Microsoft introduced a new Content Safety feature in the Azure cloud infrastructure – it is aimed at combating failures in the operation of generative artificial intelligence. The feature automatically detects and even corrects errors in the responses of AI models.
Image source: youtube.com/@MicrosoftAzure
Content Safety is available in preview in Azure AI Studio, a suite of security tools designed to detect vulnerabilities, detect hallucinations in AI systems, and block inappropriate requests from users. Content Safety scans AI responses and identifies inaccuracies in them by comparing the output with the client’s input.
When an error is detected, the system highlights it, provides information about why the information provided is incorrect, and rewrites the problematic content—all before the user can see the inaccuracy. However, this function does not provide a guarantee of reliability. The Google Vertex AI enterprise platform also has a function for “grounding” AI models by checking answers against Google’s search engine, the company’s own data, and, in the future, third-party data sets.
At the Lada Izhevsk plant, part of AvtoVAZ, mass production of the Lada e-Largus electric…
South Korea's semiconductor industry is critical to the nation's economy but continues to show growing…
The acclaimed survival simulator Palworld from the Japanese studio Pocketpair became part of the September…
Sony has unveiled new Chroma Collection glitter panels for the PlayStation 5 Slim console -…
A vulnerability has been discovered in ChatGPT that allows a potential attacker to insert false…
The Financial Times, with the support of TechInsights specialists, was able to assess the degree…