I tried to share screen with Gemini while watching a movie, but it just kept responding to the movie every two or three seconds. It seems it cannot tell the difference between my voice and sound in the video.
In another one of their videos (can’t remember exactly which), they showed Astra and it actually had a complete Uı too. It said “Project Astra (Experimental)” at the top in the style of Pixel Studio. So I wouldn’t be surprised if they release astra soon
How do I embed voice enabled help in my website using Gemini? For eg. I own a bank & I want my customers to learn how to use the website - say connecting another bank to transfer money.
Thats very impressive, nice work Google! 3:08 a remark, wouldn't it be better if when a user interrupts the ai reading that the ai stops like immediately and listens what the user want and not after the user is finished with the new request.
Hi, is it possible to share my screen with Gemini, and show my visual trading setup, showing some days and trades, and explaining with audio my setup, at the same time on the video, in order to code this human trading decisions in csharp ? for let's say for example quantower api ? thanks for your answer
Guys, the file api doesn't seem to work properly anymore and returns this... 403 You do not have permission to access the File xyzxyzxyz or it may not exist. Please help resolving it..
Web-socket technology is simply not designed for such a high volume of data transfer and concurrency - thats why we see so much complaints about errors - before we were using SSE (Server Sent Events) and it was much more robust. We need to improve websockets in order to be able to stablish long stabe and multimodal conversations
When will this be implemented in things you can say "Hey Google" to? These things barely understand basic stuff like "turn on the radio" at the moment.
Gemini 2.0’s knowledge cutoff is September 2021, so I lack information on events after that date. This limitation isn't ideal for code generation, but it's beneficial for other purposes.
Well i tried it on coding and other bunch and to my surprise this might be the best model out better then gpt 4o at par with sonnet 3.5 new and gpt o1 mini. But this is the Ai studio one the one gemini app is kinda worse
Great, for the first time I feel satisfied with Google, but it is very important to add Arabic, because it is very common in the world of the first 5 languages.
It's great that the AI is multilingual and is absolutely fluent in other languages, but why retain the accent rather than making them speak as a native? People will want to use this functionality for language learning, where practicing with a native speaker is the desire. As of now it's like practicing with a fluent, but non-native, speaker.
The technology is really cool.. but Gemini's ability to "think" is incredibly bad. It keeps making the same mistakes over and over again in spite me correcting it multiple times. I just don't understand how the team can build such cool tech but it's models are incredibly terrible at logic compared to it's competitors.
I just used it to analyze gameplay almost in real time, it blew my mind, but crashed every few minutes. Incredible model
yeah its annoying that it stops working after a while and you have to start from scratch each time.
Great improvement! Good job to all involved 👏
These interactions won't last more than 3 minutes, i get "something went wrong" then have to start all over
Did I just "that's what she said" myself 💀
This.
@@bitcode_ bruh lol
I think you have to be an early tester. I am also getting an error with outputting images
Yeaa
I tried to share screen with Gemini while watching a movie, but it just kept responding to the movie every two or three seconds. It seems it cannot tell the difference between my voice and sound in the video.
I feel like I can make an assistant for.... anything... with these APIs. Multi-lingual assistants, even though I am not. Insane.
insane for what? u are cringe af
Wait a second, if this is out.. Astra can't be far off!! 😊
Maybe by the end of this year?!
In another one of their videos (can’t remember exactly which), they showed Astra and it actually had a complete Uı too. It said “Project Astra (Experimental)” at the top in the style of Pixel Studio. So I wouldn’t be surprised if they release astra soon
this feels like astra just without an official polished and dedicated ui.
nope
Thank You So Much Sir....❤❤👍👍
How do I embed voice enabled help in my website using Gemini? For eg. I own a bank & I want my customers to learn how to use the website - say connecting another bank to transfer money.
Would be nice… if studio didn’t throw and error every minute or two.
I'm so disappointed. There's no file access.
It can listen to you while interrupting so crazy!😮
What about user voice isolation without that voice experience is very limited
Can tts output the word timings, too? We'd like to have closed captions for accessibility requirements.
