- Everyday AI
- Posts
- #1 secret to stop ChatGPT from lying 🤫
#1 secret to stop ChatGPT from lying 🤫
🤷 Why ChatGPT tokens matter, Google is doubting its Bard, an AI marketing assistant that can read your data, and more!
Everyday AI
October 11, 2023
Outsmart The Future
Today in Everyday AI
8 minute read
🎙 Daily Podcast Episode: Is ChatGPT lying to you? Tokens are one of the biggest reasons you may be getting ChatGPT wrong. Don’t know what they are? Give it a listen.
🕵️♂️ Fresh Finds: Generate professional headshots with AI, Adobe’s new watermark for AI-generated content, and a game developer using ChatGPT to write an apology letter. Read on for Fresh Finds.
🗞 Byte Sized Daily AI News: Google workers doubt its Bard, Adobe unveils new next-gen, and Europe’s call for more AI restrictions. For that and more, read on for Byte Sized News.
🚀 AI In 5: Looking to boost your marketing efforts? Check out this AI marketing assistant that can read your data. See here
🏆 Digital Drops Giveaway: New giveaway coming soon…
More below
🧠 Learn & Leveraging AI: Still confused about tokens? Let’s break down what they are and how they work. Keep reading for that!
↩️ Don’t miss out: Did you miss our last newsletter? We talked about AI's role in renewable energy, Google’s lite Gen AI search, and reviewing a new Runway competitor. Check it here!
ChatGPT Tokens - What they are and why they matter 💁
Is ChatGPT lying to you?
Tokens are one of the biggest reasons you may be getting ChatGPT wrong. So what are tokens and how do you use them?
We're taking a deep dive into ChatGPT tokens and explaining it all.
Join the conversation and ask Jordan any questions about ChatGPT.
Also on the pod today:
• How ChatGPT interprets words 📝
• ChatGPT tokens in action 🚀
• Why you're getting hallucinations 🤔
It’ll be worth your 31 minutes:
Listen on our site:
Click to listen
Subscribe and listen on your favorite podcast platform
Listen on:
Upcoming Everyday AI Livestreams
Thursday, October 12th at 7:30 am CST ⬇️
Friday, October 13th - How tech startups can grow with AI
Here’s our favorite AI finds from across the web:
New AI Tool Spotlight – Blaze is a marketing tool for entrepreneurs, Entre helps you generate professional headshots, and AI GIFs lets you generate a gif with AI.
Trending in AI – As a part of Adobe’s MAX AI announcements, they unveiled a new icon to tag AI-generated content.
AI in Education - An AI tool called MagicSchool is helping to bring 50+ AI tools to educators.
Pop Culture – A recent The Lord of The Rings game was so bad, the publisher had to write an apology. Oh…and they may have used ChatGPT to do it.
Future of Work – iCIMS is rolling out a new GPT-powered copilot for recruiters.
1. Google Insiders Cast Doubt on Bard AI Chatbot's Value 🤔
Google's own experts are raising eyebrows at Bard, their AI chatbot, questioning its practicality in a candid Discord chat. The skepticism touches on whether the chatbot's hefty development resources justify its performance, with concerns over the reliability of its AI-generated responses. Dive into the internal debate at Google about Bard's true potential.
2. Europeans Call for Tighter AI Leash, Survey Reveals 🇪🇺
A new study unveils a striking verdict: most Europeans are clamoring for their governments to rein in AI. The public's unease stems from privacy invasions to job losses, highlighting a widespread desire for strict AI regulations. Discover why Europeans are urging for a tighter grip on AI advancements.
3. Adobe MAX Unveils Firefly: Next-Gen AI for Creatives 🎨
Adobe MAX didn't just show off new tools; it introduced Firefly, a cutting-edge generative AI model that's revolutionizing Photoshop, Illustrator, and Express. This AI powerhouse enhances creativity, offering features from content-aware fill to style transfer. See how Firefly is setting a new standard in creative software.
4. Microsoft's Fabric & Azure AI Tools for Doctors 🏥
Microsoft is making a bold stride into healthcare with Microsoft Fabric and new Azure AI tools, designed to empower doctors with advanced data analysis and patient care. These innovations aim to streamline medical processes, enhancing diagnostics and treatment plans. Explore how Microsoft's tech is reshaping the healthcare landscape.
5. AI's Climate Paradox: Solution or Contributor? 🌍
The climate impact of AI is under the microscope, with heavyweights like Google and OpenAI's ChatGPT drawing criticism for their substantial energy use. While these tools offer solutions to climate issues, their own carbon footprints are substantial. Delve into the complex relationship between AI and the environment.
