Monitoring LLM behavior: Drift, retries, and refusal patterns

The offline pipeline's primary objective is regression testing — identifying failures, drift, and latency before production.
SiliconANGLE

Mend.io launches AI system prompt hardening solution to secure LLM instructions

Application security solution provider White Source Ltd., also known as Mend.io, today launched System Prompt Hardening, a dedicated capability designed to detect issues within the hidden instructions ...
InfoWorld

How to test large language models

Companies investing in generative AI find that testing and quality assurance are two of the most critical areas for improvement. Here are four strategies for testing LLMs embedded in generative AI ...
TechCrunch

Instead of fine-tuning an LLM as a first approach, try prompt architecting instead

Amid the generative AI eruption, innovation directors are bolstering their business’ IT department in pursuit of customized chatbots or LLMs. They want ChatGPT but with domain-specific information ...
CSOonline

OpenAI to acquire Promptfoo to strengthen AI agent security testing

The acquisition points to rising demand for tools that test and secure LLMs before they are deployed in enterprise workflows. OpenAI said it plans to acquire AI testing startup Promptfoo, a move aimed ...
CSOonline

10 most critical LLM vulnerabilities

Prompt injection and supply chain vulnerabilities remain the main LLM vulnerabilities but as the technology evolves new risks come to light including system prompt leakage and misinformation.

LLM-As-A-Judge: What To Expect From Using AI To Evaluate AI

LLM-as-a-judge is exactly what it sounds like: using one language model to evaluate the outputs of another. Your first ...
VentureBeat

New LLM optimization technique slashes memory costs up to 75%

Researchers at the Tokyo-based startup Sakana AI have developed a new technique that enables language models to use memory more efficiently, helping enterprises cut the costs of building applications ...