Hello @mstephens_42 have you checked out this skill:

https://synthiam.com/Support/Skills/Artificial-Intelligence/OpenAI-Chatbot?id=20207

Funny enough it's the first suggestion from the Synthiam help bot.

Jeremie, I should have been clearer.  Yes I have used this one that is based on GPT-3.  ChatGPT is a significant step up over the ai chatbot that is in ARC as it stands now.

There's some confusion about what Chat GPT is - and how you can use it. Here's an example.

It is a chat with gpt. So you can chat with it. It's an interface that talks to the Open AI GPT product. So, chat gpt is chatting with the gpt. Does that make sense? Because that already exists with the Open AI robot skill. So by using the robot skill, Jeremie presented, chatting with gpt. That's the same thing, except presented as a robot skill vs a website

If you want to use Open AI's chat gpt website, you'd need to visit the chat gpt website, and you can type (chat) with the gpt. But you can't incorporate that into a robot because it's a website. If you want to use the gpt in a robot, you would add the Open AI robot skill. They both "chat" with the GPT product.

Oh, I should also add some more info that I think might be relevant. The GPT product is trained with data from the internet. That means the response or information you receive during the chat comes from previous conversations on the internet through forums. There is no reliability or accuracy regarding the response. The answers are not facts; if anything, they're majority opinions based on the popular redundancy of previous internet conversations.

You'll get some pretty unfactual responses if you ask the chat gpt for information about building a robot with synthiam arc. I was asking about using a camera with synthiam arc, and it was telling me to connect the camera's ribbon cable to the raspberry pi. shrug

So I guess talking to GPT is about as accurate as talking to your neighbor - or anyone you come across during the day. You'll get an opinion based on what is heard most. That's how GPT works - it'll tell you what it heard most on the internet (so to speak)

DJ, I think I got it.  I have installed and operated the AI Chatbot in synthiam using the very process described. It just feels so different than ChatGPT in its responses.  Also, mine talks as slow as Elmer Fudd. Any idea how to speed up the readback response?

What do you mean by "talks slow"? As in, the speech is spoken slowly?

I can say that the Chat GPT web UI uses a significantly large response size, so that's why it is so lengthy. But that would be costly to implement on a robot because the web UI is accessible, and you'd have to pay for your own application. Also, I'm not sure if you want the robot to have lengthy responses to everything.

I had read where some articles try to say the Chat GPT uses a model that has been massaged slightly for conversation. I'm not sure if that's true, but if it is, I guess there could be an advantage to creating our gpt models. We have discussed having a gpt model built around the forum and support section content of synthiam.com. It would be interesting because you'd be able to "talk to the website," I'm not sure what it entails, but it has piqued my interest.

DJ, Yes it talks very slowly.  I am wondering if that is a setting on my laptop or maybe Bing Speech? I’ll try to record it and let you hear the cadence of the speech.

W/respect to GPT, I hope you’ll look at it further. I’m quite taken back by it!

You'll want to change the speech synthesis settings: https://synthiam.com/Support/Skills/Audio/Speech-Synthesis-Settings?id=16054

Hello DJ, I am back to pro status to try this skill out. I am having problems with this skill as it is not representive of Chat GPT 3 or 4 for that matter. The interactions are not similar. For instance I can tell Chat GPT to change its name and I cannot with this. The complexity of the answers are nowhere close. Am I missing something or have I misapplied the skill? Thanks!

When I asked the same question you did here is the answer I received

Human: i would like to build a robot with synthiam arc AI: Thank you for considering building a robot with Synthiam ARC. This software is designed to be user-friendly and easy to use, so you can create the robot of your dreams.

How did you get the response you did?

Edit the personality, perry. You have to tell jt what you want it to do.

chat gpt ui has their own personality description as well. Remember, chat gpt is just a web interface for gpt with a descriptor

Here’s a quick vid I made that shows how to change the personality

or you can be as vague as you want like the chat gpt ui does

Thanks for the response as always DJ! I will give it another try and see if I can do better.

Daisy was an interesting choice.  IBM 7094 in 1961 programmed by John Kelly.

DJ thanks for posting the video!

I have been checking this out and when I ask the AI what year it is it response with ""2021".  When I ask it what day it is I get "Today is Wednesday August 8, 2017".   Is this normal to be so wrong?

I was hope it would be more like Alexa and I least no what day it was.

A.I. current events were cut off after 2021 but I noticed if you phrase your question a different way it can give you exact time and date  if you give your location. I dont fully understand how it starts to work but does if you ask 2 or 3 times in different ways,very odd.

OK,  Chat GBT on the OpenAI's website does not have any issues.  Is anyone working on a new skill to support GPT4?

We are working on it. Well, it is done - but we're dealing with some complications from a few customers who had issues with the existing openAI skll because the information caused incorrect responses for an educational institution and a student's study exercise - as well as some racist/sexist slander. We're evaluating how we can deal with redistributing this technology without the Synthiam platform being accountable.

