OpenAI builds LifeVal to grade ChatGPT on childcare, budgets and paperwork
OpenAI said it used the internal evaluation for a year to steer ChatGPT toward acting on personal errands, with GPT-6 Astra scoring 80% in CNN's reporting.
By Ryan Merket · Published
Primary source: openai.com
Why it matters
LifeVal gives OpenAI a training target for personal agents that browse, use computers and act through connectors, extending the work-task logic of GDPVal into household life.
OpenAI announced LifeVal on November 2nd, a benchmark that grades AI models on everyday personal tasks including finding childcare, creating a budget, ordering groceries and accessing government services. OpenAI said it used LifeVal over the past year to track and drive improvement in model performance on those tasks.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.