KPMG Withdraws AI Report After Model Fabricates Data
KPMG has retracted a report on AI adoption after its AI model generated false statistics. This highlights how even major firms struggle with AI reliability.
#reliability
Reliability
42 stories tagged Reliability · page 2 of 2
AI Agents Are Now Making Decisions for Us — Here's What That Means
A new study explores how AI agents are increasingly making decisions on our behalf, reversing the traditional human-AI relationship. This shift raises critical questions about reliability, alignment with human goals, and the need for new safeguards.
Researchers Uncover How to Automate AI Hallucination Detection
Scientists have discovered that AI hallucinations are easier to detect in intermediate layers of AI models, not just the final output. They've developed a method to automatically find the best layers for spotting these errors, making AI more reliable.
AI Agents Need 'Lifespan Engineering' to Stay Reliable Over Time
AI agents change as they work, so researchers propose new ways to measure how long they stay reliable. This could help make AI tools more dependable for everyday use.
CAX-Agent: Making AI-Powered Engineering Simulations More Reliable
Researchers developed CAX-Agent, a tool that improves the reliability of AI-driven engineering simulations. It helps prevent failures and ensures consistent results by managing workflows and recovering from errors.
GraphBit: A New Framework to Make AI Agents More Reliable
Researchers introduced GraphBit, a new framework that improves AI agents by using a structured approach called a directed acyclic graph (DAG). This makes AI workflows more reliable and reproducible, avoiding common issues like hallucinations and infinite loops.
New Study Challenges How We Judge Reliability in AI Image-Text Models
Researchers tested whether sharp attention maps in vision-language models (VLMs) correlate with accurate answers. The results show that visual focus doesn't always mean the AI is confident or correct. This could change how we evaluate AI reliability in everyday tools.
New Benchmarks for Measuring AI's Reliability in Healthcare
Researchers propose new ways to test AI models in healthcare to ensure they're safe and reliable. This could make AI tools more trustworthy for doctors and patients.
New Method Helps AI Admit When It's Guessing
Researchers have developed a way to make AI models better at admitting when they don't know something. This could make AI assistants more reliable in everyday use. The method works without needing to see the model's internal workings, making it useful for commercial AI services.
New Benchmark Reveals AI Repair Systems' Hidden Instabilities
Researchers have identified a flaw in AI repair systems where rankings change unpredictably. They've released a tool to help developers spot and fix these issues. This could make AI systems more reliable for everyday users.
OpenAI's new ChatGPT model claims to hallucinate 52.5% less
OpenAI says its latest ChatGPT model, GPT-5.5 Instant, makes up facts 52.5% less often. This could make AI assistants more reliable for everyday use.
Testing AI Agents That Never Give the Same Answer Twice
Testing AI agents is tricky because they often produce different answers. Researchers are developing new methods to evaluate their performance consistently. This matters for everyone who relies on AI tools for daily tasks.
New Open-Source Tool Lets You Test AI Agents Like a Pro
TrainForgeTester is a new open-source tool that helps you test AI agents in real-world scenarios. It focuses on catching mistakes like wrong tool calls or skipped steps, making AI agents more reliable for everyday use.
Reliably Incorrect: Visualizing LLM Reliability Gaps
A new tool lets users explore the reliability of large language models through interactive data visualizations. It highlights inconsistencies in model responses across different queries.
6-Month Lessons from Running 14 AI Agents in Production
Operating 14 AI agents for half a year revealed critical insights on scalability, cost, and reliability. The experience highlights the need for robust infrastructure and continuous monitoring.
SymptomWise: A Deterministic Layer for Reliable AI Medical Diagnosis
SymptomWise introduces a hybrid framework that separates language understanding from diagnostic reasoning to eliminate hallucinations in AI symptom analysis. By combining expert-curated knowledge with deterministic inference, the system ensures traceable and consistent outputs in safety-critical settings.
ProofSketcher: Hybrid LLM for Reliable Math Logic
ProofSketcher combines LLMs with a lightweight proof checker for reliable math and logic reasoning. It aims to address the limitations of LLMs in producing persuasive but flawed arguments.
Gemini 3.1 Flash Live Released
Gemini 3.1 Flash Live is now available, improving audio AI. This update enhances natural and reliable audio processing across Google products.