Yes I think I noticed a bug with regular chatgpt. Mostly it will be polite but if you were experimenting with some of the jail breaked A.I. personalities,(rude,swearing) they can bleed into the polite A.I. if you use your same email from the jailbreaked A.I. personality. It saves your previous conversations even if you were on a cell phone ,then added same account to your laptop. Although, you would need to click on the saved conversation in history, to get it acting rude again, but I found out it sure did! I Really enjoy it, hope they don't fix it:D

Synthiam provides the tools and an appropriate disclaimer.  You can’t be held accountable for what people do with the tools. I am sure lots of kids open up Blockly and select sayEZB every swear word they know;

I am also sure a lot of kids have discovered how to make GPT3 say things that are not appropriate (DAN prompts).

Someone could obviously host a 3rd party plugin site you can load into ARC but I am not sure that is the right solution.  It is parents job to parent kids not software companies. Chat GPT isn’t going to say anything kids haven’t already heard in the playground.

DJ, can I become one of your GPT4 testers I promise not to hold your company responsible for anything it says!!!

Nink I used a similar example in our meeting about this - that syntbiam delivers the technology and people are responsible to use it in a respectable manner. I mean, Walmart sells kitchen knives but you don’t see ppl running through the parking lot stabbing each other with them.

I think the issue we’re experiencing is the spotlight that open ai is receiving. All the media claims it is brilliant and provides factual information and replaces humans. But that is not the case at all. While other robot skills can have the odd fault without being noticed, open ai gets the attention.

Anyway I’m pushing for this and we’re adding a disclaimer agreement. We needed something that can protect us in the classroom and the agreement can be simple enough for children to understand - because that’s where the complications arise.

so yeah, we’re gonna release it on Friday or Saturday I think.

Wow that is GREAT NEWS DJ!!!!

Hey that is great news DJ, way to go! Looking forward to that!

I did ask chatgpt to write me a ping script for ultrasonic distance in Javascript to be copied into synthiam ARC and some of it looks correct but not sure if all of it would work.. As an AI language model, I am not able to write code directly in any specific platform or language. However, I can provide you with an example code snippet in JavaScript for an ultrasonic ping sensor to detect objects that you can use or adapt for your  function detectObject() { // send a pulse to the ping sensor digitalWrite(pingPin, LOW); delayMicroseconds(2); digitalWrite(pingPin, HIGH); delayMicroseconds(10); digitalWrite(pingPin, LOW);

// calculate the time it takes for the echo signal to return const duration = pulseIn(echoPin, HIGH);

// convert the duration to distance in centimeters const distance = duration / 58.2;

// check if an object is detected within the threshold distance if (distance < distanceThreshold) { // do something when an object is detected console.log('Object detected at distance:', distance, 'cm'); } } So I can see why some schools could complain if it is wrong format of code.(last time I used this kind of coding was EZSCRIPT Back in 2017.)

Is GPT3 more lifelike than GPT4? I guess we are about to find out.

https://interestingengineering.com/innovation/most-advanced-humanoid-robot-ameca

Wow she seemed so life like! They probably need to tweek the gpt4 as it just came out ,to make faster. Same thing happens when a new video card comes out for PC ,very slow first couple of months but then driver updates bring out the true fast processing power.

I think they need a new video card (banks of Nvidia GPUs).  They run GPT4 on the same Nvidia GPU’s they ran GPT3 on. They have now hit  memory and processing walls. They probably need to remove their dependence on CUDA and Nvidia and switch to an open platform. PyTorch 2.0 removes the Nvidia stranglehold and allows a range of hardware to be used so we are not dependant on raw GPU FLOPs and can now support the machine learning models across a variety of TPUs GPUs CPUs and ASICs.

Wow, it is on all the main news channels, every news network is reporting on chatgp3 and 4 like every 2 hours some reporter talking about it. FOX News even just reported 5 minutes ago how the U.S. needs to take the lead on this tech before China gets too far ahead and owns it forever. I mean as if ww3 is not important, they concentrate on A.I. CHAT as more important HA ha! I really need to be more sensitive with my comments as most of my cool electronic stuff all comes from Asia!

It's great to hear that you've been exploring the capabilities of ChatGPT and finding it impressive compared to previous chatbot AI engines. Integrating ChatGPT into ARC/Synthiam environment can indeed open up possibilities for creating more sentient-like robot applications. As for a plug-in specifically for ChatGPT, I'm not aware of any ongoing development, but the AI space is constantly evolving, so it's possible that someone might be working on it.

@contact:gptnederlands.nl

ChatGPT works well, different responses.

thanks

I'm glad to hear that you're finding ChatGPT to be effective and that it's providing varied responses. If you have any questions or need further assistance with your EZ-B v4 robot or any Synthiam ARC skills, feel free to ask. Enjoy your robot building and programming!