正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

98% users are still wasting time switching between ChatGPT, Gemini, Claude, DeepSeek, and Grok just to compare answers. Today I tried TantyAI after a friend suggested it, and wow… With just one prompt, you get access to all the models and answers side-by-side. Thanks to the team for letting... show more

Shruti

178,501 subscribers

22,202 次观看 • 10 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I just tried Grok Build for the first time and it’s incredibly good. After just one prompt and 91 seconds, Grok Build created a complete website for me and it looks great.

I just tried Grok Build for the first time and it’s incredibly good. After just one prompt and 91 seconds, Grok Build created a complete website for me and it looks great.

Testlabor

23,625 次观看 • 27 天前

ChatGPT generates fake references to papers that don't even exist even if connected to the internet. So, we built It helps you integrate ChatGPT, Claude, and Gemini with academic databases so you get answers with real, published papers. Tutorial:

ChatGPT generates fake references to papers that don't even exist even if connected to the internet. So, we built It helps you integrate ChatGPT, Claude, and Gemini with academic databases so you get answers with real, published papers. Tutorial:

Mushtaq Bilal, PhD

134,617 次观看 • 1 年前

Serno just dropped and it's the first AI tool that doesn't feel like a chatbot. It's a canvas. With a team of expert personas. Who debate before they answer you. Claude, GPT, and Gemini all run the same question side by side. Here's how to use it: 👇

Serno just dropped and it's the first AI tool that doesn't feel like a chatbot. It's a canvas. With a team of expert personas. Who debate before they answer you. Claude, GPT, and Gemini all run the same question side by side. Here's how to use it: 👇

Hasan Toor

66,443 次观看 • 1 个月前

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

Ethan Mollick

137,392 次观看 • 1 年前

In 2023, Sam Altman said to Indian Engineers: "It is totally hopeless to compete with us in building foundational models". Today: India build one of the Best LLM Model for Indian Language just in one year. It is 5 times better than ChatGpt, Gemini and Grok. Thanks Sarvam

In 2023, Sam Altman said to Indian Engineers: "It is totally hopeless to compete with us in building foundational models". Today: India build one of the Best LLM Model for Indian Language just in one year. It is 5 times better than ChatGpt, Gemini and Grok. Thanks Sarvam

Farrago Abdullah Parody

19,711 次观看 • 4 个月前

Open “Ask ChatGPT” and ChatGPT can see the page you’re on to give instant, accurate answers—no tab-switching required.

Open “Ask ChatGPT” and ChatGPT can see the page you’re on to give instant, accurate answers—no tab-switching required.

OpenAI

256,863 次观看 • 8 个月前

The "best AI model" keeps changing. ChatGPT → Claude → Gemini → Grok → repeat. I've been hopping between them constantly. And every single time I switch, I'm back to square one — re-explaining who I am, what I'm building, and what we already covered. There has to be a better way. 🧵

The "best AI model" keeps changing. ChatGPT → Claude → Gemini → Grok → repeat. I've been hopping between them constantly. And every single time I switch, I'm back to square one — re-explaining who I am, what I'm building, and what we already covered. There has to be a better way. 🧵

Manish Kumar Shah

56,084 次观看 • 18 天前

here's a side by side comparison of a ray-tracing simulator by gpt-5 and claude 4.1 (opus) gpt-5 one-shotted this. claude genuinely blew me away with how badly it failed (and you all know how much i like claude)

here's a side by side comparison of a ray-tracing simulator by gpt-5 and claude 4.1 (opus) gpt-5 one-shotted this. claude genuinely blew me away with how badly it failed (and you all know how much i like claude)

Riley Coyote

42,687 次观看 • 10 个月前

This is the one prompt that stops AI from gaslighting you. Force AI to tell the truth. No sugarcoating. No hallucinations. No fake confidence. Brutally honest answers. Every time. I packaged my reality filter prompt into a plug-and-play guide To get it, just: → Comment “REALITY” → Follow me (so I can DM)

This is the one prompt that stops AI from gaslighting you. Force AI to tell the truth. No sugarcoating. No hallucinations. No fake confidence. Brutally honest answers. Every time. I packaged my reality filter prompt into a plug-and-play guide To get it, just: → Comment “REALITY” → Follow me (so I can DM)

Charlie Hills

336,947 次观看 • 4 个月前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 3 个月前

“It was always just about me. I was looking for answers in somebody else, but I had all the answers. I just needed to stop being so goddamn scared.”

“It was always just about me. I was looking for answers in somebody else, but I had all the answers. I just needed to stop being so goddamn scared.”

valeria ⚓︎ st5 spoilers

177,013 次观看 • 6 个月前

❄️I’M A FAST LEARER! ❄️With grok imagine I saved so much time and money in figure skating lessons. I quickly became the world’s best ice skater after just a few hours. Now people are telling me to participate in the Winter Olympics. It is in February but with my insane progress it’s probable that I’ll get first. I’ll consider it!

❄️I’M A FAST LEARER! ❄️With grok imagine I saved so much time and money in figure skating lessons. I quickly became the world’s best ice skater after just a few hours. Now people are telling me to participate in the Winter Olympics. It is in February but with my insane progress it’s probable that I’ll get first. I’ll consider it!

