Latest

SuperBPE: Rethinking Tokenization for Language Models

SuperBPE: Rethinking Tokenization for Language Models

In the domain of language models, tokenization i.e. the process of breaking down text into manageable units plays a pivotal role. Traditionally, models rely on subword tokenization, where words are split into smaller units. However, this approach often overlooks the semantic significance of multi-word expressions and varies across languages.

Maxim x Clin

Elevating Conversational Banking: Clinc's Path to AI Confidence with Maxim

About Clinc Clinc provides a sophisticated conversational AI platform, primarily focused on the banking industry, enabling financial institutions to build advanced virtual assistants. Recognizing that state-of-the-art AI results are increasingly obtained by orchestrating multiple components into Compound AI Systems, rather than relying on single large models, Clinc is specifically designed

Scaling Enterprise Support: Atomicwork's Journey to Seamless AI quality with Maxim

Scaling Enterprise Support: Atomicwork's Journey to Seamless AI quality with Maxim

About Atomicwork Atomicwork is an agentic service management platform that helps businesses automate IT, HR, and workplace support, enabling employees to solve issues faster, work smarter, and stay productive. Built AI-native, Atomicwork combines intelligent agents, adaptive workflows, and enterprise-grade governance to deliver proactive support right in the flow of work.

Can Your AI Explain Why It’s Moral?

Can Your AI Explain Why It’s Moral?

Large‑language models (LLMs) already draft contracts, triage medical claims, and screen résumés. Every one of those tasks is laced with ethical choices, yet most benchmarks still judge models on math puzzles or multiple‑choice trivia. The authors of the paper “Auditing the Ethical Logic of Generative AI Models” step

Evaluating the Quality of AI HR Assistants using Maxim AI

Evaluating the Quality of AI HR Assistants using Maxim AI

Use of Artificial Intelligence in Human Resources is reducing administrative load by automating routine tasks such as hiring and resolving employee queries, freeing HR teams to focus on people-centric initiatives. The applications of AI span every stage of the HR workflows, including: * Sourcing candidates from large talent pools * Screening thousands

Last Week at Maxim (Weekly Updates)

Last Week at Maxim (Weekly Updates)

This week at Maxim, we’ve rolled out some powerful updates focused on dynamic scripting, enhanced LLM flexibility, and deeper error visibility across our SDKs and libraries. Script-Driven Variables in Evaluations Evaluations just got a whole lot smarter! All variables defined via custom scripts are now surfaced directly in workflow

Introduction to the Agent2Agent Protocol (A2A)

Introduction to the Agent2Agent Protocol (A2A)

Communication protocols play a crucial role in enabling seamless interactions between different systems. Google's recently published Agent to Agent Protocol (A2A) represents a significant advancement in this space, designed specifically to facilitate collaborative scenarios between autonomous agents. What is A2A? The protocol is an open specification that enables