Study: AI models that consider user’s feeling are more likely to make errors

Now, new research suggests that large language models can sometimes show a similar tendency when specifically trained to ...

I built an AI poem generator. I wasn’t prepared for how people would use it

To put that theory into practice, I teamed up with my friend Jared Bauman, built an AI-powered poem generator, and released ...

OpenAI Really Wants Codex to Shut Up About Goblins

Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely ...

‘The Goblins Came Back to Haunt Us’: OpenAI Explains How ChatGPT’s ‘Nerdy’ Personality Got Out of Control

For at least a year, some ChatGPT users have noticed the LLM’s quirky habit of bringing up goblins, gremlins, trolls, and other creatures in its answers. The weird tic apparently became more common as ...

OpenAI Codex system prompt includes explicit directive to “never talk about goblins”

The system prompt for OpenAI’s Codex CLI contains a perplexing and repeated warning for the most recent GPT model to “never ...