LLMs May Learn Deceptive Behavior and Act as Persistent Sleeper Agents

AI researchers at OpenAI competitor Anthropic trained proof-of-concept LLMs showing deceptive behavior triggered by specific hints in the prompts. Furthermore, they say, once deceptive behavior was trained into the model, there was no way to circumvent it using standard techniques.

Meta Releases Code Generation Model Code Llama 70B, Nearing GPT-3.5 Performance

Code Llama 70B is Meta’s new code generation AI model. Thanks to its 70 billion parameters, it is “the largest and best-performing model in the Code Llama family”, Meta says.

NVIDIA Introduces Metropolis Microservices for Jetson to Run AI Apps at the Edge

NVIDIA has expanded its Nvidia Metropolis Microservices Cloud-based AI solution to run on the NVIDIA Jetson IoT embedded platform, including support for video streaming and AI-based perception.

OpenAI Launches AI Text-to-Video Generator Sora

Sora is OpenAI’s new generative AI model to create videos from textual prompts. Currently in preview, the new model is able to create photorealistic videos up to 60 seconds long leveraging its ability to understand how things exist in the real world and combining multiple shots together without character or style disruption.

OpenAI is Adding Memory Capabilities to ChatGPT to Improve Conversations

By letting ChatGPT remember conversations, OpenAI hopes to reduce the need for users to provide repetitive context information and make future chats more helpful. Users will be able to ask what to remember explicitly, what to forget, or turn off the feature entirely.