AI LABS explores integrating the decision-making model Jev with coding agents to optimize workflows. This guide details seven practical use cases for implementing Jev to enhance speed and reduce costs when managing tasks like compaction, skill selection, file searching, code reviews, browser testing, and enforcing project rules.
Anthropic today released Claude Haiku 5.5, cutting token prices by 90% for requests below 100,000 tokens and targeting the repetitive work that can make enterprise AI expensive at scale: summarizing documents, classifying information, querying databases and handling smaller assignments for more capable agents.
The model starts at $0.10 per million input tokens and $0.50 per million output tokens, matching OpenAI’s GPT-6 Luna. Anthropic estimates that workloads cost approximately 75% less to run than on Haiku 4.5, once request sizes and changes in token consumption are considered.
Amid a growing divide between closed models that can be unplugged and open models that are often made in China, Mistral is positioning ML4 as an alternative to both. Nicknamed Le Chonk in reference to its 1 trillion parameters, ML4 is definitely not small; but is not an open-weight model yet. For the time being, it can only be accessed via a public guardrail endpoint, but Mistral plans to make its weights available in just three weeks, after safety testing is complete.
Reflection AI is officially unveiling Beam, its first frontier, open-weight AI model. The two-year-old, Brooklyn-based startup claims Beam matches the performance of leading Chinese open models on advanced reasoning benchmarks at dramatically lower costs, a claim that could heat up the race to build a Western answer to DeepSeek, Qwen, and Z.ai.
Matt Pocock introduces version 1.3 of their skills repository, focusing on workflows for large-scale coding projects and automated retrospective analysis. Learn how these new tools help manage sub-agents, improve pull request documentation, and refine repository health to increase overall development efficiency.
Simon Scrapes explores updated best practices for building effective skills, focusing on structural improvements and file management. The guidance covers implementing contents lists, managing degrees of freedom, optimizing for specific models, and ensuring portability across environments.
Google releases Gemini 4 Argon
Google parent company Alphabet has launched Gemini 4 Argon, a new AI model built to handle a variety of tasks such as coding, research, and writing. But it’s cybersecurity that Gemini 4 Argon is supposed to have a particular knack for, according to Google.