ChatGPT/GPT-4 for WhatsApp, Instagram, Telegram and others…
AutoResponder is the easiest way to combine the state-of-the-art AI ChatGPT, GPT-3 or GPT-4 by OpenAI with WhatsApp, Telegram, Facebook Messenger, Instagram, Viber or Signal. You can have your chats answered automatically with an artificial intelligence that has been trained on most of the internet text and thus offers answers to any query you can imagine. As a chatbot, OpenAI's GPT can perform various tasks including replying to questions, generating text, and much more.
It is known for its flexibility and customization capabilities, allowing you to specify the tone, style, and formality of its replies. You can even tell ChatGPT / GPT-4 whose personality it should assume when replying (e.g. that of a cell phone salesman). Or you define what it should pay special attention to when answering. It's like your personal assistant. Look at the examples and be amazed.
AutoResponder also offers many configuration options, including AI replies to selected messages only and user-defined rules for others. You can get the app for free and without an account. What are you waiting for?
Always note: GPT can sometimes generate wrong information, harmful instructions, or biased content. Also, it has limited knowledge of anything that happened after 2021.
Follow these instructions to set up ChatGPT/GPT-4 and AutoResponder
1. Get AutoResponder. Check the how-to if needed.
2. Create an OpenAI API account.
3. Get your API key from here and copy it.
4. Create a new AutoResponder rule.
5. Tap the All-button at the top right corner if you want the AI to reply to any incoming messages. You can still limit replies to specific contacts. Otherwise, you can use the other Received message features of AutoResponder. Check the info buttons next to each option.
6. Make sure the Reply message field is blank. Then activate the Connect OpenAI's ChatGPT checkbox below.
7. The prompt is automatically filled in, based on which the AI will generate an answer later. You can always customize it to suit your needs. For example, add general information about your business that it should refer to when responding. Check here for how to design your prompt and combine it with the answer replacements of AutoResponder (previous messages, name, date, time etc.). But test with the ready-made text for now.
Note that chat models like gpt-3.5-turbo (which is the default now) or gpt-4 can use special prompt formatting. In AutoResponder please use 1:: before any text you want to send with user role and 2:: for assistant. Any text before the first 1:: or 2:: has the role system. However, you don't need to use 1:: or 2:: - then the prompt will be sent to the API as a user message. If you want to use another model like text-davinci--003, which is a text-completion model, you can keep the formatting to get similar results. There the prompt is always sent as a whole to OpenAI.
8. Now paste the API key you copied earlier below. The other parameters are already pre-filled. You don't have to change them, but you can see how it works here.
Change the model parameter to the version of GPT you want to use (e.g. gpt-4). Note that OpenAI may not have granted you access to specific models yet.
If you do not want the answers to be cut off at a certain length, increase the max_tokens value or tell ChatGPT that it should write shorter replies.
Reply prefix and Policy violation reply are custom fields of AutoResponder. For example, you can use the robot emoji 🤖 as an optional reply prefix to show your chat partner that the answer comes from an AI.
9. Save the rule. That's it! You can now test your ChatGPT / GPT-4 and messenger integration and impress your friends or clients 🎉
Tips and Tricks
1. If you are an advanced user, you could even train the AI using your own chat history. Please check GPT fine-tuning.
2. Improve the reliability of the AI by checking here.
3. If you are using the gpt-3.5-turbo model it may sometimes be better to append ChatGPT commands to the last user message to get more consistent results:
4. You can use AutoResponder's answer replacements to give the AI more useful information. For example, it can address the user by name if you are using %name% in the prompt. The same is also possible with the date and time.
5. OpenAI bills for used tokens (when registering you get free money to spend). See their pricing. Then you can check here how much tokens a specific text consists of. Note that all tokens of the prompt AND the reply are counted. To save reply tokens you can do several things:
Keep your prompt short (for example, by including less of your users' message history).
Use a less capable AI model instead of the default gpt-3.5-turbo (which results in answers that are not as good, but it can be useful for simpler tasks).
Reduce the max_tokens parameter (makes the answers shorter).
Only use ChatGPT replies for specific received messages.
Write a specific prompt for a specific rule without including the incoming message of the user.
Reduce the maxlength number of the AutoResponder answer replacements like %message_512%. The "512" can be changed to limit the number of characters.
Just create normal AutoResponder rules for messages you receive very often.
Be creative :)
With the default settings, you can send around 2000 AI messages per 1 USD. I think that's already a fair price considering how long it would take to write so many WhatsApp or other messenger messages manually.
You keep getting a similar response even though you have changed the prompt? GPT-4 also takes into account the reply history if used in the prompt. To fix the error, you can, for example, delete the reply history for this AutoResponder rule.
Your replies are cut off at a certain length? Increase the max_tokens parameter or tell the AI to write shorter answers.
If you receive the following error, this can have several causes.
Error: One of the parameters is invalid or OpenAI is currently unavailable.
Please test the ChatGPT feature first with the default settings as described in this guide and as they are pre-filled by AutoResponder. If it still doesn't work, please don't give up. At certain times during the initial hype phase, OpenAI may simply be flooded with requests and therefore unable to respond due to limited server capacity. So I recommend trying it again later. I think this will get better over time.
Otherwise, please check these steps:
Make sure your API key is valid.
Make sure you have enough free funds in your account or that a credit card is connected.
Make sure you didn't hit your maximum monthly spend (hard limit), otherwise increase it.
Your OpenAI account needs to be a member of an organization to use the API
All parameters need to be correct as described in the GPT documentation (e.g. the model name, temperature setting etc.)
Make sure the prompt+response combined doesn't exceed the supported 4096 token limit.
Check your internet connection.
When using a different model, please check if you have already access to that model. Some require you to sign up for a waitlist on OpenAI.