properbrew

> please only use official builds

Wasn't this an official build though? A signed updated version of a package released by the same developer as the one you've already installed, the supply chain was hacked.

Not true at all, especially in this scenario (emergency), when you finally leave hospital there is no bill to pay for the treatment you received.

> GPS synchronized emergency lights

I actually did and whilst I can understand how ridiculous it sounds, to be honest it kind of makes sense. A large number of emergency vehicles at a scene at night can become it's own mini light show which can be really distracting / blinding.

https://standbygroup.com/uk/sync-breathe/

It does look kinda cool though.

I also see the washout on firefox. I think you can guess which is which - https://imagepaste.org/i/k2ect45t.png

I whipped something up for a friend a few months ago, it's not just fixing timestamps like you've asked, it's processing the whole audio but it does a good job (uses parakeet) and is quite quick.

Download links and a bit of write up here - https://news.ycombinator.com/item?id=48528779#48535207

Honestly you can probably build your own quite easily. I put together a plex player for firetv that does on device subtitling for whatever you're watching. I got sick of having to find subtitles.

> Currently using F5-TTS

Thanks for listing the model you're using, I've not really done any TTS stuff and this sounds like a fun thing to spin up.

> It seems like LLMs are great for the kind of generic work you'd usually pawn off to a new associate or paralegal

This seems to be the case with most industries that LLMs are impacting, coding, data input, legal etc.

Whilst it's great to get the time saving from not delegating to a junior (LLMs are much faster at the basic level 1 work) there's going to be this big knowledge gap that you really only gain from actually doing the mundane boring shit.

A lot of this _should_ be automated away, but we really need to think about how the next group of people are going to learn the skills and nuance to applying them. I don't really have an answer to that one other than still giving that work to junior staff, but they will then just utilise an LLM to help complete the job, and rightfully so, I'd have done exactly the same thing.

I think OpenAI tried doing this with some early chatgpt settings with "learning mode" or whatever that is. But an LLM just telling you what to do will never teach someone, there was something about having to go out and hunt for the answer through the sea of crap responses or wrong SO questions that really taught you something. How do you replicate that learning with an LLM and how do you apply that to different industries like Law?

Honestly, probably open up codex/Claude/pi in the folder and ask it where to start. Modern LLMs are crazy good.

For example I had a VR setup of GTA5 with adaptive triggers during covid but it eventually degraded due to updates and compatibility issues. Quite literally today I opened codex and had it up and running with custom patches for some bugs I used to deal with in a few hours.

I would start by asking it how to start and then digging away.

Might look into embedding Whistle into Whistle if it can make it 30x smaller (https://play.google.com/store/apps/details?id=com.blazingban...) - It's a shame there isn't as many languages supported though, I'm surprised at the amount of non-english downloads (I really shouldn't be, of course non-english speakers want dictation) of the app there is.

> “The first slow-motion video of a butterfly I put through our bird-vision computer model was glowing with downwards motion even though the butterfly was moving up.

Yep, really would have loved to see that video. Why mention it and not link to it.

Still working away on the same thing - https://whistle-enterprise.com

Latest updates around audio processing and quality are out, I've also made a substantial addition by implementing extensions.

This allows people to hook up to M365 or Google to get desktop notifications to start the recording, it can also export to share point and stop the recording at the registered meeting end.

Was a fun process keeping the offline and online functionality completely separate, also getting validated by Microsoft for the M365 extension was a bit of a chore, but finally have the verified blue tick.

https://getsoftwarehouse.com - I'm also working on the governance layer for AI tooling that is being built by employees, there's just HTML files flying all over the place, no security, no home. So built software house as a place for these things to live, be secured, put OIDC in front etc. It's fun!

But what if they no longer have to "tolerate mucking out the stables" and can instead focus on riding.

We could go back and forth on the analogy but I think it comes down to one of two things:

1. You enjoy writing code to fix a problem

2. You enjoy fixing problems and solve that by writing code

If you're in camp 1 then AI feels extremely unfulfilling and understandably so, for camp 2 it's a whole new world.

Thank you, the fact that's all you picked up on makes me very happy.

I can see the analogy, but fundementally that human liked caring for animals, they didn't like transporting the goods as effectively as possible, if they did then sitting in a box optimising delivery time would make them feel useful and respected.

The human in your analogy would be better off working with animals on a farm, or vet practice, where the technological advances that deliver better care to animals would make them feel even more fulfilled.

Is that because they didn't type code on the keyboard? They still had to think of an idea, conceptualise it, work and prompt AI, test the results, alter things, work through problems, stick to a direction and bring about something from nothing.

