I've had this on my side project todo list for a while but was waiting until image editing models got good enough to make something that really works.

Here's the link: https://fitpic.app

At first I just wanted to spend a couple of days having fun building a basic demo but I was so impressed with the results that I decided to spend another week making this into a real product.

It's all powered by Google's new Nano Banana/Gemini Flash Image 2.5 model, with the catalog powered by https://trychannel3.com/ (recently on HN) and Google image search.

It does require signup to use once for free and then credit purchases (I would like to have it be usable without signup but the model is not cheap and I don't want to bankrupt myself by opening it up to abuse).

I did throw a quick page together with some examples here though: https://fitpic.app/examples

I know HN is very well-dressed and style-conscious so I hope someone here finds it interesting or useful.

Comments URL: https://news.ycombinator.com/item?id=45209422

Points: 1

# Comments: 0

[1] - https://browsable.app

Notably not an AI agent like Operator, Manus, etc. which are largely unreliable for the time being. Instead this uses AI to turn your task into something repeatable and configurable.

Currently focusing on scraping use cases but hope to make it more powerful soon so it can actually do complex tasks rather than just extracting data.

It's RPA for browsers which is not fundamentally new, what I'm trying to do that is new is use AI to make it as easy as possible to create automations. Most of the existing tools require you to locate CSS selectors, XPaths, etc. whereas this is just point, click, type, describe data you want to extract in English, etc.

Still early days and it works much better for some tasks/websites than others but it's improving rapidly and I'm quite excited about it.

Also hoping that the likes of OpenAI Operator, etc. are rolled out in a way that I can use them to build a better product rather than being runover by them.

As someone who supports Brexit, I always thought there would be greater costs in the short term but getting out of institutional structure of the EU would be beneficial long term, as long as we take advantage of the institutional freedom and try to get onto a different path as a country (investing heavily in science and technology, having a more rational approach to regulation, having an immigration system that attracts great talent while also controlling the borders and thus making the whole thing less toxic).

I haven't overall changed my view as the EU still seems to be on a very bad path as I see it, I can't say I'm hugely optimistic about the UK either though. There are glimmers of hope like the new ARIA institution for blue sky science, but the main political parties are a pretty depressing spectacle.

I'm excited to build something for the new Stripe Apps marketplace and landed on the idea of a tool to query your Stripe data using natural language instead of SQL (e.g. asking "How many customers are on annual subscriptions?" rather than writing a SQL query). Seems like it could be useful for users who don't know how to code in particular.

This isn't a Show HN as I'm at the discovery stage here so I just thought I'd ask here if people would envision this being useful in their companies.

Quick landing page here: https://cashquery-marketing-site.vercel.app/

Comments URL: https://news.ycombinator.com/item?id=31539333

Points: 1

# Comments: 0

For searching documentation there's a lot to be desired too so I'll make a shameless plug for my side project: https://neat.wiki. It's a simple wiki creator on top of Google Drive but I'm layering on some GPT-3 goodness for semantic search and question answering so you can always find what you're looking for.

Yes the current public version of Pygma is no good - I've just been heads down trying to get the complete version working and haven't really been attending to the current plugin.

Anyone reading this whose looking for the holy grail solution of Figma to code that's written like a developer wrote it, I'm working on this (should be ready soon!) and would love to talk to you - please email me on emile@pygma.app (note that the current public version isn't very good and suffers from the same problems as all the others).

I've built a tool to quickly create wikis from Google Drive folders that makes it easy to find files fast. It's similar to creating a wiki with Google Sites, but it looks nicer and the search is faster and more accurate. You can easily publish public wikis to a custom domain too.

Here's the link: https://neat.wiki

Hope it's useful, any feedback is much appreciated.

Comments URL: https://news.ycombinator.com/item?id=29240933

Points: 8

# Comments: 2