All news
11850
US Treasury Wants Access to Anthropic's Mythos Model to Hunt for Vulnerabilities
The US Treasury's technology team is seeking access to Anthropic's Mythos model to probe it for vulnerabilities and assess the risks of using such systems in…

Fintech group Svoi explains how to make LLM coding agents cheaper and more accurate
Fintech group Svoi has published a practical guide on turning an LLM from an "enhanced search" into a controllable agent, cutting token costs and improving code…

How a Habr author turned seven n8n workflows into an autonomous AI news system
In six weeks, the author turned a brittle set of seven n8n workflows into a single Python pipeline with 11 workers, 5 AI agents, a local LLM and Telegram control.

Why OpenCode and Strong Models Write Green but Useless Tests — and How to Fix It

Guidesly shows how Jack AI on AWS turns trip media into reports and marketing

Google DeepMind unveils Gemini Robotics-ER 1.6 for autonomous real-world tasks

Boston Dynamics and Google DeepMind teach Spot to reason on industrial inspection rounds

Cybersecurity industry pushes back on Anthropic's Mythos vulnerability-hunting claims
An Aisle executive questioned Anthropic Mythos's unique cyber capabilities: in internal tests, cheap open-source models found the same vulnerability.

OpenAI opens access to a vulnerability-hunting model in response to Anthropic's Mythos
OpenAI has opened limited access to a model for finding software vulnerabilities, a week after Anthropic announced Mythos, as the race for the AI cybersecurity…

NVIDIA opens free API to 100+ AI models with OpenAI-compatible access

Why the Brain Is Hundreds of Millions of Times More Efficient Than GPT-4, and Where Neuromorphic Chips Are Heading

Anthropic updates Claude Code with Routines, parallel sessions and autonomous tasks on Mac

Anthropic unveiled Mythos as too dangerous to release — and the problem reaches well beyond banks

ASML raises its 2026 forecast as AI drives demand for chipmaking equipment
ASML lifted its 2026 revenue forecast to €36–40 billion after a strong quarter, as AI infrastructure spending speeds up fab expansion and lithography demand.

ChatGPT study: does a feminine-form prompt affect coding performance?
An independent LiveCodeBench experiment found that in GPT-5.4 mini, a feminine self-presentation in a Russian prompt slightly lowers pass@1, especially on hard…