Sure your one shot generic websites don't really have any "skill" or "honour", I may as well just read a text file of what you wanted to say (and I'd prefer that), but to say there is no sweat, tears or skill to using _any_ generative AI is a little bit narrow minded.

Appreciate you taking a look through!

> my issue isn't the use of AI at all (I use it myself), the problem is being able to recognize a carbon copy Claude/Codex design in <5 seconds. At that point I can't help but assume it's just slop that was fired off with a couple prompts and not worth my time engaging any further.

You absolutely hit the nail on the head.

This is absolutely a generic AI website. Do you feel the same about one I've developed using AI? https://whistle-enterprise.com/

I think the AIslop of websites is down to the lack of vision or user journey and just going with the default which will always be generic and bland.

If it does feel in the "AI style" I'd love to understand what it is.

I still don't understand how these massive touchscreen displays are allowed in vehicles.

I had to rent a van that had everything "integrated" in its display. Absolutely atrocious software, latency and responsiveness for standard things such as temp and fan speed.

Also withholding this "extra" means you have to take your eyes off the road and look down to the right/left to make sure you're doing the right speed. Sounds a bit over the top, but I wonder if these designers think about the fact they might actually be the ones responsible for people dying in crashes.

Yes GEO (Generative Engine Optimisation) is one I've seen around.

100% looking at it from an after use basis, whilst there is live transcription, trying to do anything above that on 6 year old laptop CPU just grinds stuff to a halt.

Some great suggestions, appreciate you taking the time to write it out, it's given me some things to think about.

Thank you! Feel free to drop me and email (info in bio or on the website) if you run into any issues or have any suggestions.

I tried something similar by putting together a "global ledger" of speaker identities. This was more happening during the call than having a predefined one but I just couldn't get it to work properly. The issue being that as soon as some speech gets assigned to a new label or an incorrect one, everything ends up getting misaligned and gets messy quickly.

I might take another look into doing it in a different way that gradually builds up from successful calls, I just need to think of how to do this in a simple(ish) way for non-technical users and a way that still works well enough on low to mid tier laptops.

I think this is just to capture the audio to ship off to their servers and do the crunching. You mentioned the word "extension" and thank you so much, I've been thinking about how to do integrations as it's something a few users have mentioned, but keep the whole "completely offline" angle. I could build standalone extensions that integrate with it if it's something a user wants. So damn obvious in hindsight!

Ahh yea as for the models:

Speech to text - Nvidia Parakeet TDT 0.6b V3

Diarisation - Nvidia Marblenet for the speech detection, TitaNet-Large for the embeddings and then using NeMo multi-scale to do clustering around them

Thank you, great question! Hard one to answer, thought about it a lot and it's going to be the diarisation of more than 5+ speakers per audio stream (your microphone + system audio for a max of 10). I actually spent a lot of time that went completely nowhere trying to fine tune my own diarisation model, it was fun to a degree but painful to see my output end up worse than what I currently had after days of work. Having a bot join the call would be such an easy way of diarising, the call software has already done it for you, but feels like a bit of a cop out.

Two more improvements, audio quality improvements which is currently in the works and close to release and a new document generation model. I'm currently using a custom fine tuned Phi-4 (released December 2024!) model, that's _so old_ in the grand scheme of LLMs, I just haven't had time to benchmark and properly test some new models whilst this currently does a good job as it is. There has to be some gains here, but who knows!

I'm definitely biased as the developer, but maybe try https://whistle-enterprise.com and see how it works for you.

It's a hard problem I've been working away on for a while now. It's far from perfect but every step brings it a bit closer.

I didn't quite understand what you meant from your description, started playing it and love it! Educational too!

Still working away on a completely offline meeting document generator that works on generic laptops with no GPU (https://whistle-enterprise.com). A new release coming very soon focusing on getting clearer audio which in turn makes the transcription and end document generated more accurate.

Inbetween that I've been working on a "software house" (don't know how else to describe it). Pretty much codex/claude running on a VPS with a web interface and the ability to actually build and publish software / webapps etc.

It came from me sitting on the train on the way home and I had an idea pop into my head for a pebble watch app, I wanted to build it and test it there and then as I still had about 45 mins left. I know you can run codex against git repos in the cloud but I didn't want to faff with that (and last I remember the allowances for this were much less generous). It's been really fun, probably many things like this out there but it works exactly how I want it to. I plan to open source it once I've tidied things up a bit more.

What you can do is use AI to drive your browser to navigate the maze of "deals" on offer to actually find the best one for you as a consumer.

You probably don't need the AI _they_ shoehorn in.

The card idea is absolutely great. I'm totally going to do the same. There's a number of songs in my playlist that I _really_ enjoy that I would make cards for.

Thank you for the inspiration for a weekend project!