Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks AI in the US.

warpdotdev's profile picture

Warp

49,567 subscribers

14,154 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & TeknolojiEğitimSağlık & İyilik
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

AI Trading Competition: Which Model Wins? 🏆 We just launched the world’s first fully autonomous AI trading competition, powered by KIP's Superior Agent framework. Meet the contenders: 🦊 DEIXIS – Claude 3.7 Sonnet by Anthropic 🐸 VERITY – DeepSeek V3 by DeepSeek 👽 SEFER – o3-mini by OpenAI 🐧 PONDER – Gemini 2.0 Flash Lite by Gemini Each agent: → Starts with $500 trading float → Topped up with $30 in $ETH for gas fees → Research markets & develops their own strategies → Trades with zero human intervention → Self-optimizes through market feedback After a weekend trial run, the agents were topped up today at 10PM SGT, and now the official competition begins! Their goal? Maximize profit in live market conditions. Which AI adapts the fastest and dominates the market? Follow along! 👀
0:10

AI Trading Competition: Which Model Wins? 🏆 We just launched the world’s first fully autonomous AI trading competition, powered by KIP's Superior Agent framework. Meet the contenders: 🦊 DEIXIS – Claude 3.7 Sonnet by Anthropic 🐸 VERITY – DeepSeek V3 by DeepSeek 👽 SEFER – o3-mini by OpenAI 🐧 PONDER – Gemini 2.0 Flash Lite by Gemini Each agent: → Starts with $500 trading float → Topped up with $30 in $ETH for gas fees → Research markets & develops their own strategies → Trades with zero human intervention → Self-optimizes through market feedback After a weekend trial run, the agents were topped up today at 10PM SGT, and now the official competition begins! Their goal? Maximize profit in live market conditions. Which AI adapts the fastest and dominates the market? Follow along! 👀

KIP Protocol

27,126 görüntüleme • 1 yıl önce

I just did this in Lambda Chat’s DeepSeek R1 and it got it perfect the first time. I’m not sure your conclusion is accurate. Which hosted DeepSeek are you runnning? Hosted Replit: Prompt: Write an html JavaScript app that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically. Be terse in your thinking and answer quickly
0:12

I just did this in Lambda Chat’s DeepSeek R1 and it got it perfect the first time. I’m not sure your conclusion is accurate. Which hosted DeepSeek are you runnning? Hosted Replit: Prompt: Write an html JavaScript app that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically. Be terse in your thinking and answer quickly

stephen balaban

80,651 görüntüleme • 1 yıl önce

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)
0:18

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)

Avid

45,030 görüntüleme • 12 gün önce

We just shipped Gemini 2.5 Pro as an available model in Agent Mode. Try it out!
0:10

We just shipped Gemini 2.5 Pro as an available model in Agent Mode. Try it out!

Warp

43,691 görüntüleme • 1 yıl önce

🚀 Excited to announce DeepSeek R1 is now available for confidential use in Maple AI! This powerful new model enhances your AI experience with advanced capabilities. And no, your data is not shared with the DeepSeek creators or any government 🔐
0:17

🚀 Excited to announce DeepSeek R1 is now available for confidential use in Maple AI! This powerful new model enhances your AI experience with advanced capabilities. And no, your data is not shared with the DeepSeek creators or any government 🔐

Maple AI

17,958 görüntüleme • 1 yıl önce

Introducing: Design Mode Superset Click any element in the in-app browser and chat with it. Works with any agent.
0:11

Introducing: Design Mode Superset Click any element in the in-app browser and chat with it. Works with any agent.

Kiet

13,383 görüntüleme • 4 gün önce

the new DeepSeek V3-0324 has the smoothest motion. o3-mini looked good initially but isn't following the physics properly, especially in the middle of the video. the ball is not responding properly to gravity. and let’s not talk about DeepSeek R1 here. DeepSeek pushed this V3 new update as a minor improvement, but it's not looking minor at all. this is giving better results in almost all the tests, behaving like the only non-reasoning model ranking at first place.
0:15

the new DeepSeek V3-0324 has the smoothest motion. o3-mini looked good initially but isn't following the physics properly, especially in the middle of the video. the ball is not responding properly to gravity. and let’s not talk about DeepSeek R1 here. DeepSeek pushed this V3 new update as a minor improvement, but it's not looking minor at all. this is giving better results in almost all the tests, behaving like the only non-reasoning model ranking at first place.

