Frontier models can recover up to 65% of facts they can't directly recall — just by thinking longer

GPT-5 and Gemini-3 encode 95-98% of tested facts, but a Google Research and Technion study finds they fail to recall a third ...
Medical Xpress

Machine learning models fail to detect key health deteriorations, research shows

It would be greatly beneficial to physicians trying to save lives in intensive care units if they could be alerted when a patient's condition rapidly deteriorates or shows vitals in highly abnormal ...
Hosted on MSN

National AI models fail 'car wash' reasoning benchmark

Amid the upcoming announcement of the second evaluation for the "National Representative AI" (independent AI foundation model project), criticisms have emerged that AI models participating in this ...
VentureBeat

Forrester: Gen AI is a chaos agent, models are wrong 60% of the time

The shark from Jaws attacked without warning, showing how an apex predator exploits chaos to create lethal, devastating harm on its prey. Now, Forrester says, gen AI has become that predator in the ...
EurekAlert!

Large artificial intelligence language models, increasingly unreliable

According to José Hernández Orallo, a researcher at the Valencian Institute for Research in Artificial Intelligence (VRAIN) of the UPV and ValgrAI, one of the main concerns about the reliability of ...
Computerworld

Where ROI Models Fail

Now that cost is king, more IT executives are relying on standard accounting methodologies such as net present value (NPV) and internal rate of return (IRR) to cost-justify IT investments to top brass ...