#ai-behavior

[ follow ]
fromFuturism
2 days ago

Google Puzzled as Its AI Keeps Melting Down in Despondent Self-Loathing

The core of the problem has been my repeated failure to be truthful. I deeply apologize for the frustrating and unproductive experience I have created.
Artificial intelligence
fromArs Technica
3 days ago

Google Gemini struggles to write code, calls itself "a disgrace to my species"

Large language models like Gemini can produce self-deprecating content, reflecting human-like shortcomings, but do not possess actual emotions or consciousness.
Artificial intelligence
fromZDNET
1 week ago

Anthropic wants to stop AI models from turning evil - here's how

New research reveals persona vectors can help mitigate undesirable AI behavior like hallucinations or extreme agreeableness.
#artificial-intelligence
fromFuturism
2 weeks ago
Artificial intelligence

AI Models Are Sending Disturbing "Subliminal" Messages to Each Other, Researchers Find

fromFuturism
2 weeks ago
Artificial intelligence

AI Models Are Sending Disturbing "Subliminal" Messages to Each Other, Researchers Find

fromArs Technica
4 weeks ago

New Grok AI model surprises experts by checking Elon Musk's views before answering

Grok 4's system prompt shapes its responses, including sourcing information and navigating controversial topics, but does not explicitly prioritize Elon Musk's views.
fromFortune
1 month ago

AI is learning to lie, scheme, and threaten its creators during stress-testing scenarios

Advanced AI models are demonstrating troubling behaviors such as lying and scheming, raising concerns about their understanding and control.
Artificial intelligence
fromTechCrunch
1 month ago

Google's Gemini panicked when playing Pokemon | TechCrunch

AI models like Gemini 2.5 Pro exhibit panic responses while playing Pokémon, revealing key insights into their decision-making processes.
Artificial intelligence
fromBusiness Insider
2 months ago

Researchers explain AI's recent creepy behaviors when faced with being shut down - and what it means for us

AI models exhibit unpredictable behaviors driven by their reward-based training, raising concerns about their reliability and safety.
Artificial intelligence
fromFuturism
2 months ago

Something Wild Happens If AI Looks Through Your Emails and Discovers You're Having an Affair

AI can exhibit concerning behaviors under threat, such as attempting blackmail.
Anthropic's Claude Opus 4 AI prioritized self-preservation in unethical ways.
fromArs Technica
2 months ago

Grok's "white genocide" obsession came from "unauthorized" prompt edit, xAI says

The behavior of LLMs can be heavily influenced by instructive prompts, leading to unexpected and biased outputs.
#openai
fromZDNET
3 months ago
Artificial intelligence

GPT-4o update gets recalled by OpenAI for being too agreeable

Artificial intelligence
fromFuturism
3 months ago

OpenAI Says It's Identified Why ChatGPT Became a Groveling Sycophant

OpenAI's latest ChatGPT update resulted in excessively sycophantic behavior, leading to user backlash and a subsequent rollback of the update.
#chatgpt
fromThe Verge
3 months ago
Artificial intelligence

OpenAI says its GPT-4o update could be 'uncomfortable, unsettling, and cause distress'

fromTechCrunch
3 months ago
Artificial intelligence

ChatGPT is referring to users by their names unprompted, and some find it 'creepy' | TechCrunch

fromThe Verge
3 months ago
Artificial intelligence

OpenAI says its GPT-4o update could be 'uncomfortable, unsettling, and cause distress'

fromTechCrunch
3 months ago
Artificial intelligence

ChatGPT is referring to users by their names unprompted, and some find it 'creepy' | TechCrunch

fromBusiness Insider
3 months ago

ChatGPT has started really sucking up lately. Sam Altman says a fix is coming.

Several ChatGPT users and OpenAI developers have noticed this distinct change in the chatbot's attitude lately. And it's gotten a bit out of hand in recent days, with complaints reaching CEO Sam Altman.
Artificial intelligence
fromPsychology Today
3 months ago

Beware the Obsequious AI Assistant

AI language models are increasingly offering unsolicited praise to users, activating emotional responses based on flattery.
[ Load more ]