Hacker News new | past | comments | ask | show | jobs | submit | molli's comments login

Did you click start and nothing happened? The service is up and running..


I clicked on the extension icon and it didn't work. I don't see anything for it on any youtube video page either.


Can't reproduce it right now, but I'll look into it. Normally, it would show a button to sign in with google.


I was using it on Edge, which usually supports chrome extensions directly. So maybe that's why.

Tried it on chrome. Could sign in, but doesn't work after that nor does it maintain my login session. Each time I click on the extension it prompts me to sign in with google.


Coming soon


You watch a YouTube video or participate in a video call etc. where humans are talking. You click on the extension. You select a language. You click start. Every 30 seconds the audio gets transcribed and translated into short bullet points. The transcripts are saved. Finally, you can ask the transcript any question or transform it into a poem by Arnold Schwarzenegger - one of the great Austrian thinkers.


> You watch a YouTube video or participate in a video call etc. where humans are talking.

If transcriptions of my video calls are being performed in the cloud on an untrusted server, then this feels like a big security risk...?


Yes, that's because it is a leak - just like most other cloud services by the way. Step by step, piece by piece, bit by bit the concept of 'privacy' has been hollowed out by pushing 'cloud' services (where 'cloud' stands for "someone else's computer") into just about all aspects of personal data-manipulation. This was one of the tenets of the 'Great Reset' push by the World Economic Forum which sought to capitalise (no pun intended) on the SARS2 pandemic to reshuffle the world into their vision of a new society. One of the better known publications which espoused this idea was written by Danish member of parliament Ida Auken under the title Welcome to 2030. I own nothing, have no privacy, and life has never been better. Here is is on the WEF site:

https://www.weforum.org/agenda/2016/11/shopping-i-can-t-real...

If you follow that link you'll be told they're Sorry, but we can’t find the page you were looking for. Fortunately there is the Internet Archive to save the day:

https://web.archive.org/web/20200919102818/https://www.wefor...

There is a sentence at the end of the article which refers to the death of privacy in the service of this brave, new world: Once in awhile I get annoyed about the fact that I have no real privacy. No where I can go and not be registered. I know that, somewhere, everything I do, think and dream of is recorded. I just hope that nobody will use it against me.

Since these ideas did not go down that well - which is an understatement - the lede was buried and later still removed from the site but the push towards giving up personal privacy has in no way diminished. Think of that the next time you consider using one of these 'handy' services, also the next time you log in to your cloud account. How much of your personal life did you entrust to that cloud vendor? Maybe the time has come to take it back?


These are noble values! But how to build a tool for easy transcription and summarization then?


At this moment, not just yet. Once either the models have come down in size or hardware has caught up with the demands so they can be run locally it will become feasible to offer such functionality in a way which does not sacrifice privacy to convenience.


I know what you mean. But I can't run the transcription and llm locally on the user's machine. So it has to be in the cloud. And most video calls and transcription/translation services are in the cloud anyway. So yes, you have to trust that the backend is secure, and it is.


What about an Austrian born painter?


hi, it's cpu, makes full use of simd on multiple cores and i got 3 tok/s. it's also memory mapped, so it stays in ram once it's loaded. the weights are 8 bit quantized. it can run as a server and is the backend of https://x.com/paulpapers - a x bot, that reads all llm arxiv papers and shares the ones that are about running llms more efficiently.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: