Why LLM applications need better memory management

You delete a dependency. ChatGPT acknowledges it. Five responses later, it hallucinates that same deprecated library into your code. You correct it again—it nods, apologizes—and does it once more. This isn’t just an annoying bug. It’s a symptom of a deeper problem:...

JetBrains open-sources Mellum LLM

JetBrains has open-sourced its Mellum large language model (LLM), which was purpose-built for code completion, with the aim to grow Mellum into a family of models specialized for different coding tasks. The Mellum base model was open-sourced and made available on...

How MCP could add value to MongoDB databases

MongoDB has added Anthropic’s Model Context Protocol (MCP) to all its databases, including Atlas, to help developers accelerate software development and manage database administrative tasks. MCP, which has seen a rise in popularity since its release in November last...

Knowing when to use AI coding assistants

Just because you can use generative AI in software development doesn’t mean you should. AI coding assistants powered by large language models (LLMs) are a productivity dream in some cases but a debugging nightmare in others. So, where is that line? “Knowing when and...

Bringing DevOps, DevSecOps, and MLOps together

There are many moving parts in software development, particularly as tech and the role of engineers quickly evolve. Against this backdrop, there is transformative potential for “EveryOps” in 2025. But what exactly is EveryOps? We coined the term to include DevOps,...