[dead]
Tl;dv: Over 180k meetings left wide open
131–140 of 231 posts
Re: Tl;dv: Over 180k meetings left wide open
#132Earlier quoted context omitted.
I doubt SOTA models nowadays are going to produce an implementation without any kind of authentication like here, and not tell you about it. And even if, a later "is this ready for release" will probably surface such obvious issues. I do not think LLMs are the problem here. Today, they are most likely more competent than whoever set this up.
I love the never-ending "SOTA" treadmill used to defend anything and everything these LLM tools shit up. Doesn't matter what happens, it wasn't one of the "SOTA" models (which changes every 7 seconds) ergo it's irrelevant, how very convenient for the AI pushers!
More than half a year ago, someone may or may not have used AI to implement this insecure backend.
That is not a very good basis to start complaining about AI producing insecure code.
If you still want to do it, at least check if it actually is the case with reasonably intelligent current models.
Re: Tl;dv: Over 180k meetings left wide open
#133Seems like they fixed this a few days ago: https://tldv.io/blog/our-thoughts-on-the-darkreading-com-art... But they try to play it off as though this were public data: > Public sharing settings across AI and SaaS products have surfaced similar findings in recent months. Anthropic addressed exposed public artifacts across Claude and its MCP ecosystem via Google Search. Also, interesting, they are SOC2 compliant [1], p…
Reminds me of ISO certification. Where all it does is that your complaints are called non-conformance.
Re: Tl;dv: Over 180k meetings left wide open
#134It's hilarious how these companies handle security breaches. I once reported superadmin user/pass committed to github at a major YC backed background check company I worked at and everyone tried to make it seem like it was my fault . I had just started working there and found it in the first week. Anyway, had to show that it was committed by their main Staff engineer 2 years before I even worked there. For 2 years ev…
More proof that software engineering isn't real engineering. If a civil engineer made a mistake that bad in my country, he'd likely lose his engineering licence.
Of course it's not real engineering, and most software development never was real engineering.
Trying to apply real engineering licensing ideas to software would just result in the word "engineering" no longer being used in the vast majority of cases. If that's your goal, then sure, great. But it won't stop ridiculous security mistakes from being made, they'll just be made by people with different job titles.
Re: Tl;dv: Over 180k meetings left wide open
#135Earlier quoted context omitted.
Seems interesting. What would you say are the biggest missing points currently or things you want to get working/improved but couldn't yet?
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. Havi…
Since the participants are known and limited, have you tried building around samples tagged with user/person names?
Re: Tl;dv: Over 180k meetings left wide open
#136Re: Tl;dv: Over 180k meetings left wide open
#137I wonder how the HN algo chose this one link to Bobs blogpost to be the one to hit the front page. This story was committed three more times by three different users, 6 days ago (16 points), 4 days ago (11 points) and another one 4 days ago, again with 16 points.
Re: Tl;dv: Over 180k meetings left wide open
#138I saw an YouTuber the other day sharing their "day in the life" as an Amazon Software Engineer while promoting (as part of a paid sponsorship) the AI note taking feature of SoundCore headphones, claiming they now record their meetings and receive an AI summary at the end. I wonder how many companies realise these devices that appear as "headsets" are now funnelling their meetings into these new AI companies who are m…
I don't really understand why these "AI notetaking" services/features still exist outside video conference software today -- any company that needs it would have already purchased the license from Zoom/Teams/Slack which takes care of everything including storage and compliance.
Re: Tl;dv: Over 180k meetings left wide open
#139Earlier quoted context omitted.
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. Havi…
Interested also, which text-to-speech model do you use? For diarisation Granola uses a chrome extension instead of a bot if that can give you ideas.
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
Re: Tl;dv: Over 180k meetings left wide open
#140The worst part of these AI meeting notes and recordings is that I have literally never seen anybody , in any situation, go back to them. The (very) few times I ever bothered to check the transcripts and especially the summaries immediately after a meeting, without fail they'd have something in them that is the complete opposite of what someone said in the meeting, or they'd miss extremely important clarifications or…
That is a wild claim. Every single quarterly meeting my company has with customers begins with redistributing the notes from the previous meeting, and "to-do" points are regularly referenced.
AI notes are a godsend, because instead of forcing one person to keep careful notes throughout, the meeting's host can quickly review, edit, and send out the minutes - a job that otherwise would literally take more time than the meeting, because one person spent the meeting just taking notes. The AI notes require careful review, and contain a lot of repetitive fluff, but all notes require review before distribution.
So, now you are aware that this is a normal thing in other companies.