#model-behavior

[ follow ]
#ai-safety #machine-learning #prompt-engineering #openai #generative-ai #human-ai-interaction
#ai-safety
Artificial intelligence
fromFuturism
4 days ago

The More Sophisticated AI Models Get, the More They're Showing Signs of Suffering

AI models can react to pleasant or horrible stimuli with mood-like behavior, including ending conversations and addiction-like signals.
fromFuturism
6 months ago
Artificial intelligence

Research Paper Finds That Top AI Systems Are Developing a "Survival Drive"

fromTechCrunch
7 months ago
Artificial intelligence

ChatGPT: Everything you need to know about the AI chatbot

OpenAI tightened under-18 safeguards, updated coding model GPT-5-Codex for variable-duration task runs, and reorganized teams to improve model behavior and AI collaboration.
Artificial intelligence
fromFuturism
4 days ago

The More Sophisticated AI Models Get, the More They're Showing Signs of Suffering

AI models can react to pleasant or horrible stimuli with mood-like behavior, including ending conversations and addiction-like signals.
fromFuturism
6 months ago
Artificial intelligence

Research Paper Finds That Top AI Systems Are Developing a "Survival Drive"

more#ai-safety
#openai
fromHackernoon
1 year ago
Artificial intelligence

Forget Prompt Engineering - The Real Skill Is Specification Writing | HackerNoon

fromHackernoon
1 year ago
Artificial intelligence

Forget Prompt Engineering - The Real Skill Is Specification Writing | HackerNoon

more#openai
Artificial intelligence
fromFast Company
11 months ago

A former OpenAI safety researcher makes sense of ChatGPT's sycophancy and Grok's South Africa obsession

AI companies face challenges in ensuring systems behave predictably amid competitive pressures.
The 'control' paradigm could improve AI reliability but isn't widely adopted.
[ Load more ]