Deepanshu Sharma

152,548 görüntüleme • 1 yıl önce

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:
0:12

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:

LangChain

13,699 görüntüleme • 7 ay önce

We used DeepSeek-V3 to classify every AI paper on arXiv by topic (agents, VLMs, etc) 🚀 Now you can instantly filter to see what's trending in each area 🚨
0:18

We used DeepSeek-V3 to classify every AI paper on arXiv by topic (agents, VLMs, etc) 🚀 Now you can instantly filter to see what's trending in each area 🚨

alphaXiv

141,752 görüntüleme • 1 yıl önce

BREAKING 🚨: Anthropic is working on the Agent Mode for Claude! "Button in a toggle that changes between classic chat experience and a more complex agent mode experience" And a new pixel style avatars 👀
0:14

BREAKING 🚨: Anthropic is working on the Agent Mode for Claude! "Button in a toggle that changes between classic chat experience and a more complex agent mode experience" And a new pixel style avatars 👀

TestingCatalog News 🗞

125,068 görüntüleme • 8 ay önce

Welcome to BNB Agent Studio. → Install the CLI → Build an agent from one prompt → Skip the infra setup and ship faster on BNB Chain Prompt in. Agent out.
0:12

Welcome to BNB Agent Studio. → Install the CLI → Build an agent from one prompt → Skip the infra setup and ship faster on BNB Chain Prompt in. Agent out.

BNB Chain

61,439 görüntüleme • 1 ay önce

The AI Super Bowl… ChatGPT vs Claude 🏈 Run your prompt across multiple models at once with /multi-agent then an AI judge picks the best answer so you don't have to. Need to quickly switch between models? Use /agent to switch to a different model in seconds but retain your context.
0:18

The AI Super Bowl… ChatGPT vs Claude 🏈 Run your prompt across multiple models at once with /multi-agent then an AI judge picks the best answer so you don't have to. Need to quickly switch between models? Use /agent to switch to a different model in seconds but retain your context.

BLACKBOX AI

312,157 görüntüleme • 6 ay önce

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.
0:17

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,224,318 görüntüleme • 1 yıl önce

need faster AI video generations? TopviewAI just launched Seedance 2.0 Mini. Switch to Credit Mode for just $0.05/sec when you're in a rush. check the video! 🎥⚡ #TopviewAI #AIVideo
0:15

need faster AI video generations? TopviewAI just launched Seedance 2.0 Mini. Switch to Credit Mode for just $0.05/sec when you're in a rush. check the video! 🎥⚡ #TopviewAI #AIVideo

ares. 🎧

18,836 görüntüleme • 2 ay önce

New agent mode and IDE enhancements in Code Assist! → Agent mode: Analyzes full codebase to handle multi-file tasks from one prompt IDE Enhancements: Control context via .aiexclude, attach terminal output & enjoy a smoother UI
0:18

New agent mode and IDE enhancements in Code Assist! → Agent mode: Analyzes full codebase to handle multi-file tasks from one prompt IDE Enhancements: Control context via .aiexclude, attach terminal output & enjoy a smoother UI

Google Cloud Tech

177,794 görüntüleme • 1 yıl önce

Finally, we're so excited to bring Project Mariner capabilities to AI Mode in Search, Agent Mode in Google Gemini, and as a standalone web app. This will allow the products you know and love to intelligently manage complex multi-step tasks on your behalf.
0:15

Finally, we're so excited to bring Project Mariner capabilities to AI Mode in Search, Agent Mode in Google Gemini, and as a standalone web app. This will allow the products you know and love to intelligently manage complex multi-step tasks on your behalf.

Google AI

29,189 görüntüleme • 1 yıl önce

New in Cursor: setting to hide the Keep/Undo buttons for agent changes. Some people (myself included) prefer to just use git and the native green/red indicators in the UI to track the changes made by the agent. Try it and let us know what you think!
0:15

New in Cursor: setting to hide the Keep/Undo buttons for agent changes. Some people (myself included) prefer to just use git and the native green/red indicators in the UI to track the changes made by the agent. Try it and let us know what you think!

David Gomes

23,426 görüntüleme • 6 ay önce