Latest

🚀 Better Dashboards, Smarter Workflows – Maxim Weekly Release Notes (June 9–13, 2025)

🚀 Better Dashboards, Smarter Workflows – Maxim Weekly Release Notes (June 9–13, 2025)

Last week at Maxim, we rolled out several powerful upgrades to give teams more control, clarity, and customization across the platform. Here's what’s new: Custom Dashboards Just Got an Upgrade Dashboards are now more flexible and insightful: * Custom metric cards – Build exactly what you need to monitor

Do Language Models Know That They're Being Evaluated?

Do Language Models Know That They're Being Evaluated?

Picture this scenario: You’re very new to AI, exploring chatgpt by testing its capabilities on various topics, expecting honest answers unaware that behind the scenes, it already figured out that it’s being tested and is subtly changing its behaviour to ace your tests. This feels like a subtle

🌤️ Building a Gemini-Powered Conversational Weather Agent with Maxim Logging

🌤️ Building a Gemini-Powered Conversational Weather Agent with Maxim Logging

“How’s the weather today in Delhi?” Simple question - but what if we wanted a conversational AI that could answer it, explain the temperature trend, and log every detail of its interaction for analysis? Agentic systems are booming. But building a reliable production-ready AI agent involves more than just

✨ Agentic mode, Scheduled runs, New evals, and more

✨ Agentic mode, Scheduled runs, New evals, and more

Feature spotlight 🤖 Agentic mode in the Prompt Playground Prototype complete agent behavior, including automatic tool calling, directly within the playground. Here’s what you can do: * Test multi-step flows: Experiment with and evaluate complex agentic interactions where the model automatically calls tools and executes steps until a final response is

AlphaEvolve : AI for Scientific Discovery

AlphaEvolve : AI for Scientific Discovery

Introduction Consider a scenario: You're facing a complex optimization challenge with no known solution - the kind that requires inventing entirely new algorithms, not just tweaking existing ones. There's no textbook answer, no established approach. Existing coding models like Claude, Gemini 2.5 can implement known

Bifrost: A Drop-in LLM Proxy, 50x Faster Than LiteLLM

Bifrost: A Drop-in LLM Proxy, 50x Faster Than LiteLLM

When you’re building with LLMs, day-to-day tasks like writing, brainstorming, and quick automation feel almost effortless. But as soon as you try to construct a robust, production-grade pipeline, the real challenges emerge. One of the first hurdles is interface fragmentation: every provider exposes a different API, with its own

VGBench: Evaluating Vision-Language Models in Real-Time Gaming Environments

VGBench: Evaluating Vision-Language Models in Real-Time Gaming Environments

Introduction Vision-Language Models (VLMs) have achieved remarkable success in tasks such as coding and mathematical reasoning, often surpassing human performance. However, their ability to perform tasks that require human-like perception, spatial navigation, and memory management remains underexplored. To address this gap, the paper titled "VideoGameBench: Can Vision-Language Models complete