Thats very impressive, nice work Google! 3:08 a remark, wouldn't it be better if when a user interrupts the ai reading that the ai stops like immediately and listens what the user want and not after the user is finished with the new request.
When it started to speak English, French and Korean was mind-blowing 😮
Hi, is it possible to share my screen with Gemini, and show my visual trading setup, showing some days and trades, and explaining with audio my setup, at the same time on the video, in order to code this human trading decisions in csharp ? for let's say for example quantower api ? thanks for your answer
Esto es extraordinario, habre un abanico de posibilidades impresionantes
Google Ai Studio - Always returns error "An internal error has occurred"
Guys, the file api doesn't seem to work properly anymore and returns this... 403 You do not have permission to access the File xyzxyzxyz or it may not exist.
Please help resolving it..
I can't reproduce the demo with the car to convertible, no image is generated, anyone else?
Are you an early tester?
Which of these features are live?
To try
all of them
It can't whisper or speak in other languages
@@samwolfe1000 It already can switch language
@@samwolfe1000 same
Web-socket technology is simply not designed for such a high volume of data transfer and concurrency - thats why we see so much complaints about errors - before we were using SSE (Server Sent Events) and it was much more robust. We need to improve websockets in order to be able to stablish long stabe and multimodal conversations
How to get access?
When will this be implemented in things you can say "Hey Google" to? These things barely understand basic stuff like "turn on the radio" at the moment.
Gemini 2.0’s knowledge cutoff is September 2021, so I lack information on events after that date. This limitation isn't ideal for code generation, but it's beneficial for other purposes.
Dude the cut off august 2024 😭
@ I just checked from a API. Its September 2021!
@ no bro check it on Gemini on Ai studio its august 2024 even the google gemini 1 had a mid 2023 cut of time.
Gemini on Ai studio is cracked
@@my_name_is_ahad bro on ai studio its august 2024 try it there. They perform much better there
Even if it's 2021...give it rag and a search tool
Looking forward to real-world productivity gain applications at affordable price points.
What about junior devs?
When will we meet Gemini 2.0 pro?
I hope never
Pricing?
Gemini 2.0 is insane
Massive unemployment?
We can put this multimodal live API to a robot and interact with them more naturally
Great improvement
Interesting 😊🥰🤣
aitutorialmaker AI fixes this. Gemini 2.0, multimodal AI model.
Native language and Image isn't working
Node ?? when
Well i tried it on coding and other bunch and to my surprise this might be the best model out better then gpt 4o at par with sonnet 3.5 new and gpt o1 mini. But this is the Ai studio one the one gemini app is kinda worse
Got a lot of wrong answers. Needs work.
It was answering questions that I didn't ask as well 😮
This is awesome
Something has to give with giving ai internet access...those with constant access are just infinitely better
Great, for the first time I feel satisfied with Google, but it is very important to add Arabic, because it is very common in the world of the first 5 languages.
whispering: "thank you Google"
Google, can you please stop sending ads on my phone and I use Gemini on my phone
Googs, gotta hand it to ya, this ish gettin gud (*lawnchair*)
🎉
It's great that the AI is multilingual and is absolutely fluent in other languages, but why retain the accent rather than making them speak as a native? People will want to use this functionality for language learning, where practicing with a native speaker is the desire. As of now it's like practicing with a fluent, but non-native, speaker.
1.6k views in 40mins:
Bro fell off ❌
The world is sleeping on bro ✅
First
Crashy baby
"something went wrong"
awesome
تحسن رائع
Is he real?
DRAMATIC
...
PAUSE
🥱🥱
Give us AIOS and no-code App development.
The technology is really cool.. but Gemini's ability to "think" is incredibly bad. It keeps making the same mistakes over and over again in spite me correcting it multiple times.
I just don't understand how the team can build such cool tech but it's models are incredibly terrible at logic compared to it's competitors.
First improve its language hearing ability.... mostly it misunderstands my words..with chatgpt i never faced any problem
will you steal our data again bro?
if u have privacy issues don't use all ai products. u can use open source instead