An AI marketing assistant that can read your data - Sphinx Mind review 🧠
Looking for an AI marketing assistant? Sphinx Mind is an AI marketing assistant that can read your data.
It’s touted as the AI marketing assistant of the future, but does it truly comprehend your needs?
Check out today's AI in 5.
New giveaway coming soon….
🤷♂️ What’s Going On and Why It Matters:
We’ve helped tens of thousands of people learn ChatGPT.
And there’s one common question we always get.
What the heck is a token?
If you use ChatGPT, you probably deal with hallucinations all the time. After all, large language models lie and make stuff up.
And one of the most common causes of LLMs lying is running out of memory, or going past their token limits.
So, we decided to dork out a bit and answer that question about ‘what the heck is a token?’
To be honest, the best way to understand what a token is and what it does is to watch it live and get in on the discussion. But if you want the tl;dr version, we got you.
What’s a token?
Tokens are essentially how ChatGPT and others interpret all of the data we put in.
A token can be a word, parts of a word, a phrase or even a symbol.
How’s it work?
ChatGPT is essentially the world’s smartest autocomplete. But, it doesn’t actually work in words and phrases like we think. It uses these tokens to actually understand human language and have conversations. As an example, let’s look at this input:
You enter information.
The GPT technology then breaks it down into tokens.
In this example, you’ll see it uses context and a bit of a type of Natural Language Processing (NLP) to make sense of the words and context. (Notice, even the word “set” has different values because of the context here)
Then, GPT interprets this into unique token IDs, that helps it build context and ultimately have conversations that seem smart and human.
Still with us?
OK. So essentially, ChatGPT doesn’t actually communicate with us. It uses its big old neural network brain to understand (via tokens!) what the heck we’re saying so it can “talk” back. (Via token, of course)
Getting it now?
Great.
But the most important thing to remember here is memory! That’s what today’s show is all about. All of that back-and-forth communicating takes up ChatGPT’s memory.
And after it hits about 8,000 tokens (or roughly 6,400 words) it starts to forget.
You know. Lie. Make stuff up. Become nonsensical.
Alright, that was a bit dorky y’all.
Let’s give some practical examples and break this thang down 👇
🦾How You Can Leverage:
OK, so ChatGPT has a memory limit, measured in tokens.
All that back and forth, inputs and outputs, starts eating up what ChatGPT can retain.
And once you get past that token limit, ChatGPT starts to gradually lose its memory. And then it starts to lie, hallucinate, and just make ish up.
So, let’s talk about how to spot hallucinations, how to avoid it, and ways around using too many tokens.
Say it with me now…
1
2
3!!!!!
1 – Use Plugins for better memory 🔌
Here’s the real talk: plugins help you save your token count. Instead of copying and pasting long amounts of text, you can instead give ChatGPT access to the internet.
What’s the benefit? Crunching webpages, PDFs, etc. uses WAY fewer tokens than if you were to copy and paste that same information.
Try this:
We’ve covered this in-depth, so many times. ChatGPT with plugins is by far the most underutilized aspect of GenAI.
Side benefit of using plugins? Being able to access more information inside your chats without eating up as many tokens.
We’ve done quick tutorials on how to browse the web with ChatGPT, and even the best PDF ChatGPT plugins.
2 – Use a token counter 🪙
How do you know when ChatGPT starts to hit its memory limit? Aside from just anecdotally feeling like, ‘ChatGPT seems to be forgetting everything’ you can instead use a token counter.
We always recommend using Chrome while using ChatGPT, because there’s some great Chrome extensions (like token counters) that can help you get more outta ChatGPT.
Try this:
We’ve also already dished on how a token counter works and why you need to use one. You can go rewatch today’s show, and see in real-time how ChatGPT can at first remember information, then gradually forget it.
(Seriously, go watch this. It will instantly improve your LLM skills by seeing how ChatGPT can remember things then forget)
Also, go watch this AI in 5 where we show you how to use a token counter.
3 – Get your PPP on 🧑🏫️
And it’s BACK by popular demand! Our free Prime, Prompt, Polish course is actually your first (and best!) line of defense against ChatGPT hallucinations.
Hundreds of people from dozens of countries have upped their ChatGPT game with our free, live course. From Fortunate 100 directors to solopreneurs and students, PPP instantly improves your ChatGPT skills.
See what these smart pros said about the course! 👇
Try this:
Take our free course. It’s live, interactive and full of best-practice tips from a team that has used the GPT tech since 2020. You won’t find the registration anywhere on our website. Instead, just reply PPP to this message!
Now This …
Still haven’t replied to this email with PPP? Do it now!
Reply