Can someone give mea reference that describe how exactly multimodal tokens are generated?
The killer app of Gemini Pro 1.5 is using video as an input
151–160 of 507 posts
Re: The killer app of Gemini Pro 1.5 is using video as an input
#152Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
That's impel - https://tryimpel.com
Re: The killer app of Gemini Pro 1.5 is using video as an input
#153Earlier quoted context omitted.
Unless its open sourced :)
In modern world open code often doesn't mean much. E.g. Chrome is opensourced. And yet no one really contributes to it or has any say over the direction its going: https://twitter.com/RickByers/status/1715568535731155100
Open source isn't meant to give everyone control over a specific project. It's meant to make it so, if you don't like the project, you can fork it and chart your own direction for it.
Re: The killer app of Gemini Pro 1.5 is using video as an input
#154Earlier quoted context omitted.
Unless its open sourced :)
In modern world open code often doesn't mean much. E.g. Chrome is opensourced. And yet no one really contributes to it or has any say over the direction its going: https://twitter.com/RickByers/status/1715568535731155100
One needs to follow the money to find the true direction. I think the ideal setup is that such a product is owned by a public figure/org who has no vested interest in making money or using it in a way.
Re: The killer app of Gemini Pro 1.5 is using video as an input
#155I can’t wait for the closed source and NDA future of everything. It’s gonna suck.
Re: The killer app of Gemini Pro 1.5 is using video as an input
#156Earlier quoted context omitted.
Unless its open sourced :)
In modern world open code often doesn't mean much. E.g. Chrome is opensourced. And yet no one really contributes to it or has any say over the direction its going: https://twitter.com/RickByers/status/1715568535731155100
Chrome is not open sourced, Chromium is.
Re: The killer app of Gemini Pro 1.5 is using video as an input
#157Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
That's impel - https://tryimpel.com
There's limited information on the site - are you using them or affiliated with them? What's your take? Does it work well?
Re: The killer app of Gemini Pro 1.5 is using video as an input
#158Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
A version of this that seems both easier and less weird would be an AI that listens to you all the time when you're learning a foreign language. Imagine how much faster you could learn, and how much more native you could ultimately get, if you had something that could buzz your watch whenever you said something wrong. And of course you'd calibrate it to understand what level you're at and not spam you constantly. I would love to have something like that, assuming it was voluntary...
Re: The killer app of Gemini Pro 1.5 is using video as an input
#159Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
That's impel - https://tryimpel.com
The "smart tasks" functionality looks like the most compelling part of that to me, but it would have to be REALLY reliable for me to use it. 50% reliability in capturing tasks is about the same as 0% reliability when it comes to actually being a useful part of anything professional.
Re: The killer app of Gemini Pro 1.5 is using video as an input
#160Earlier quoted context omitted.
That's impel - https://tryimpel.com
There's limited information on the site - are you using them or affiliated with them? What's your take? Does it work well?
I have been using their beta for the past two weeks and it's pretty good. Like I am watching youtube videos and it just pops up automatically.
I don't know if it's public yet, but they sent me this video with the invite: https://youtu.be/dXvhGwj4yGo