dthedavid

I work on a video editor. It exposes 100+ possible tools to LLMs. We use Jev to decide which subset of tools to send to the LLM. We also use Jev to classify a user's request, are they saying "Hello" or do they want some work done. I looked into OAI decision api, it's strongest advantage right now is multimodal but we don't need that yet. The makers of Jev just announced something similar.

Looks like they are clearing the backlog now. Wait time was 2 weeks. Not sure what it is now.

https://x.com/mxstbr/status/2108600018789634370

Wow 4 weeks. I'm shocked.

Looks promising. I'm building an AI video editor and multi tool calls take >30s using Gemini. This would be a a game changer if Jev can take that down to single digits at p95.

-> But how you get authentic and engaging for bank statement converter? People search for it to solve particular problem in the first place, not to hear your life story.

That's the hard part :)

You can stand out by being authentic. Your face on the video, etc. Even writing it yourself genuinely instead of using an LLM. ex the article felt authentic.

Hey, I'm building exactly this.

I ask it to add subtitles, text effects, color grade my clips, cut out the silent parts.

100% open source

https://github.com/DonkeyCut/Donkey

How does it work? Im building a video editor and right now it has access to nearly 100 tools. Would be good to learn the techniques you used to make tool discovery more efficient.

I'm building an open source video editor fulltime.

https://github.com/DonkeyUseCorp/Donkey

Currently doing this bootstrapped. I'm getting a lot of feedback from free users and barely any from those who pay. Quite interesting.

Appreciate the candid feedback. I'm working on this every day. What bugs did you run into? Trying to make AI video editing best in class.

donkeyuse.com it’s also open sourced

I feel the same way too. I also open sourced a video editor. It's free to use and you can buy credits whenever you want to access AI specific features.

Nice project. I’m building a similar project. It’s open source too.

https://github.com/DonkeyUseCorp/Donkey

It’s mostly a web app with a native swift companion app to access local resources like TTS, file storage and video rendering.

I arrived at the same conclusion as you; every app should have AI chat. Just give it full access to the app like a real user. I found that users prefer talking to the AI when editing vs clicking around.

I can't believe iMovie doesn't have text overlays so I'm building a replacement at cut.donkeyuse.com

It's opensource and more modern.

I'm a SWE and still a SWE. Just moved from HCOL to LCOL and am working for myself.

If you can afford it, I highly recommend quitting and going independent at least for a while. It’s so much fun building right now.

Auto makers have always been bad at software. They just don’t care. Tesla is an exception.

Great work. Did you consider buying instead of building? I’ve worked at organizations that built similar systems, but what was often lacking was developer experience, observability, and scalability, basically everything outside of core functionality; essentially the stuff that you're trying to tack on as you improve your system.

Now that I'm building on my own, I’ve thought about building as well, but I’ve found that off-the-shelf systems handle all of this far better (and they are opensourced too), ie trigger-dot-dev and many others.

We will be able to help sellers find buyers faster. This improves selling efficiency, therefore helps grows world GDP.

Submitted.

I'm building a copilot for salespeople on LinkedIn (heysalesman.com). I'm using the product to sell the product.

Looking forward to the feedback.

In university I noticed that some of my classmates just sat there and didn't take notes. So I stopped as well. I sat there, listened and then took pictures of the blackboard. This method worked better for me and I noticed that I performed better. The lesson here is that people learn in different ways.

Cool. I'm building something like this on the side. It's called bannerbox.io. The difference is that it requires no code, has a WYSIWYG editor and works everywhere.

I share the same dream; of one day charting my own path. I've been doing things a bit differently. I've kept my job and am building my product (www.bannerbox.io) on the side. I wake up early and dedicate a few hours to it in the morning. So far I've built the MVP but have no users. I'm fine with this because I'm learning.

Last year I've dedicated 100% of my time to building. This year I'm spending half of my time marketing. I'm struggling with this new arrangement. Marketing makes me uncomfortable. I haven't made meaningful progress on marketing yet but it's the right move as long I am consistent.

Bannerbox: https://bannerbox.io

Embed banners and modals onto your site with no code.

I spent the last 7 years as a growth engineer building banners and modals. Each time there was a custom requirement. I've always thought there should be a Wix kind of experience for tiny components that can be embedded anywhere on a site.

Currently I have 0 users. This year I plan on spending more time on marketing and improving the product. It cost me about $50/month to run. Most is for storage (postgres and redis). A large chunk is for a custom email address through Google. I spend about 1-2 hours working on it every day. I'm thinking long term. Slow and steady.

I'm in the same boat. Been working on www.bannerbox.io for 2 years, no customers, no revenue. Marketing is important to the success of any project. This year I plan on focusing at least 50% of my time creating content; mostly blog posts and sharing my journey so far. With persistence any idea should work out.

What is your business? I'm starting out now at $0 profits. Hope to change that this year.

I've spend many years in Growth engineering. We often get asked to build this banner or that modal. I've always felt there should be a Wix kind of experience, but for smaller components. I didn't find one so I decided to build it.(bannerbox.io).

Bannerbox is targeted at existing site owners, specifically non-technical people (i.e. Marketing).

I do all of the design and coding myself (both backend and frontend in Typescript). I've been building this on the side and it's been a slog. I'm nearing feature complete and aim to start marketing the product this year.

It's currently costing me ~$50/month in hosting fees and generating 0 in revenue.

What alternative approaches did you try?

Would loading a placeholder image for the map and transitioning it in when ready help?