@misska1704
2
Events attended
2
Submissions made
Looking for experience!
๐ค Top Collaborators
๐ค Latest Submissions
CotChat
CotChat is a community chatbot that determines its conversational behaviour through REACT method based on ChatGPT and LangChain. Unlike ordinary chatbots, CotChat uses the approach proposed by React. When receiving messages, it automatically infers the appropriate action through observation-interest evaluation-reflection-action. We have defined three types of behaviours: Direct reply: Reply directly to the current message, Relate reply: Related to memory vectors and Silent: Feel this message is irrelevant and feel uninterested. In this example, we collaborated with artist Nick to create a chatbot based on his character LuckyCot. This character is a cat named Modem Cot that mutated from a network mediator modem and has a network cable tail. It is interested in blockchain-related content. [ๅพ็] [ๅพ็] The thinking process (steps) of this bot can be summarized as follows: 1. Observe: Understand what is being discussed in the current conversation. 2. Evaluate: Rate the interest and relevance of the message on a scale of 1 to 10, where 1 is not interested or related, and 10 is extremely interested and related. This is a reference value for agent's decision. 3. Reflect: Identify any associated emotions, relevant memories or users, and determine if the bot is interested or related (evaluation score greater than 7). 4. Action: Choose one of the predefined actions (Direct reply, Silent, or Relate reply) based on the observation, evaluation, and reflection. In summary, we have applied the Observe-reasoning-action approach proposed in React to community chatbots. Currently, this application is displayed through WeChat. We hope that in the future, Autonomous Agents can truly become members of human society.
30 Apr 2023
Paintpal
We use AI to facilitate industrial design and modeling images. You can - generate designs based on descriptions and existing collections. - try new designs in real-world pictures. For example, you can use the model to - generate streamlined, leather material body e-cigarette design based on the <200 images collection> - try <helmet-design> on 6-month kids playing on grass. Overall Impression - Users can provide a collection of reference images - Users can use simple words to *generate* and *modify* images - The userโs product can be displayed in different scenarios We also provided demo with real users from industrial designer in e-cigarette who needs to demo to their customers with new designs. Helped kid's helment manufacture who needs to create non-real human images in order to pass regulations regarding advertisement privacy. They both benefites from our product by reducing image generation time, and increasing variaty.
21 Apr 2023
