We have 2 Frame TVs. It's a great product if you aren't someone who obsesses over picture quality and have the budget.

I'd love a clean UI to accompany the minimalistic design of the TV itself...but this looks a bit early for me to try :).

I built this for my own private use but it’s since become public.

Free to use, no accounts, no subscriptions.

https://trysojourn.app

I was using Claude to bounce ideas for parenting with a focus on biblical principals. Trying to really understand how to discipline my children without provoking them, for example.

I was pleased with the experience but Claude did not make it easy for me to dive deeper into scripture. I wanted a different LLM chatbot experience that was focused on less chatting and more scripture reading.

I TestFlighted it out and friends liked it so I ended up publishing it.

does it exist as a webapp?

Not yet, unfortunately. Nor Android, which people have asked for.

I think Android would be supported first but no specific timeline for it yet.

Exposing yourself to great taste educates AND inspires. I love Peters Design Company and how amazing they are at identity branding.

Here's an example of rebranding Uhaul. https://www.youtube.com/shorts/cMU0G8h0pys

The problem with a "software factory" as a dev is that it leads to infinite dev work. Build project A and struggle to get users, start project B.

The author is saying, build project A and stick with it. This isn't new to the "AI era" but it's more pertinent.

Thanks for clarifying. I can stand behind that, it’s a solid argument.

I even think that most ideas no matter how dumb they sound in the present could become profitable businesses in the future. Survival is key here. Basically outlast your naysayers until an opportunity appears and then grab it with both hands. You’ll automatically have the first mover advantage.

The most famous example I can think of is Nvidia!

I think many of us have already started automating it so that they update alongside code changes.

I used their API for several years for a project to get reverse geocoding to turn city names into lat/lon pairs and vice versa.

Like Mapbox, I assume they have a profitable business selling their mapping services to other companies.

Can this work against a cheaper cloud LLM like Deepseek? https://api-docs.deepseek.com/quick_start/agent_integrations...

Screencast looks great btw.

Please make this more generic, using the OpenAI API standard with model discovery. That way it works against a bare Llama.cpp instance out of the box, the local inference server that many others wrap around (like Ollama and LM Studio).

I've found that many "skills" with regard to using AI become obsolete very quickly. It's really hard to stay ahead of the curve, IMO. I was using agents over 2 years ago and felt way ahead of the curve [1]. Today, Claude will spin up agents without even having been asked.

Feels a bit like a fools errand.

[1] https://www.loom.com/share/aa6e55acb18c445e9186637ac763c08d

This is an idea that a platform like Kickstarter used to be great at validating. I did this in 2012 and found around 500 users willing to pay for an open source photo management software.

Finding customers will be difficult. I suggest finding a couple and then talking with them to learn what they want first and then understand their willingness to purchase by offering them a device at a cost.

For me - I’m in the market. I flashed my Asus router with Merlin. I’d do the same for my next router. What might lead me to buy my next device from you?

- I like to support independent vendors when I can. (See caveats below) - I would like a built in way to keep the firmware up to date … mine is old. - I would want to understand the commercial equivalent router based on specs to make it easier for me to decide if it will meet my needs. - The rest is provided by DD-wrt.

Happy to be user #1. Contact in profile.

Trust over speed. That’s all that’s being said here.