Mail.ru Reduces Lifetime 1TB Cloud Storage Promo to Standard 8GB Quota for Select Users

Kimi K3 Open Model Surpasses Closed AI Leaders with Million-Token Context and 896 Experts

Kimi K3 is an open-weights model that outperforms closed systems from GPT and Anthropic on several independent benchmarks. Developers achieved this by scaling three dimensions simultaneously: one million tokens of context, deeper layers, and 896 Mixture-of-Experts specialists. The team replaced the standard KV-cache with a fixed-size state matrix updated via the delta-rule, solving numerical instability by clamping the forgetting coefficient alpha between e^-5 and 1. Sequential state updates were parallelized across chips, GPUs, and multi-GPU nodes using the open-source FlashKDA kernel built on CUTLASS. Inter-layer information flow was preserved through learned pseudo-queries that selectively retrieve relevant outputs from prior blocks rather than passing full activations. Load balancing across 896 routed experts uses per-expert quantile thresholds and a distributed histogram method to guarantee fair token allocation without full sorting.

Innostage Completes Functional Testing of PT NGFW 1.10.3 Across 156 Criteria

Innostage has published the second part of its evaluation of PT NGFW version 1.10.3, focusing on functional capabilities rather than raw performance. The testing covered 156 individual checks grouped into categories such as basic technical features, firewalling, IDS/IPS, web filtering, malware protection, logging, routing, deployment, cryptographic controls and access management. Out of the total, 136 checks passed fully, seven passed with remarks, and 13 did not meet the predefined criteria. Key confirmed functions include high-availability clustering, centralized management via PT-MNGT, AD-based rule application, Site-to-Site VPN, TLS inspection, and Syslog integration with external security systems. Several advanced scenarios, including custom block pages, application risk classification, and centralized software distribution, were not confirmed under the test conditions. The report provides detailed protocol notes that help organizations map product capabilities against their specific infrastructure and regulatory requirements.

MITRE ATT&CK in Detective Settings: Avito Launches Cyberdetective Game for Security Awareness Training

Avito security awareness specialist Ilya Nikiforov has developed Cyberdetective, a browser-based detective game that trains employees against real-world attack techniques mapped to MITRE ATT&CK. The game places players in the fictional company Lumi where they control mascot Spock the honey badger, investigate six cases involving voice cloning, MFA fatigue, lookalike domains, and physical tailgating. Each scenario trains specific defensive habits such as callback verification and evidence preservation rather than simple rule recall. Development took 74 days with AI agents handling code, tests, art generation, voice synthesis, and video while the creator focused on scenario design and methodology. The project includes 21 additional training tasks on a firing range covering phishing, AI misuse, and supply-chain risks, supported by 2,200 automated tests and an editor system for future content updates. The initiative demonstrates how non-developers can build production-grade security tools using modern AI tooling while maintaining strict data-protection controls.