jarodxu

The tool behind the game: https://proto.trickle.so/

I'm really happy you picked up on that feature! Combining different tools to get work done is exactly what we're aiming for.

To make a possibly imperfect analogy, Trickle is like a Jupyter notebook designed specifically for LLMs, but without the need to write any code.

Thanks for the feedback! It’s not just a wrapper around an LLM—Trickle lets users integrate different tools into a workflow, all through a document-like interface. You can build multi-step processes that can be reused or shared as apps. While ChatGPT acts more like an chat assistant, Trickle helps you create structured workflows, making it more powerful and flexible for personalized tasks. And best of all, it’s as simple as writing a document!

I think I’ll start by removing the non-English demo links from the landing page, and later, when we have multilingual versions, we’ll link the corresponding demos.

As for the second issue, We’ll remove unnecessary userInfo. Also, although these demos allow users to duplicate the internal blocks and prompts of the agents, we’ll implement some optimizations on the API next week to prevent unnecessary exposure.

It’s great to have you take a look and provide this feedback!

Thanks for the reminder! I actually posted a 'Show HN' a few days ago specifically introducing the product, but for some reason, it didn’t appear in the show list. Anyway, today I just wanted to focus on discussing the landing page. I’ve added the 'Ask HN' prefix—do you think that makes it better?

Let me see what I can do to optimize it. Thanks for the heads-up, I’ve added the 'Ask HN' prefix.

Hey HN,

We're not promoting anything, just looking for feedback to improve our landing page after a recent big update. We’ve shifted from being a screenshot tool to an AI agent creation platform (long story, happy to share more in the comments if you're curious!).

I’d really appreciate your thoughts on the clarity of the text, the UI/UX, the illustrations, and any other details. Most importantly, can you tell what the tool is for just by looking at the landing page?

If you're interested in exploring the tool itself, I’d love to hear your feedback on that too. All suggestions—positive or critical—are very welcome!

Thanks in advance for your time and help!

Been working on something cool—imagine building powerful AI agents just by writing it out in a doc. No code, just ideas.

Excited to share this with the HN community! Would love any feedback. You can use the free plan credits to try building your own agent.

Thanks for your feedback :)

Absolutely! We'll keep you posted once a local-only option is available. Thanks for your interest!

By the way, are you more excited for the iPhone app or the Mac client?

While it might seem like we're on a similar tech trajectory as Rewind, we're actually diving into totally different use cases. Rewind is all about enhancing memory. This means when it's recording automatically, users don't really know which parts will be valuable until they think back and search later on.

Trickle, on the other hand, is all about helping users manage those fragmented bits of info via screenshots. So when someone takes a screenshot, it's because they know there's a chance they'll need it somewhere down the line. Hope that clears things up!

If your screenshots have any NSFW or NSFWL content, we'd suggest giving them a quick check before uploading. Our platform's main goal is to help you manage and search your screenshots better, but we won't review or differentiate the content in user uploads.

In fact, we've built a wealth of application-layer features based on OpenAI's API, many of which I believe OpenAI wouldn't necessarily pursue:

- A screenshot library supporting fast search.

- Ask AI optimized for screenshot contexts.

- A Mac screenshot client tool.

- Our upcoming Mac and iPhone apps, which will likely allow screenshots to be stored on the devices.

- Integrations: for instance, auto-syncing your screenshots and generated digests to Notion; or uploading screenshots from Discord without even having to open Trickle, among others.

- Leveraging the screenshot library to deliver more value, such as collating user feedback screenshots and periodically generating user insights from them.

We're eagerly looking forward to GPT-4's image understanding capabilities being released so we can offer our users an even more imaginative experience.

In our current web app, users' screenshots are stored on AWS cloud. Only the essential information processed from these screenshots is sent to the OpenAI API. According to OpenAI API's public commitment, this data will not be used for any training purposes.

For our upcoming Mac client and iPhone app, we're considering storing the screenshots on the device. However, we still need to weigh the pros and cons of cross-device syncing versus local storage. Your feedback is invaluable in guiding our final decisions for the Mac client and iPhone app. Thanks for sharing :)

Thanks for the support!

We only used the standard GPT-4 API (without visual capabilities).

I think it's okay to have a some discussion here. We employed traditional OCR, GPT-4, and some of our own algorithms to assist GPT-4 in understanding the context and relationship within the image scene (allow me to retain a bit of mystery here).