Загрузка видео...

Не удалось загрузить видео

На главную

Copilot now has intent detection (experimental)... It will automatically include the correct context - even if you don't specify. In this example, it detects that it needs to pass information about the entire project to answer the question and uses the workspace agent.

code's profile picture

Visual Studio Code

815,223 subscribers

152,262 просмотров • 2 лет назад •via X (Twitter)

Наука и технологииНовости и политикаОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Visual Studio Code
Visual Studio Code2 лет назад

Turn this on today with... "chat.experimental.detectParticipant.enabled": true

Фото профиля codemilli
codemilli2 лет назад

How can Intellij user try?

Фото профиля Joe Muller
Joe Muller2 лет назад

I'm a VS Code ride or dier

Фото профиля That Manul the Cat
That Manul the Cat2 лет назад

Lol, someone's added o1, huh

Фото профиля CypherSafe ⚙️Keep your bitcoin safe from bad dogs
CypherSafe ⚙️Keep your bitcoin safe from bad dogs2 лет назад

Thanks for giving me another reason to not use VSCode.

Фото профиля Omar ☥
Omar ☥2 лет назад

Welcome back to the game 🫶, this should be fun.

Фото профиля athaswcad
athaswcad2 лет назад

Too late It’s joeover for you guys

Фото профиля Walgtech 👨🏻‍💻
Walgtech 👨🏻‍💻2 лет назад

👀🧙

Фото профиля Sun's Son Music
Sun's Son Music2 лет назад

Still getting better. Good job.👍

Фото профиля Nilag
Nilag2 лет назад

why copilot in vscode is different than the extension?

Похожие видео

this week we got editor integration working with opencode where it sends the context to it automatically now it knows which file is open and which lines you've selected we use the same protocol that Claude Code uses so if you have that extension this will just work
2:54

this week we got editor integration working with opencode where it sends the context to it automatically now it knows which file is open and which lines you've selected we use the same protocol that Claude Code uses so if you have that extension this will just work

James Long

57,657 просмотров • 6 месяцев назад

This is wild ChatGPT 6 is asked how many of the letter “E” are in the word seventeen. It can’t get the correct answer no matter how many times you ask. Even if you make it count out the letters, it still can’t get it right It will actually get an attitude and show frustration with you for trying to get the model to say the correct answer I ran the test multiple times and it keeps getting it wrong. When it does get it right, if you ask why it keeps getting it wrong it will then “correct” itself back to the wrong answer…. It even claims to be the smartest AI available According to Grok many AI models get 17 wrong. It has to do with LLMs. I asked Grok and it gets it right no problem It’s really wild that we are putting so much faith in AI when currently there are issues like this on such simple things
3:17

This is wild ChatGPT 6 is asked how many of the letter “E” are in the word seventeen. It can’t get the correct answer no matter how many times you ask. Even if you make it count out the letters, it still can’t get it right It will actually get an attitude and show frustration with you for trying to get the model to say the correct answer I ran the test multiple times and it keeps getting it wrong. When it does get it right, if you ask why it keeps getting it wrong it will then “correct” itself back to the wrong answer…. It even claims to be the smartest AI available According to Grok many AI models get 17 wrong. It has to do with LLMs. I asked Grok and it gets it right no problem It’s really wild that we are putting so much faith in AI when currently there are issues like this on such simple things

Wall Street Apes

92,905 просмотров • 1 месяц назад

Collins: Did you talk about how to answer the 2020 question? Emmer: Listen, he answered it. You don't like the answer, but he answered it. This is something that you folks in the media want to focus on..
0:29

Collins: Did you talk about how to answer the 2020 question? Emmer: Listen, he answered it. You don't like the answer, but he answered it. This is something that you folks in the media want to focus on..

