reads like an AI article.

regardless, having used both in side projects I will say they are roughly the same with different semantics. So, either use langchain b/c it has more pre-built solutions or use neither because your project probably won't benefit from the abstractions they provide.

seconded sibling comment's advice. just do it yourself. the overhead of learning these frameworks is not worth it because they aren't doing anything groundbreaking.

having tried them both, they are nearly the same with different semantics. langchain (python) had more libs and prebuilt integrations though.

Not disagreeing that it must work, however, I think immunity is possible with a simple heuristic: Say no to all inbounds.

Or more specifically, if you get a call and it's not from someone you know then you simply hang up. Relevant information comes from you seeking it out, not the other way around.

So... an ad-based search engine? Sounds familiar. The alternative needed is an alternative business model

kagi exists. If you're not already using that then I'm not sure what other alternative business model you can ask for.

Indeed, I use Kagi daily. My point above was simply that this company looks like it will be subject to the same incentive problems as almost all other search engines, Kagi being the exception.

All we need is to show less SEO and more sites made with passion, that have communities involved in them, etc.

Aka things made by real people and not marketing drones.

Unfortunately, all the "real people" are only publishing things on closed-off social media sites instead of the wider internet, so the majority of things outside of those sites is either crap nobody wants to read, or mono-culture nerd/tech blogs from people like us.

You're right that it exists, but it's complete crap outside a quiet environment. Try to use it while walking around outside or in any semi-noisy area and it fails horribly (iPhone 13, so YMMV if you have a newer one).

You cannot use an iPhone as a dictation device without reviewing the transcribed text, which IMO defeats the purpose of dictation.

Meanwhile, i've gotten excellent results on the iPhone from a Whipser->LLM pipeline.

I've never found real-time dictation software that doesn't need to be reviewed.

I'm definitely waiting for Apple to upgrade their dictation software to the next generation -- I have my own annoyances with it -- but I haven't found anything else that works way better, in real time, on a phone, that runs in the background (like as part of the keyboard).

You talk about Whisper but that doesn't even work in real time, much less when you have to run it through an LLM.

What's the real-time requirement for? We may have different use cases, but it's not needed if I don't need to review the results. Speak -> Send, without reviewing the text, is the desired workflow. I.e. so you can compose messages without looking at your phone.

So yes, i'm not sure of alternate real-time solutions, but the non real-time solution of Whisper is much better for my real-world use case.

With Tailscale you could access the port serving the models API (assumedly via ollama or similar) so the friend wouldn't have to grant any access beyond that.

This, plus connect via Tailscale and you can access it from anywhere (assuming you're friends laptop is online).

While I know this isn't an option for everyone, pursuing your own small business is an alternative to employment. Requires some savings to get started, and no guarantees of success, but it's worth considering.