#model-behavior
#model-behavior

[ follow ]

#openai #generative-ai #post-training #ai-behavior #oai-labs #ai-engineering #specification-development

Artificial intelligence

OpenAI reorganizes research team behind ChatGPT's personality | TechCrunch

Artificial intelligence

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

Artificial intelligence

OpenAI reorganizes research team behind ChatGPT's personality | TechCrunch

Artificial intelligence

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

Artificial intelligence

On Grok and the Weight of Design | HackerNoon

Targeted fine-tuning can lead to systemic behavioral distortions in large-scale models.

Artificial intelligence

fromFast Company

As AI models start exhibiting bad behavior, it's time to start thinking harder about AI safety

AI models are evolving rapidly, presenting increased safety risks as their capabilities expand.

Artificial intelligence

fromFast Company

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 ]