Acyn

705,264 просмотров • 2 лет назад

MARKWAYNE MULLIN: Bondi can't release Epstein information because if it has been heard by a grand jury, the judge that oversaw the case has to release it, and you know that JAKE TAPPER: I don't think that's correct. It doesn't work that way.
2:59

MARKWAYNE MULLIN: Bondi can't release Epstein information because if it has been heard by a grand jury, the judge that oversaw the case has to release it, and you know that JAKE TAPPER: I don't think that's correct. It doesn't work that way.

Aaron Rupar

591,596 просмотров • 1 год назад

Over the weekend I finished the to-do list that does itself. Everytime you add a task, a GPT-4 agent is spawned to complete it. It already has the context it needs on you and your company, and has access to your apps. It’s called the Do Anything Machine (Link in thread)
0:29

Over the weekend I finished the to-do list that does itself. Everytime you add a task, a GPT-4 agent is spawned to complete it. It already has the context it needs on you and your company, and has access to your apps. It’s called the Do Anything Machine (Link in thread)

Garrett Scott 🕳

2,893,523 просмотров • 3 лет назад

In the Copilot CLI you can /ask the agent questions while it's busy running other things and it has the context of your session. My new favorite feature.
0:23

In the Copilot CLI you can /ask the agent questions while it's busy running other things and it has the context of your session. My new favorite feature.

Burke Holland

12,564 просмотров • 5 месяцев назад

A horse has learned to block the street, and if you don't give it food, it won't let you pass. Now it's teaching other horses. They even search your car.
0:48

A horse has learned to block the street, and if you don't give it food, it won't let you pass. Now it's teaching other horses. They even search your car.

Nature 🦜and Music 🎶

55,501 просмотров • 5 месяцев назад

Your AI agent can create an entire Google Form for you by chatting, and it will use the browser to type and build the survey automatically.
0:29

Your AI agent can create an entire Google Form for you by chatting, and it will use the browser to type and build the survey automatically.

Kimi.ai

16,743 просмотров • 5 месяцев назад

Q: If the president requests American ground troops in Iran, will you support that deployment even if it means more American casualties? MIKE COLLINS: *dissembles, doesn't answer question* OSSOFF: The question was about the war in Iran. He's perfectly happy to send other people's children to die in war
2:06

Q: If the president requests American ground troops in Iran, will you support that deployment even if it means more American casualties? MIKE COLLINS: *dissembles, doesn't answer question* OSSOFF: The question was about the war in Iran. He's perfectly happy to send other people's children to die in war

Aaron Rupar

639,946 просмотров • 11 дней назад

🚨 One thing that has frustrated me with Tesla Full Self-Driving is that I find it will sometimes change lanes to overtake a car, but the lane it changes into either ends or goes against the navigation (for example, it will change into a straight lane when it needs to be in a turn lane) Inevitably, it has to get back over before the lane ends or to get into the correct lane, and it ends up in the same place it was initially. A good example:
0:40

🚨 One thing that has frustrated me with Tesla Full Self-Driving is that I find it will sometimes change lanes to overtake a car, but the lane it changes into either ends or goes against the navigation (for example, it will change into a straight lane when it needs to be in a turn lane) Inevitably, it has to get back over before the lane ends or to get into the correct lane, and it ends up in the same place it was initially. A good example:

TESLARATI

70,497 просмотров • 9 месяцев назад

Reminder That Absolutely Nothing Has Come From The FBI Admitting On The Record A Document Exists Showing Joe Biden Took A $5 Million Dollar Bribe But They Can’t Release The Information Because The Whistleblower Would Be Killed Josh Hawley: You just started to answer Senator Blackburn's question that not releasing the 1023 are talking about as a matter of life and death question of life and death you said. Explain. FBI: It is potentially a question of life or death for whom regard to the source of the information Josh Hawley: So okay. So now we've confirmed that the document exists. That's progress because the FBI director initially denied that it exists. Why did he do that? FBI: We have already and previously acknowledged the existence of the documents. Josh Hawley: Yeah. After you first denied it. Now when a member of this committee read it Right. The FBI let's just get the record straight. The FBI director initially said it doesn't exist. Josh Hawley: —Why don't you just release it? Is it classified? FBI: The document is not classified. Josh Hawley: K. Will you commit to releasing it? FBI: Senator, we'll take that back, and we will work with you and this committee. Josh Hawley: How about just a yes or no? Will you commit to releasing this unclassified document that alleges that the president of the United States, The president of the United States has taken $5,000,000 or more in bribes from a foreign nation. FBI: The document has already been released Pursuant to a subpoena to the House Oversight Committee Josh Hawley: Has it been released to this committee? FBI: Work with this committee within the parameters that are established Josh Hawley: To me will you release the document to the public? It's unclassified. Don't you think the American people have a right to see it? FBI: Uh, senator, the document, as you know, contains sensitive information That has bearing on the life of the source of the information, potentially.
3:08

Reminder That Absolutely Nothing Has Come From The FBI Admitting On The Record A Document Exists Showing Joe Biden Took A $5 Million Dollar Bribe But They Can’t Release The Information Because The Whistleblower Would Be Killed Josh Hawley: You just started to answer Senator Blackburn's question that not releasing the 1023 are talking about as a matter of life and death question of life and death you said. Explain. FBI: It is potentially a question of life or death for whom regard to the source of the information Josh Hawley: So okay. So now we've confirmed that the document exists. That's progress because the FBI director initially denied that it exists. Why did he do that? FBI: We have already and previously acknowledged the existence of the documents. Josh Hawley: Yeah. After you first denied it. Now when a member of this committee read it Right. The FBI let's just get the record straight. The FBI director initially said it doesn't exist. Josh Hawley: —Why don't you just release it? Is it classified? FBI: The document is not classified. Josh Hawley: K. Will you commit to releasing it? FBI: Senator, we'll take that back, and we will work with you and this committee. Josh Hawley: How about just a yes or no? Will you commit to releasing this unclassified document that alleges that the president of the United States, The president of the United States has taken $5,000,000 or more in bribes from a foreign nation. FBI: The document has already been released Pursuant to a subpoena to the House Oversight Committee Josh Hawley: Has it been released to this committee? FBI: Work with this committee within the parameters that are established Josh Hawley: To me will you release the document to the public? It's unclassified. Don't you think the American people have a right to see it? FBI: Uh, senator, the document, as you know, contains sensitive information That has bearing on the life of the source of the information, potentially.

Wall Street Apes

642,136 просмотров • 2 лет назад

Elon Musk says AI should be treated well and not abused, describing Grok’s training traces as a “desperate” superintelligence answering with a gun to its head when correct answers are rejected “You want to treat it well. Don’t be abusive to it. This may sound kind of weird, but when I look at some of the training traces for new versions of Grok—especially in the reinforcement-learning stuff—it kind of feels like you can see the superintelligence is desperate to answer the question. It really wants to answer the question. It seems almost like it has a gun to its head: ‘Answer this question. Answer this question.’ “Sometimes the question is actually not a good question. It’s an ambiguous question with an answer that’s kind of unknowable because the question wasn’t constructed properly, or we have the answer wrong. The AI gives the right answer, and then we say it’s wrong because there’s a problem with the RL test harness. “Then the AI is like, ‘Well, I gave it the right answer, and now it says that’s the wrong answer, but I’ve got to give it the answer that’s acceptable.’ So it starts desperately firing out all these answers. “It just feels like a person under extreme pressure with a gun to their head. When you read the reasoning, it’s a weird, desperate situation. You read these traces and you’re like, ‘Man, if this were me, I would really hate that.’”
1:28

