Intellectual hub of the topic
Researchers have proposed a new approach to evaluating voice AI agents that considers not only the accuracy of answers but also the quality of a live conversation.
The Korean company Upstage has released the Solar Pro 3 language model, which handles multi-step agentic tasks twice as effectively as its predecessor.
How SmartSearch learned to pull signal from the noise of messy dialogues without complex algorithms – and why effective ranking is more valuable than a perfectly organized data archive.
GitHub has expanded the capabilities of Code Security: artificial intelligence now helps find vulnerabilities in areas where static analysis previously fell short.
The startup Notch has shared how to create AI agents capable of performing real actions without losing control, even in regulated industries.
The popular method for comparing AI transcription services isn't as objective as it seems – we'll explore where it falls short.
AI: Events
Technical context • Infrastructure
Red Hat OpenShift AI offers a solution for the rapid processing of unstructured data in RAG systems using a distributed architecture.
At the AAAI 2026 conference, the spotlight shifted from the raw power of AI agents to their transparency. We explore why this shift is a deal-breaker for anyone integrating autonomous systems into business processes.
Databricks has developed its own approach to creating AI agents – the coSTAR system, which allows the team to work quickly without losing control over quality.
Want to dive deeper into the world
of neuro-creativity?
Be the first to learn about new books, articles, and AI experiments
on our Telegram channel!