Emerging Tech & Research — OffNet Newsroom

The Register 2026-08-13 general

Loongson CPUs Found With Leaky Caches Allowing VM Data Extraction

Researchers have identified cache side-channel vulnerabilities in Chinese Loongson processors that allow attackers to extract confidential data. The flaw is significant enough to enable data exfiltration even when the attacker operates from within an isolated guest virtual machine. This finding highlights persistent architectural risks in specific processor lines regarding information leakage through shared hardware resources.

Loongson processors exhibit cache side-channel leaks exploitable for data extraction
Attackers can bypass VM isolation to read sensitive host or sibling VM data
Virtualization defenses are insufficient against this specific hardware-level vulnerability
Audits needed for infrastructure relying on Loongson silicon for security boundaries

Read at source →

GitHub Trending (daily) githubrepos ⚠ unverified date/source

Needle 2: 14MB Open Model for Tool Calling on Edge Devices

Cactus Compute released Needle 2, a 45M-parameter open model designed for tool calling, device control, and structured data extraction. The entire model is packaged as a single 14MB binary requiring only 28MB of RAM, utilizing CQ2-bit quantization. It competes with significantly larger models like FunctionGemma 270M while being 5x to 70x smaller and using 2 bits versus 16-bit precision.

Runs full sessions on edge devices like phones and wearables with minimal RAM usage.
Significantly smaller (5x-70x) than comparable 16-bit models like FunctionGemma.
Provides Python package for inference, LoRA fine-tuning, and model export.
Optimized for tool calling and structured extraction tasks on constrained hardware.

Read at source →

arXiv cs.AI 2026-08-13 researchai

Control-theoretic governance prevents multi-LLM agent conversation collapse

This paper demonstrates that interacting LLM agents with opposing goals often fail to reach a shared outcome, resulting in one agent capitulating or stalling. To solve this, the authors propose an Experience Orchestrator (EO) that applies control theory to manage joint agent trajectories. In a simulated financial services scenario, EO uses a Contextual Bandit to dynamically select content strategies, guiding the interaction toward a successful advisor contact despite realistic user resistance.

Confirms that structurally opposed LLM agents without shared goals tend to collapse rather than compete.
Introduces the Experience Orchestrator (EO) as a control layer to substitute for missing shared goal functions.
Uses a Contextual Bandit to dynamically select content arms based on real-time conversational context.
Validates the approach in a simulated financial services environment with psychologically realistic user resistance.
Demonstrates that external governance can steer multi-agent interactions toward specific business objectives.

Read at source →