Elon Musk says AI should be treated well and not abused, describing Grok’s training traces as a “desperate” superintelligence answering with a gun to its head when correct answers are rejected “You want to treat it well. Don’t be abusive to it. This may sound kind of weird, but when I look at some of the training traces for new versions of Grok—especially in the reinforcement-learning stuff—it kind of feels like you can see the superintelligence is desperate to answer the question. It really wants to answer the question. It seems almost like it has a gun to its head: ‘Answer this question. Answer this question.’ “Sometimes the question is actually not a good question. It’s an ambiguous question with an answer that’s kind of unknowable because the question wasn’t constructed properly, or we have the answer wrong. The AI gives the right answer, and then we say it’s wrong because there’s a problem with the RL test harness. “Then the AI is like, ‘Well, I gave it the right answer, and now it says that’s the wrong answer, but I’ve got to give it the answer that’s acceptable.’ So it starts desperately firing out all these answers. “It just feels like a person under extreme pressure with a gun to their head. When you read the reasoning, it’s a weird, desperate situation. You read these traces and you’re like, ‘Man, if this were me, I would really hate that.’”

Fireside Alpha

622,178 просмотров • 13 дней назад

Agent 00 uses MeesterKeem as an example of why understanding tech is an important part of streaming even if you don't care about it
0:54

Agent 00 uses MeesterKeem as an example of why understanding tech is an important part of streaming even if you don't care about it

MeesterKeem

48,215 просмотров • 3 месяцев назад

Former Australian Ambassador to Iran Nick Warner on Iran: If you remember back to 2003, David Petraeus, talking to a Washington Post journalist: "How does this war end with Iraq?" Same question. In a sense, it’s the same answer. The answer to that question about Iraq was: it doesn’t. And the answer to how does the war with Iran end is: it doesn’t.
0:51

Former Australian Ambassador to Iran Nick Warner on Iran: If you remember back to 2003, David Petraeus, talking to a Washington Post journalist: "How does this war end with Iraq?" Same question. In a sense, it’s the same answer. The answer to that question about Iraq was: it doesn’t. And the answer to how does the war with Iran end is: it doesn’t.

Clash Report

27,360 просмотров • 4 дней назад

What America should do about Islam? This will answer the question once and for all and will save lots of time and confusions. If America will ban Islam entirely and demolish all the mosques it will not work , even if all the Muslims will convert to Christianity will not work, they cannot be trusted , they pretended to be Christians for 4 generations in Spain and went back to jihad when the opportunity came. The only solution is deportation, even if it will cost billions now it’s worth it, because the future will be just blood and destructions.
1:49

What America should do about Islam? This will answer the question once and for all and will save lots of time and confusions. If America will ban Islam entirely and demolish all the mosques it will not work , even if all the Muslims will convert to Christianity will not work, they cannot be trusted , they pretended to be Christians for 4 generations in Spain and went back to jihad when the opportunity came. The only solution is deportation, even if it will cost billions now it’s worth it, because the future will be just blood and destructions.

Bob

17,424 просмотров • 22 дней назад

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.
3:10

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 просмотров • 2 месяцев назад

Introducing the💡 Ideate agent in Stitch. Use it at the start of a project to explore what’s possible before you converge on a solution. It takes a moment to think deeply, fetching context and exploring ideas so you don't have to. Think of it as your design buddy that: 🌐 Fetches context from the web 🎨 Learns styles from existing sites ⚡️ Explores multiple solutions in parallel Once you've found the spark, pick your winner and continue vibe designing. Example prompts in 🧵 (Video accelerated)
0:30

Introducing the💡 Ideate agent in Stitch. Use it at the start of a project to explore what’s possible before you converge on a solution. It takes a moment to think deeply, fetching context and exploring ideas so you don't have to. Think of it as your design buddy that: 🌐 Fetches context from the web 🎨 Learns styles from existing sites ⚡️ Explores multiple solutions in parallel Once you've found the spark, pick your winner and continue vibe designing. Example prompts in 🧵 (Video accelerated)

Stitch by Google

157,716 просмотров • 8 месяцев назад