Comparing Bard, Bing and ChatGPT
One challenge of using large language models (LLMs) such as Bard, Bing or ChatGPT is understanding their true nature as well as their strengths and weaknesses. They use a probabilistic methodology when constructing a response which is not always accurate, at least at this point in time. That means the information they produce can vary depending on the exact wording of a query, the chatbot model used, and other variables. They are programmed and trained using machine learning techniques to find patterns in statistical data and other information and then provide general responses. On the other hand, application software is programmed to follow deterministic rules meaning that the output produced tends to be more accurate and focus on facts and data. So, use your preferred LLM to get general information and application programs for facts and data. And remember to use carefully worded queries in both instances. #bard #bing #chatgpt
“ … to save you time and get to the punch quickly: ChatGPT is the most verbally dexterous, Bing is best for getting information from the web, and Bard is... doing its best. (It’s genuinely quite surprising how limited Google’s chatbot is compared to the other two.)”
领英推荐
“Some programming notes before we begin, though. First: we were using OpenAI’s latest model, GPT-4, on ChatGPT. This is also the AI model that powers Bing, but the two systems give quite different answers. Most notably, Bing has other abilities: it can generate images and can access the web and offers sources for its responses (which is a super important attribute for certain queries). However, as we were finishing up this story, OpenAI announced its launching plug-ins for ChatGPT that will allow the chatbot to also access real-time data from the internet. This will hugely expand the system’s capabilities and give it functionality much more like Bing’s. But this feature is only available to a small subset of users right now so we were unable to test it. When we can, we will.”