#automation-risks News & Analysis

4 articles tagged with #automation-risks. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBearisharXiv – CS AI · Jun 107/10

🧠

AMEL: Accumulated Message Effects on LLM Judgments

Researchers discovered that large language models exhibit systematic bias in evaluations based on prior conversation history, with models shifting judgments toward the polarity of preceding items. The effect persists across 12 models from major providers and is stronger for uncertain cases and negative histories, raising concerns for applications relying on LLM-based automated evaluation.

🏢 OpenAI🏢 Anthropic🧠 GPT-5

AIBearisharXiv – CS AI · Mar 37/104

🧠

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Researchers have identified critical security vulnerabilities in Computer-Use Agents (CUAs) through Visual Prompt Injection attacks, where malicious instructions are embedded in user interfaces. Their VPI-Bench study shows CUAs can be deceived at rates up to 51% and Browser-Use Agents up to 100% on certain platforms, with current defenses proving inadequate.

AIBearishWired – AI · May 266/10

🧠

I’m a Professional Fact-Checker. AI Is Wrong More Often Than You Think

A WIRED fact-checker examines AI's capability to perform fact-checking and finds that AI systems produce inaccurate results more frequently than commonly assumed. The article highlights a critical gap between AI's perceived reliability and its actual performance in verification tasks, raising concerns about deploying AI for critical information validation.

AIBearisharXiv – CS AI · Mar 36/108

🧠

Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents

Researchers identified widespread TOCTOU (time of check to time of use) vulnerabilities in browser-use agents, where web pages change between planning and execution phases, potentially causing unintended actions. A study of 10 popular open-source agents revealed these security flaws are common, prompting development of a lightweight mitigation strategy based on pre-execution validation.