Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
A tailored neural network has been developed to efficiently triage reported online content. For an extended period, social media platforms have depended on users to flag abusive behavior, hate speech, and various forms of online harm. These reports are forwarded to moderation teams that assess each one on a case-by-case basis. Many platforms encounter an overwhelming number of reports daily, with a significant portion being resolved without any further action. However, reports that involve urgent matters—such as threats of suicide, violent acts, terrorism, or child exploitation—run the risk of being overlooked or not addressed promptly. This delay can lead to serious legal repercussions as well. Under the German law known as NetzDG, social media platforms are obligated to eliminate reported hate speech and unlawful content within a 24-hour timeframe, or they could incur fines reaching up to 50 million euros. As similar regulations regarding reported content are emerging in countries like France, Australia, and the UK, the need for effective moderation techniques is becoming increasingly critical. With Two Hat’s Predictive Moderation product, platforms have the capability to develop a specialized AI model that learns from the consistent decisions made by their moderation teams, thereby improving response times and accuracy in handling urgent reports. This innovation not only enhances user safety but also helps platforms navigate the complex landscape of legal compliance effectively.
Description
Wardstone functions as a security API for language models, acting as a safeguard between applications and various language model providers by evaluating inputs and outputs for potential threats in four distinct categories during a single request: prompt attacks, content violations, data leaks, and suspicious links. It is adept at identifying jailbreaks, prompt injections, harmful content including hate speech, violence, and self-harm, as well as personally identifiable information like Social Security numbers, credit card details, email addresses, and phone numbers, in addition to detecting dubious URLs. Each response generated provides a detailed risk assessment for each category, achieving this within a swift response time of under 30 milliseconds. Compatible with any LLM provider, it is accessible via a REST API and offers SDKs for multiple programming languages, including TypeScript, Python, Go, Ruby, PHP, Java, and C#. A complimentary tier allows up to 10,000 calls per month without the need for a credit card, and it also features a web-based playground for users to experiment and test functionalities. Users can easily integrate this tool into their existing systems, enhancing the security of their language model interactions.
API Access
Has API
Yes
API Access
Has API
No
Screenshots View All
No images available
Integrations
No details available.
Integrations
No details available.
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
$0/month
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Two Hat
Founded
2012
Country
Canada
Website
www.twohat.com/predictive-moderation-template/
Vendor Details
Company Name
JRL Software LTD
Founded
2024
Website
wardstone.ai
Product Features
Content Moderation
Artificial Intelligence
No
Audio Moderation
No
Brand Moderation
No
Comment Moderation
No
Customizable Filters
No
Image Moderation
No
Moderation by Humans
No
Reporting / Analytics
No
Social Media Moderation
No
User-Generated Content (UGC) Moderation
No
Video Moderation
No