Apr 17, 2024

Retrieval-augmented generation (RAG) enables large language models to generate better output by retrieving documents that are relevant to a user’s prompt. Fine-tuning further improves RAG performance.

OpenAI has been moderating its GPT Store with a very light touch. In a survey of the GPT Store’s offerings, TechCrunch found numerous examples of custom ChatGPT instances that appear to violate the store’s own policies.

Language models can generate code that erroneously points to software packages, creating vulnerabilities that attackers can exploit.

Google is empowering developers to build autonomous agents using little or no custom code.

Multi-agent collaboration is the last of the four key AI agentic design patterns that I’ve described in recent letters.

The Batch AI News and Insights: Multi-agent collaboration is the last of the four key AI agentic design patterns that I’ve described in recent letters. Given a complex task like writing software, a multi-agent approach would break...

This week's top AI news and research stories featured all about Google's Vertex AI Agent Builder, security holes in generated code, a series of policy violations in the GPT Store, and RA-DIT, a fine-tuning procedure that trains an LLM and retrieval model together to improve the...