Not Diamond

Name: Not Diamond
Rating: 3.0 (2 reviews)

The last chatbot you’ll ever need

3.0•2 reviews•

653 followers

The last chatbot you’ll ever need

3.0•2 reviews•

653 followers

Visit website

AI Coding Agents

•

AI Chatbots

•

AI Infrastructure Tools

Not Diamond isn’t like other chatbots you’ve used. Not Diamond automatically calls the best model for any prompt and improves in real-time based on your feedback, continuously learning your preferences. Not Diamond is the last chatbot you’ll ever need.

Free

Launch tags:Developer Tools•Artificial Intelligence•Bots

Launch Team / Built With

Topview Motion StudioGet a launch video for about $3, not thousands

Promoted

Lancey

Congrats on the launch! How does Not Diamond handle context retention across multiple interactions, especially when switching between different AI models?

Report

2yr ago

Not Diamond

Maker

Thanks @virajpatel ! We retain information across models in the way most LLM multi-turn interactions work (including ChatGPT)—by re-sending the entirety of the previous conversation to the LLM and asking it to generate the next response. So even as different models are used over the course of the conversation, each one will always receive the full conversational context.

Report

2yr ago

🎉 Congratulations! 🎉 Just out of curiosity, I was wondering about the ai-model-router. It seems to be a classifier that categorizes conversations based on their semantics and then forwards them to different specialized models for responses. I'm curious if using a small model in your own application to classify queries into limited categories before submitting the results to the corresponding specialized models would achieve similar effects. Let's set aside the potential delay caused by adding this extra layer of classification for now. Here's a prompt example for reference: ``` You are a professional assistant, and your task is to correctly understand user requests and classify them. You are only allowed to search within the given range to determine if a corresponding skill needs to be executed. If the skill is not within the given range, return your result directly; otherwise, provide the name of the required skill. Always follow the format I provide. ## Available Skills 1. email_writer: I can send email to given users. required email address and email content. 2. weather_forecast: I can search for the weather of a given location. Require location. 3. home_assistant: I can help query the sensor data or send control commands to your smart home system. require specific commands like: open the light in the kitchen. ## Response Format { skill: write_email, // email_writer, weather_forecast, home_assistant, NO confidence: 0~1, // give the confident score of this classification } ``` What do you think? Would this approach work? 🤔

Report

2yr ago

Not Diamond

Maker

@linjiejim that's a great question! The short answer is yes—people have been experimenting with using LLMs to handle classification and routing. However, some of the drawbacks with this approach include duplicating your cost and latency on every call, the evolving capabilities of LLMs being routed to, the evolving task domains and requirements of AI-powered applications (for example, there are many different types of emails one might write), and the simple fact that LLMs often struggle to classify and route accurately. We talked to many folks who explored this path and ended up abandoning it due to these reasons, and it's partly why we were motivated to develop a more precise and efficient solution to the problem. I encourage you to play around with LLMs-as-routers though and lmk what you think! We absolutely still have a lot of uncharted territory ahead of us.

Report

2yr ago

@tomashernandokofman Thank you for sharing your thoughts! At the moment, I haven't tried out detailed categorization within the same application scenario (e.g., handling work emails and personal emails with different AI models). More refined classification might indeed require the classifier to capture and understand subtle nuances. From my understanding, achieving classification accuracy with LLMs-Router currently requires some work in prompt engineering. I believe that if Not Diamond can continuously learn and fine-tune based on user feedback, it would be incredibly helpful (much like a constantly learning spam filter).

Report

2yr ago

Not Diamond

Maker

@linjiejim absolutely—if you're building an application that needs routing, please give it a try and lmk what you think. Also happy to jump on a call and walk through it together! My email is t5@notdiamond.ai.

Report

2yr ago

Congrats on the launch, Not Diamond team! 🚀 This is such an innovative and creative product. I absolutely love the name too - very clever and memorable. Wishing you all the success, keep killing it! 🏆

Report

2yr ago

Not Diamond

Maker

@ethan_miller5 thank you!

Report

2yr ago

Not Diamond

Maker

@ethan_miller5 thanks Ethan!

Report

2yr ago

The NOT Diamond chatbot AI offers a unique conversational experience that prioritizes user engagement with a blend of natural language understanding and context-aware responses. Its advanced algorithms enable seamless interactions, making it a versatile tool for customer support, personal assistance, and casual conversation. With continuous learning and updates, NOT Diamond chatbot AI stands out as an innovative solution in the realm of artificial intelligence-driven communication.

Report

2yr ago

Not Diamond

Maker

@juliujuly thank you!

Report

2yr ago

mysite.ai

Just looking for a chatbot also another tool falls into the list to test ;) Congratulations on the launch!

Report

2yr ago

Not Diamond

Maker

@patpijanowski awesome! lmk what you think : )

Report

2yr ago

looks interesting :) Good job guy and good luck!

Report

2yr ago

Not Diamond

Maker

@anna_hanusova tysm!

Report

2yr ago

Not Diamond

Maker

Thanks @anna_hanusova, I'd love to hear what you think!

Report

2yr ago

TalkTastic

Woot! This sounds cool. Congrats on the launch!

Report

2yr ago

Not Diamond

Maker

@mattmireles thanks Matt!

Report

2yr ago

Not Diamond

Maker

Thanks @mattmireles!

Report

2yr ago

•••

7 8 9

3.0

Based on 2 reviews

Review Not Diamond?

Reviews

Most Informative