This is much better but I can still tell. But I'm sure you guided it a lot to arrive at this state. Surely people with less care are one shotting and publishing boring websites.
FWIW, I clicked through a few pages and this doesn't register as AI slop to me at all.
At least, it's missing the cargo cult telltales like the beige or unreadable neon hax0r dark mode theme, that console looking font with three different sizes and tiny headings, formatting vomit with italics/bolding every other word, useless cards/animated colored dots, scrolling text, excess boilerplate text on every surface, useless generated tags/categories/chips everywhere, etc that plague the designs of the last year.
Overall it's clean and modern (and the interactive table actually has content not pointless filler). It definitely wouldn't have triggered my visceral slop reaction and therefore wouldn't bother me if I later learned the dev used AI to make it.
I can't speak for everyone, but personally 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.
(Mostly) the same with prose. But that's playing with fire a bit because while a website/app might have a utilitarian purpose, I will have zero motivation to continue reading text I didn't prompt myself once I suspect it's from an LLM. There's just too much spam now to give benefit of the doubt unfortunately. The writing on your site doesn't scream LLM either though so I think you're good on both fronts.
It's like the saying "if you're explaining you're losing": once the seed is planted that it's AI, it's extremely hard to successfully argue your identical Claude-designed site is the exception that deserves users' limited time. Putting in some minimal thought and care in advance to avoid that first impression means fewer of those arguments with potential users experiencing slop fatigue like me. Anyway, nice job!
> 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.
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.
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 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
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 know this is hn and not a product development meeting, but:
If you’re targeting data for people to use on the same call then requires more intense work, while if you’re targeting data for people to use after or on an ongoing basis (eg an established business meeting with staff/vendors/etc) then having a predefined one seems good. Same interface as a CRM: picture, some audio clips for users to choose from, and confidence scores on each section of the recording for cases where people sound similar or are talking over each other. Over time the diarization gets better as users accept/reject/tag samples and that work helps them feel more aligned with the tool.
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.
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.
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!
Have spent the last month giving the UI a bit of a modernisation refresh and simplifying/improving some elements based on early user feedback. There's also been a boat load of performance improvements in the dirarisation and document generation pipeline.
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.
reply