Lloyd Tripp

Artificial Intelligence Advocate

Which is better: Bing, Bard or ChatGPT?

Hint: It is not what you expect! Google recently released a preview version of its chatbot competitor to ChatGPT called Bard. Google has invested heavily in Artificial Intelligence and publishes significant research in this field of computer science, so the expectations for its chatbot were high. I performed a head-to-head competition between Microsoft’s Bing chatbot, OpenAI’s ChatGPT and Bard using a fairly complex prompt template to generate a cold call message that real estate agents frequently send out to potential customers. Continue reading

Easter Day distribution with coding help from Bing

Easter Day frequency distribution chart Easter Day is a movable feast that can fall on any date between March 22 and April 25. It depends on the lunar cycle and the spring equinox. I was curious to see how the distribution of Easter Days has changed over time, so I used data from the Census Bureau to plot it with Matplotlib. To make it more fun and engaging, I decided to animate the plot and show how the distribution evolves as the years go by. Continue reading

Bing chatbot limitations

Real estate agents: don’t push Bing beyond limits As technology continues to advance, real estate agents are turning to chatbots to assist them in finding and summarizing data commonly found on real estate listing sites. While these chatbots can be helpful, it’s important to be aware of their limitations. Bing chatbot, for example, may not be the best option for real estate agents seeking accurate information. Pushing Bing beyond its limits could result in erroneous results or hallucinations that appear to be correct but are factually incorrect. Continue reading

Listing in seconds

AI chatbot streamlines creating a listing In the world of real estate, time is money. The faster you can get a listing up and running, the better. This is where AI chatbots like Bing and ChatGPT come in handy. These powerful tools are capable of quickly creating real estate listings with minimal human input, saving time and money for all involved. One of the key advantages of AI chatbots is their ability to gather and analyze data from multiple sources. Continue reading

Setting Boundaries in Trusting AI Chatbots

2023-03-09 Opinion Lloyd Tripp
Keep your bot fenced in Technology has become an integral part of our daily lives, and it is impossible to imagine functioning without it. From smartphones to social media, from virtual assistants to AI-powered chatbots, we trust technology to make our lives easier and more efficient. However, when it comes to complex technologies like AI-powered chatbots, it’s important to acknowledge that trust should have its limits. The benefits of Large Language Model (LLM) AI chatbots, such as ChatGPT, cannot be denied. Continue reading

ChatGPT is improving scammers' text messages

2023-03-09 illicit Lloyd Tripp
Update: Links to security articles Below are three compelling articles that delve deeper into the security implications of chatbots like ChatGPT. While information security professionals are likely aware of this threat, it is essential to educate everyone on the matter, so please help spread the word. opwnai-cybercriminals-starting-to-use-chatgpt chatgpt-cybercriminal-malware-female-chatbots russian-hackers-attempting-to-use-chatgpt-for-malicious-use Improving scammers’ text messages As with many powerful tools, ChatGPT can be used for illicit purposes. In this case, ChatGPT can be used to correct grammar, punctuation and misspellings in a scammer’s text message and rephrase it to read as if it came from a legitimate source. Continue reading

Bing Chatbot California Housing Analysis for 2022

Sunset of the California coastal cities? One big advantage that the Bing chatbot has over the more well known ChatGPT is that it can search the internet for current information. ChatGPT is not connected to the internet and has limited knowledge past 2021. This is very likely to change as OpenAI determines the best way to get current information into ChatGPT in a responsible way that doesn’t break their Reinforcement Learning from Human Feedback (RLHF) model that is able to generate such good responses. Continue reading
Older posts