Software Development

The author shares his experience building an efficient AI agent using a small local model, Qwen2.5-Coder-32B. Instead of relying on massive context windows, he employs architectural solutions: task decomposition among sub-agents, external search tools, and structured data delivery, proving that architecture is more important than model size.

Anthropic announced a 25% increase in the base quota for Claude Code, but the removal of a temporary 50% bonus results in a net 17% reduction in limits for users.

Many companies evaluate AI tool effectiveness based on token counts or code usage percentages, which fails to capture real productivity. To measure impact, organizations must implement attribution metrics that link model output to code quality and business outcomes.

The Evolve to AI 2026 conference is back, focusing on the practical implementation of AI agents within organizations. Organizers are seeking expert speakers to cover topics such as autonomous development and orchestration.

Google is launching an innovative working model designed for advanced coding and autonomous agents. The upgrade arrived just three weeks after the previous version and includes a leap forward in bug fixing and complex document processing. Alongside performance improvements, the company is cutting rates by 50% to facilitate AI integration in organizations.

Swedish AI startup Lovable has completed a $400 million funding round, reaching a valuation of $13.3 billion. This marks a significant increase from the $6.6 billion valuation recorded in December of last year.

Meta has introduced Muse Code, an autonomous programming agent designed to compete with tools from Anthropic and OpenAI. The tool enables developers to automate code planning, writing, and testing.

The Israeli company Tabnine, a pioneer in AI-powered code completion tools, has been acquired by the American corporation Tricentis. The startup will continue to develop its product under the new ownership.

Asaf Goldstoff explains how to organize a hackathon so that its results don't just remain a 'pizza day' but turn into real, working solutions. Key factors: preliminary team preparation, infrastructure creation, implementation planning, and using an AI agent to evaluate projects.

The AI revolution is transforming team building and candidate assessment. Join our upcoming webinar to learn how to adapt your recruitment processes.