In the absence of actual regulation, AI companies use "adversarial testers" to check their new models for safety. Does it actually work? Whe

The crash test dummies for new AI models

submited by

Style Pass

2024-10-16 12:00:04

In the absence of actual regulation, AI companies use "adversarial testers" to check their new models for safety. Does it actually work?

When a car manufacturer develops a new vehicle, it delivers one to the National Highway Traffic Safety Administration to be tested. The NHTSA drives the vehicle into a head-on collision with a concrete wall, batters it from the side with a moving sled, and simulates a rollover after a sharp turn, all filmed with high-speed cameras and crash test dummies wired with hundreds of sensors. Only after the vehicle has passed this rigorous battery of tests is it finally released to the public.

AI large language models, like OpenAI’s GPT-4o (one of the models which powers ChatGPT), have been rapidly embraced by consumers, with several major iterations being released over the past year and a half.

The prerelease versions of these models are capable of a number of serious harms that its creators fully acknowledge, including encouraging self-harm, generating erotic or violent content, generating hateful content, sharing information that could be used to plan attacks or violence, and generating instructions for finding illegal content.