marktechpost

A Coding Implementation to Build a Hierarchical Planner AI Agent Using Open-Source LLMs with Tool Execution and Structured Multi-Agent Reasoning

In this tutorial, we build a hierarchical planner agent using an open-source instruct model. We design a structured multi-agent architecture comprising a planner agent, an executor agent, and an ...
VentureBeat

Microsoft's new AI training method eliminates bloated system prompts without sacrificing model performance

In building LLM applications, enterprises often have to create very long system prompts to adjust the model’s behavior for their applications. These prompts contain company knowledge, preferences, and ...
The Nation Newspaper

Multi-level collation biggest threat to elections, says INEC

The Independent National Electoral Commission (INEC) has identified multi-level collation of results as the greatest threat to Nigeria’s electoral process. INEC Chairman, Prof. Joash Amupitan, said ...
InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale. High inference latency and ...
Infosecurity-magazine.com

Chinese AI Firms Hit Claude with Distillation Attacks, Anthropic Warns

Generative AI firm Anthropic said three Chinese AI companies have generated millions of queries with the Claude large language model (LLM) in order to copy the model – a technique called ‘model ...
InfoWorld

Anthropic alleges large-scale distillation campaigns targeting Claude

The AI company claims DeepSeek, Moonshot, and MiniMax used fraudulent accounts and proxy services to extract Claude’s capabilities at scale, even as experts point out that the industry itself relies ...
IEEE

LLM-PD : A Large Language Model-Driven Policy Distillation-Based Method for Multi-UAV Path Planning

Abstract: The Industrial Internet of Things (IIoT) has accelerated the adoption of multi-UAV systems in applications such as urban inspection and emergency response. However, effective path planning ...
CSOonline

Google fears massive attempt to clone Gemini AI through model extraction

Google detected and blocked a campaign involving more than 100,000 prompts that it claimed were designed to copy the proprietary reasoning capabilities of its Gemini AI model, according to a quarterly ...
Ars Technica

Attackers prompted Gemini over 100,000 times while trying to clone it, Google says

On Thursday, Google announced that “commercially motivated” actors have attempted to clone knowledge from its Gemini AI chatbot by simply prompting it. One adversarial session reportedly prompted the ...
Bleeping Computer

Google says hackers are abusing Gemini AI for all attacks stages

State-backed hackers are using Google's Gemini AI model to support all stages of an attack, from reconnaissance to post-compromise actions. Bad actors from China (APT31, Temp.HEX), Iran (APT42), North ...
VentureBeat

MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

When enterprises fine-tune LLMs for new tasks, they risk breaking everything the models already know. This forces companies to maintain separate models for every skill. Researchers at MIT, the ...