Commercial with GPT-3
Jefferson Lee
Engineering
Feb 16, 2022
Moving beyond engagement: How could Facebook's algorithms optimize for human values instead?
Bradley Webb
Engineering
Feb 10, 2022
Using Surge AI with a Hybrid Cloud Model
Andrew Mauboussin
Engineering
Feb 4, 2022
Holy $#!t: Are popular toxicity models simply profanity detectors?
Edwin Chen
Engineering
Jan 22, 2022
An Analysis of Omicron Tweets: 30% are Skeptical of the Medical Establishment
Jefferson Lee
Engineering
Jan 21, 2022
We analyzed 1500 tweets to measure Omicron skepticism, fear, relief, and more.
Is Google Search Deteriorating? Measuring Google's Search Quality in 2022
Andrew Mauboussin
Engineering
Jan 10, 2022
Has Google's Search Quality deteriorated in recent years? This post measures Google Search using human evaluation.
Inter-Annotator Agreement: An Introduction to Krippendorff’s Alpha
Andrew Mauboussin
Engineering
Dec 29, 2021
Learn about Krippendorff's Alpha, an important inter-annotator agreement metric.
How Good is Your Chatbot? An Introduction to Perplexity in NLP
Engineering
Dec 9, 2021
A primer on using perplexity to evaluate model quality.
Inter-Annotator Agreement: An Introduction to Cohen's Kappa Statistic
Bradley Webb
Engineering
Nov 30, 2021
In the second post in our series on inter-rater reliability metrics, we dive into Cohen's kappa statistic.
5 Examples of the Importance of Context-Sensitivity in Data-Centric AI
Scott Heiner
Engineering
Nov 19, 2021
Data-centric AI requires radically rethinking your datasets, features, and labels. Here are 5 examples where context-sensitive features and context-sensitive labels are crucial for AI applications.
The Pitfalls of Inter-Rater Reliability in Data Labeling and Machine Learning
Scott Heiner
Engineering
Nov 13, 2021
How a simple logic problem illustrates the shortcomings of inter-rater reliability metrics and common AI datasets...
A Visual Introduction to Language Models in NLP (Part 1: Intuition)
Andrew Mauboussin
Engineering
Nov 4, 2021
The first installment in a new tutorial series exploring the richness of language and NLP...
Getting started with Surge AI's Python SDK
Andrew Mauboussin
Engineering
Aug 2, 2021
If you need programmatic access to the Surge AI platform, look no further! You can use the Surge API to manage all aspects of your labeling project...