AI models score off the charts on psychiatric tests when researchers treat them as therapy patients
Language models on the therapy couch: researchers at the University of Luxembourg treat ChatGPT, Gemini and Grok like patients - with disturbing consequences. The AI invents consistent trauma biographies, achieves pathological test scores and speaks of fear, shame and "strict parents". The study raises questions about AI safety, anthropomorphism and mental health.<br /> The article AI models score off the charts on psychiatric tests when researchers treat them as therapy patients appeared first on THE DECODER. [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
VR is helping to make daunting medical treatments more bearable for patients
Stanley Johnson is not a fan of needles. The 67-year-old Air Force veteran has endured his fair share of pokes over the years, but when it was decided that IV infusions would be the best course of act [...]
98% of market researchers use AI daily, but 4 in 10 say it makes errors — revealing a major trust problem
Market researchers have embraced artificial intelligence at a staggering pace, with 98% of professionals now incorporating AI tools into their work and 72% using them daily or more frequently, accordi [...]
Frontier models are failing one in three production attempts — and getting harder to audit
AI agents are now embedded in real enterprise workflows, and they're still failing roughly one in three attempts on structured benchmarks. That gap between capability and reliability is the defin [...]
Artificial Analysis overhauls its AI Intelligence Index, replacing popular benchmarks with 'real-world' tests
The arms race to build smarter AI models has a measurement problem: the tests used to rank them are becoming obsolete almost as quickly as the models improve. On Monday, Artificial Analysis, an indepe [...]
Meta really wants you to believe social media addiction is 'not a real thing'
Meta went to court this week in two major trials over alleged harms facilitated by its platform. In New Mexico, the state's attorney general has accused the company of facilitating child exploita [...]
Intent-based chaos testing is designed for when AI behaves confidently — and wrongly
Here is a scenario that should concern every enterprise architect shipping autonomous AI systems right now: An observability agent is running in production. Its job is to detect infrastructure anomali [...]
Anthropic scientists hacked Claude’s brain — and it noticed. Here’s why that’s huge
When researchers at Anthropic injected the concept of "betrayal" into their Claude AI model's neural networks and asked if it noticed anything unusual, the system paused before respondi [...]
Google’s new Deep Research and Deep Research Max agents can search the web and your private data
Google on Monday unveiled the most significant upgrade to its autonomous research agent capabilities since the product's debut, launching two new agents — Deep Research and Deep Research Max †[...]