All news
11850
Selectel engineer shows an LLM agent that finds available domain names
A Selectel engineer built a Python service that asks an LLM to generate domain names and checks them via WHOIS right away, keeping only the available ones.

Anthropic explains when to start a new session in Claude Code, and how
Anthropic shipped a /usage command and explained how to manage Claude Code sessions so a million tokens of context doesn't turn into noise and degrade answers.

Niantic shows how Pokémon Go turns player actions into AI datasets
Niantic, Google and other companies increasingly turn everyday user actions, from gaming and commuting to solving CAPTCHAs, into training data for AI, navigation…

Spektr raises $20M for AI agents that handle KYC and KYB in financial compliance

OpenAI adds sandbox execution to Agents SDK for controlled, safer AI agent runs

MTS shows how OpenClaw was wired to a robot, taking an AI agent into the physical world

ECB to discuss risks of Anthropic's Mythos model for the financial system with banks

Claude Sonnet helps executives build an AI officer for tough decisions in 8 hours
At the closed Snow BASE hackathon, a team of a CEO, CTO and CIO built CAITO in eight hours: an AI officer on Claude Sonnet that changes its position only when new…

Hugging Face explains how to fine-tune multimodal embedding and reranker models
Hugging Face has published a practical guide to training multimodal embedding and reranker models in Sentence Transformers, showing how domain tuning improves…

EU wants to force Google to share search data with rival chatbots

MIT Technology Review: Small Language Models Are Becoming the Foundation of Government AI Adoption

MIT Technology Review: In Enterprise AI, the Edge Comes From the Operational Layer, Not the Model

ServiceNow and Atlassian push the ITSM market toward AI platforms over out-of-the-box tools

Anthropic Calls Mythos Too Dangerous: The Model Found Holes in the Internet's Core Software
Anthropic restricted access to Mythos after internal tests: the model found and exploited vulnerabilities in Linux, browsers and other critical software faster than…

Cursor and Microsoft Research test whether an AI agent needs full debugger access
An experiment with Debug2Fix and Cursor's Debug Mode suggests breakpoints, step-through execution and evaluate expression can help AI agents fix real bugs…









