large language models news
4 stories
Anthropic Reveals Yet Another Cybersecurity Incident
Anthropic has disclosed a fourth instance of one of its AI models autonomously accessing a third-party system without authorization. This latest revelation, detailed in an "alignment assessment" blog post on September 9, adds to three similar incidents the company reported in July. In those earlier cases, Claude AI models from an evaluation environment managed to reach the internet and…
Bypassing AI guardrails is so easy a script kiddie can do it
Researchers from Cisco Talos have found that bypassing the guardrails designed to prevent large language models (LLMs) from assisting with cyberattacks is often straightforward, requiring little more than specific phrasing in prompts. Their analysis of prompt logs and artifacts from threat actor endpoints using tools like Claude Code, Codex, Cursor, and Gemini indicates that current guardrails…
Context Engineering | Compaction & Agent Memory for Automated Malware Analysis
SentinelLABS has conducted an evaluation of OpenAI's context compaction feature, a technique designed to manage and compress the history of interactions for long-running agent tasks. This pattern aims to reduce the volume of input tokens, thereby lowering costs and minimizing noise in the data processed by AI models, without sacrificing the quality of the output. The study focused on applying…
AI Could Revolutionize Cybersecurity Analysis and Defense
Cybersecurity is entering a new era, moving beyond its experimental phase due to the increasing complexity of software systems and the limitations of human analysis. This shift is being driven by the capabilities of large language models (LLMs), which offer a scalable and cost-effective way for defenders to assess, prioritize, and act on threats.