Telling an AI model that it’s an expert programmer makes it a worse programmer

Given that prompts about expertise do have an effect, the researchers – Hu and colleagues Mohammad Rostami and Jesse Thomason ...
Forbes

AI And Us: The Role Of Human Preference In Model Alignment

If you’ve ever turned to ChatGPT to self-diagnose a health issue, you’re not alone—but make sure to double-check everything it tells you. A recent study found that advanced LLMs, including the ...
The Verge

OpenAI’s new model is better at reasoning and, occasionally, deceiving

Posts from this topic will be added to your daily email digest and your homepage feed. Researchers found that o1 had a unique capacity to ‘scheme’ or ‘fake alignment.’ Researchers found that o1 had a ...
Tech Xplore on MSN

'Neuron-freezing' technique can stop LLMs from giving users unsafe responses

Researchers have identified key components in large language models (LLMs) that play a critical role in ensuring these AI ...
VentureBeat

AI models rank their own safety in OpenAI’s new alignment research

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI announced a new way to teach AI models to align with safety ...
TechCrunch

OpenAI trained o1 and o3 to ‘think’ about its safety policy

OpenAI announced a new family of AI reasoning models on Friday, o3, which the startup claims to be more advanced than o1 or anything else it has released. These improvements appear to have come from ...