https://replays.lol/clipper - A spin off from my main startup's product that lets Twitch streamers review their viewers' league of legend clips. Zero friction as we handle the recording of clips ourselves using bots that load up people's previous games using the League of Legends game client. Went live with my first medium-size streamer yesterday, excited to see how this goes!

Similar to Cameo but hyper specialised for league of legend streamers, if this shows some traction we'll expand to other games, and then to other industries (think a tennis star reviews one of your tennis points, beats out a generic happy birthday message?)

I'm building a Twitch streamer focused version of cameo. The first beta version is specifically for League of Legend streamers.

https://demo.replays.lol/clipper (recording the demo video today).

The idea is that a generic video message doesn't appeal to a fan of a video game streamer, instead what really would be cool would be watching them react to your best moment in a game.

Our software removes all friction from the journey, the fan doesn't even need to record their own gameplay, we have bots set up that can load up someone else's gameplay just from their username, record their highlight for them, upload it to our platform, then the streamer just needs to come in, watch a ~60 sec clip, give a genuine reaction, press 'submit' and its all done.

There's a few markets I'm trying to find product market fit in: ~1-2 minute coaching sessions, sports commentator style commentary over your clip from influencers, hyped up reactions from your favorite streamer, a community-focused segment on a stream of watching a compilation of your fan's best moments.

We're ready to launch, just trying and struggling to find the first few people to sign up.

Their proprietary models are very good too and go under the radar, they never seem to appear on any benchmarks. Qwen3-coder-plus is significantly better than their open source qwen3, Qwen3 max also rivals the SOTA models

Are these actually different models vs just different names from the open weights releases?

They generally match, except I don't think the Max ones have releases

$50 per month is their SaaS solution that let's you make 1000 requests per day. The openrouter cost is the raw API cost if you try to use qwen3-coder via the pay as you go model when using Cline

https://inspo.dev - The idea is a chrome extension that let's you iterate ridiculously fast on frontend web components - click one button, select the element like you're using Chrome's inspect dev tools, press generate, and 60 seconds later, AI has given you ~7-10 new variations on how you could style that component, with the code ready to implement.

Struggling to get the generated iterations to be up to a standard I'm happy with at the moment, but improving every day!

I think a animation or video at the top of the homepage would do wonders for understanding what your extension does.

Hey Charles, annoyed I missed out on the first batch, signed up to the newsletter looking forward to the next one!

I thought your product page could use a slightly nicer UI. - I'm building an app that let's people spin up multiple variations of their pages and easily implement new UIs. - I like to put HN websites through it whilst I'm training it up to see if I can improve them.

here's what my app came up with for your site: https://streamable.com/vbby9q

If you want the html + css, it's here free of charge, I've split each one up with a ## Variation 1/2.. etc.. just let me know what you think - https://pastebin.com/WGNieVmq

I looked at your video of alternatives and number 5 looked pretty good to me. Though, a better image of the product itself seems like the lowest hanging fruit for improving the landing. :)

For stuff like this, it would be cool if you had a hosted demo of what you clicked through in the video.

A share button is a great idea, thanks!

I think there's a big difference with how designers and programmers can use AI to enhance their work, and how exploited the average person's work has been. A lot of designers publish their work on social media, or it's visible on their websites etc., which AI models have used to train with. But with coding, most people's code only exists in private repos, or is compiled to a format that LLMs cant easily be trained on.

There is so much code on github and all the other repos that it can compare with the amount of art that is out there. Also all of your Javascript code is public once your site is published.

There is nothing stopping artists from using A.I. to improve their work. The sketch to image work flows are great, the variation work flows can save from the tedium and inpainting can help fix and improve images.

Text to image is lazy and is the cause of most of the slop but no one is saying artist should replace their Wacom tablets with text prompts. I feel like there is a lot of hurt egos going on. I remember back in the day on CGtalk, there was so much elitism and in hindsight it probably held a lot of people back, myself included.

Yes, but Warren Buffer doesn't live in El Salvador, so the only thing he could do with BTC is sell it to someone for USD so the point still stands

My stack relies on Typescript Express apps on Google App Engine. One for the API, and one for the front end.

For database I use Datastore and for storage I use Cloud Storage.

Front end uses an express app that routes the marketing pages to static html pages and then routes everything starting /app to a generic html file that uses React to render everything / sort out routing.

It's quite interesting that a successful HN launch effectively created ~$10m worth of value, as tooljet was able to raise $1.5m+ within a couple of weeks whereas fund raising efforts before were rejected.