EP 39: How To Keep ChatGPT From Lying

What do you do when ChatGPT keeps lying? That's referred to as ChatGPT "hallucinating." Today we're breaking down how to make sure you're always getting up-to-date and factual information from ChatGPT.

For more details head to our episode page!

Time Stamps:
Full show notes here
[00:01:15] Oracle stock rises after announcement of generative AI
[00:02:12] AI is coming to Starbucks
[00:03:15] Are AI watermarks coming to social media campaigns?
[00:04:46] What are ChatGPT Hallucinations?
[00:09:35] 5 Ways to Avoid ChatGPT Hallucinations
          [00:09:40] 1. Using the Wrong Version
          [00:11:32] 2. Using the Wrong Mode
          [00:13:32] 3. Bad at Prompting
          [00:15:57] 4. Not Specific Enough
          [00:17:28] 5. Not Feeding ChatGPT Data
[00:19:55] Audience Questions about ChatGPT

Topics Covered in This Episode:
1. Large Language Models and Hallucinations
- Discussion on the potential for large language models to provide inaccurate or false responses
- Focus on Chat GPT

2. Recent AI-Related News Stories
- Oracle's entry into the generative AI space
- Starbucks' implementation of AI chatbots at their drive-thrus
- Ogilvy's push for advertisers to disclose their use of generative AI

3. 5 Tips to Avoid Chat GTP from Providing Hallucinations
- Keywords and its context
- Information input
- Shorter text
- Fine-tuning
- Avoiding keyphrases and unlimited text

Keywords:
Everyday AI, language models, Chat GPT, inaccurate, false responses, AI-related news, Oracle, generative AI, Starbucks, AI chatbots, drive-thrus, Ogilvy, advertisers, campaigns, five tips, avoiding hallucinations, false responses, podcast, speaker, thank you, joining, subscribe, rating, daily newsletter, sign up, motivational message, break barriers, next episode.

Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

Ready for ROI on GenAI? Go to youreverydayai.com/partner