Angela Rose

20,765 次观看 • 5 个月前

Respan Launch Week, Day 2: Evals Evals are one of the hardest parts of building AI applications. It is not because teams cannot run them. It is because they are hard to structure, hard to compare, and even harder to improve over time. So teams end up guessing. Did this prompt actually get better? Is this model really an improvement? We built Evals in Respan to make this systematic. You define: - what you want to test, such as prompts, models, or configs - the dataset, from production logs or test cases - the evaluators, whether LLM, code, human, or a mix Then you run experiments and compare results side by side. Same inputs. Same evaluation. Clear answers. No more guessing. Start running your first eval.

Respan Launch Week, Day 2: Evals Evals are one of the hardest parts of building AI applications. It is not because teams cannot run them. It is because they are hard to structure, hard to compare, and even harder to improve over time. So teams end up guessing. Did this prompt actually get better? Is this model really an improvement? We built Evals in Respan to make this systematic. You define: - what you want to test, such as prompts, models, or configs - the dataset, from production logs or test cases - the evaluators, whether LLM, code, human, or a mix Then you run experiments and compare results side by side. Same inputs. Same evaluation. Clear answers. No more guessing. Start running your first eval.

Respan

127,602 次观看 • 2 个月前

Tested DeepSeek V4 Flash on ZenMux today Tried a more practical approach instead of just chatting. → Asked it to build a SaaS landing page → Generated full HTML, CSS, JS → Ran the code → got a working UI It handled layout, components, and styling pretty smoothly. Iteration was simple too — just refine the prompt and improve the output. Also liked how easy it is to switch between models in the same place and test things side by side without changing setups. What stood out is how quickly you can go from idea → working frontend without jumping between tools. From a cost perspective, this kind of output is more than enough for a lot of routine dev tasks. Feels less like a “Claude killer” More like a “Claude bill killer.” If you want to try it yourself, I’ve added the link below 👇 Try it here: ZenMux

Tested DeepSeek V4 Flash on ZenMux today Tried a more practical approach instead of just chatting. → Asked it to build a SaaS landing page → Generated full HTML, CSS, JS → Ran the code → got a working UI It handled layout, components, and styling pretty smoothly. Iteration was simple too — just refine the prompt and improve the output. Also liked how easy it is to switch between models in the same place and test things side by side without changing setups. What stood out is how quickly you can go from idea → working frontend without jumping between tools. From a cost perspective, this kind of output is more than enough for a lot of routine dev tasks. Feels less like a “Claude killer” More like a “Claude bill killer.” If you want to try it yourself, I’ve added the link below 👇 Try it here: ZenMux

Shruti Codes

68,739 次观看 • 1 个月前

ChatGPT got killed off by China’s version, DeepSeek? I tried it out to test its performance, output with technical knowledge and if it hallucinates with citations (as ChatGPT does). Here’s a 90 second test & review for academic use. Let me know your thoughts!

ChatGPT got killed off by China’s version, DeepSeek? I tried it out to test its performance, output with technical knowledge and if it hallucinates with citations (as ChatGPT does). Here’s a 90 second test & review for academic use. Let me know your thoughts!

Amina Yonis, PhD

26,504 次观看 • 1 年前

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season

Magnific

34,312 次观看 • 4 个月前

This AI is wild. Yupp AI just unlocked 500+ AI models side-by-side🤯 Pick the best response, earn credits. ChatGPT, Claude, Gemini, Grok & more. FREE. 8 wild examples + prompts: 1. Image generation models

This AI is wild. Yupp AI just unlocked 500+ AI models side-by-side🤯 Pick the best response, earn credits. ChatGPT, Claude, Gemini, Grok & more. FREE. 8 wild examples + prompts: 1. Image generation models

Min Choi

117,568 次观看 • 11 个月前

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Daniel San

28,410 次观看 • 11 个月前

Love this example! Congrats to Google DeepMind! I successfully replicated the Boggle game on SWE Arena. TLDR: Gemini 2.0 Pro won! In the case of Claude 3.5 Sonnet vs Gemini 2.0 Pro, both are given the image and prompt to generate the algo to get the results. The image and prompt are exactly the same. Try it out on SWE Arena: BTW can we get a bigger streaming rate limit for our API, so that ppl can better compare the latest Gemini models with other frontier models? Jeff Dean Logan Kilpatrick 👀

Love this example! Congrats to Google DeepMind! I successfully replicated the Boggle game on SWE Arena. TLDR: Gemini 2.0 Pro won! In the case of Claude 3.5 Sonnet vs Gemini 2.0 Pro, both are given the image and prompt to generate the algo to get the results. The image and prompt are exactly the same. Try it out on SWE Arena: BTW can we get a bigger streaming rate limit for our API, so that ppl can better compare the latest Gemini models with other frontier models? Jeff Dean Logan Kilpatrick 👀

Terry Yue Zhuo

48,220 次观看 • 1 年前

The one and only kim petras❤️ Thank you baby for being by my side and closing this residency with me. I love you so much!! Here’s to the next one…

The one and only kim petras❤️ Thank you baby for being by my side and closing this residency with me. I love you so much!! Here’s to the next one…

SAM SMITH

25,416 次观看 • 3 个月前