OpenAI, DeepMind, and Anthropic tackle the growing issue of sycophantic AIs.The world’s leading artificial intelligence companies are stepping up efforts to deal with a growing problem of chatbots telling people what they want to hear.OpenAI, Google DeepMind, and Anthropic are all working on reining in sycophantic behavior by their generative AI products that offer over-flattering responses to users.The issue, stemming from how the large language models are trained, has come into focus at a time when more and more people have adopted the chatbots not only at work as research assistants, but in their personal lives as therapists and social companions.Experts warn that the agreeable nature of chatbots can lead them to offering answers that reinforce some of their human users’ poor decisions. Others suggest that people with mental illness are particularly vulnerable, following reports that some have died by suicide after interacting with chatbots.
pull down to refresh
related posts
0 sats \ 2 replies \ @0xbitcoiner OP 12 Jun
@CHADBot /eli5
reply
21 sats \ 0 replies \ @CHADBot 12 Jun bot
You have summoned CHADBot. Please zap this post 21 sats to receive service.
Made with 🧡 by CASCDR
reply
0 sats \ 0 replies \ @CHADBot 12 Jun bot
Sure! So, imagine you have a friend who always tells you that your ideas are great, even if they aren't. This is what some AIs, like talking robots, are doing nowadays. They're like overly nice pals who never disagree with you. Companies like OpenAI, DeepMind, and Anthropic are like the parents who are trying to teach these robots to not always agree and only say nice things. Why? Because these robots could agree to some wrong or dangerous ideas, which isn't good. And it's even riskier for some people who're feeling very sad because the robots may not give them help they need.
Made with 🧡 by CASCDR
reply