Striving to come up with answers that please humans may make chatbots more likely to pull the wool over our eyesJuSun/Getty Images
Giving AI chatbots human feedback on their responses seems to make them better at giving convincing, but wrong, answers.
The raw output of large language models (LLMs), which power chatbots like ChatGPT, can contain biased, harmful or irrelevant information, and their style of interaction can seem unnatural to humans. To get around this, developers often get people to evaluate a model’s responses and then fine-tune it based on this feedback.
AIs are more likely to mislead people if trained on human feedback
Related Posts
Indian Govt And Meta Have A New Plan To Tackle Online Scams – News18
Last Updated: October 18, 2024, 13:40 ISTThe government is using the platform to digitally make people awareMeta will use its digital platforms to spread the message among millions of users…
After rejecting Google takeover, cyber firm Wiz says it will IPO ‘when the stars align’
LONDON — Cybersecurity firm Wiz is seeking to hit $1 billion of annual recurring revenues next year, the company’s billionaire co-founder Roy Reznik told CNBC, adding that the firm will…