Suggest New Features 💡

Fable is back and it would be great to have it on You.com as soon as possible

Dear You.com Team, I am writing to provide detailed feedback regarding my recent experience with the You.com app, specifically relating to the expectations set by your advertising and the actual capabilities presented during use. --- ### 1. Expectation vs. Reality: Image and Media Generation Your advertisements strongly suggest that the You.com Smart Assistant can generate images and videos directly within the app. As a user, this led me to believe I could receive instant, AI-generated media outputs (such as logos, pictures, or videos) directly from the assistant in the chat. However, during actual use, I discovered that the Smart Assistant is limited to text-based responses and cannot create or display images or videos directly. This discrepancy between advertising and functionality caused significant frustration and a sense of being misled. Such a gap affects user trust and may discourage continued use. --- ### 2. Impact on User Trust and Retention Frustration and Disappointment: When expectations raised by promotional material are not met, it leads to an immediate negative emotional response. Perceived Lack of Transparency: Users may feel that the advertising is deceptive or exaggerated, which diminishes trust. Risk of Uninstalling: As in my case, this frustration can lead to users uninstalling the app prematurely, losing potential long-term engagement. --- ### 3. Suggestions for Improvement Clear Communication: Ensure that ads and promotional content clearly specify the current capabilities of the Smart Assistant, emphasizing the text-first nature of this interface. Integration of Media Generation: If possible, incorporate direct image and video generation features into the Smart Assistant experience or clearly direct users to linked AI tools that provide those services. User Education: Provide onboarding or help sections that explain what the assistant can and cannot do, managing expectations upfront. Feedback Channels: Actively encourage users to report confusion or dissatisfaction so that the team can adapt communications and features accordingly. --- ### 4. Closing Thoughts Innovation and AI-driven assistance hold incredible potential, and You.com is positioned well to offer a cutting-edge experience. However, aligning marketing messages with actual app functionalities is critical to building and maintaining user trust. Thank you for considering this feedback. I hope it contributes to making You.com an even better platform for all users .

This happens with Opus models. Haven’t tried all.

Prompt: "I am a Channel Manager with Mimecast and am taking care of the partner Bechtle in the DACH region and Germany in particular. As I would like to build an agent to support me with my work with <removed>, I would like your to research a comprehensive list of publicly available resources (URLs) which I could add to the prompt of my future agent."

Insanely cheap, powerful model that is on OpenRouter already.

Can't download YouTube videos into my gallery

Try following these examples:

I would like to request the integration of two-factor authentication in You.com to improve the security and privacy of user accounts. Two-factor authentication is an additional security measure that requires users to provide two forms of identity before accessing their accounts. This could include a password and a code generated by a third-party authentication application, such as Google Authenticator, Authy, or the Microsoft authentication application. Implementing two-factor authentication in You.com would be an effective way to improve the privacy and security of user accounts, which in turn could improve the platform's prestige. Therefore, I would like to request that you consider integrating two-factor authentication into You.com . This improvement would provide an additional layer of security for users and greater trust in the platform. I appreciate your attention and I hope you will consider this request to improve the platform. Sincerely, [Your name]

The key parameters users would like to be able to configure are: 1) Temperature: Adjusting the temperature would allow users to control the "creativity" and randomness of the agent's responses, from more deterministic and logical (low temperature) to more varied and exploratory (high temperature). 2) Top P: For OpenAI models, the ability to set the Top P (nucleus sampling) parameter would give users control over the diversity of tokens the model considers, from a broader (high Top P) to a more focused (low Top P) distribution. 3) Frequency Penalty and Presence Penalty: Similarly for OpenAI models, allowing users to adjust the frequency and presence penalties would enable them to encourage or discourage the model from repeating certain words or phrases, or introducing new ones. 4) Response Mode: For Anthropic models, users would like the option to choose between "Full Responses" (more verbose, with explanations) or "Concise" mode (shorter, more direct responses). Providing these customization options would give greater control over the agent's personality and outputs. This level of configurability would significantly improve the flexibility and utility of Custom Agents.

It would be awesome if premium users could access the new GPT-4o image generation model for editing images once the API is available.