Show HN: XP1 – A GPT-based Assistant with access to the browser Tabs
xp1.dust.ttXP1 is an assistant based on GPT with access to your browser tabs content. It is geared (prompted) towards productivity and can be used to help you with your daily tasks (answering emails, summarizing, extracting structured data from unstructured text, ...) UX-wise, IMO This is the right way to do it. I believe we will see entire new browsers centred around this type of ideas. However, it is still the early days and I would have personally gone for a longer-term vision, with - a more Freemium-oriented pricing to grow the userbase. - a more openly extensible approach : If you don't want to open source the app, you could at least open-source an interfacing part through which people can augment the usages with custom scripts of their own. Completely agreed! I believe I’ll open source the app in the coming days. This is before anything else an exploration at this stage. I see you already open-sourced dust. I love this one too. So is it dust like "des grains de poussière qu'on assemble ?" ;-) Anyway, you chose the most direct "Data flow Programming" approach. It is neat and works at a flexible level. However, one of the amazing things about ChatGTP is its ability to remember and respond to incremental "conversational" prompts in a smooth way. How to integrate this kind of manual feedback-like "flow" within that other more rigid automatic "dataflow" of dust is something to think about, I guess. It is not just "time for AI-native products!" [1], it is now time for "AI-prompts-native products", and yours are more like platforms than products. This is what I like about them. A lot of coming pseudo-apps are going to be really just simple prompts in disguise [2]. So open platforms are the way to go. [2] Example from HN today : https://news.ycombinator.com/item?id=33975805 Dust XP1 runs on a Dust app. You just need a "history" input parameter that gets injected at the right place. Does that make sense? It does. The real value will accrue as the assistant become more personalised as users use it. This is exactly what I've been hoping for after a week of pairing with chatGPT. The LLM is a powerful source of recommendations, but too much gets lost in translation between browsing/context and the chat UX. Excited to try this! Some additional context here if interested: https://twitter.com/spolu/status/1602692992191676416 So does this use one of OpenAI's models?