Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Hybrid models efficiently route complex tasks to larger cloud models, but how do you go about creating one? 🤔 Cactus solved this by post-training Gemma 4 to return a confidence score for every prompt. Process the prompt locally when confidence is high, route to a larger model when confidence... show more

Google Gemma

95,710 subscribers

24,618 views • 13 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Aiswarya Sankar

81,455 views • 26 days ago

A lot of men confuse online boldness with real confidence. But those are not the same thing. If a man only feels expressive when he is anonymous, distant, or protected by a screen, that is not solid confidence. That is borrowed boldness. Real confidence does not need hiding to exist. Real confidence can stay grounded in real time. Real confidence does not collapse into every urge. And that is what many men are actually hungry for. Not just relief. Not just expression. Not just another place to dump tension. They want to feel steady. Natural. Calm. More in command of themselves. That is what the full YouTube video is really about.

A lot of men confuse online boldness with real confidence. But those are not the same thing. If a man only feels expressive when he is anonymous, distant, or protected by a screen, that is not solid confidence. That is borrowed boldness. Real confidence does not need hiding to exist. Real confidence can stay grounded in real time. Real confidence does not collapse into every urge. And that is what many men are actually hungry for. Not just relief. Not just expression. Not just another place to dump tension. They want to feel steady. Natural. Calm. More in command of themselves. That is what the full YouTube video is really about.

Command Within | Build Self-Command

25,719 views • 4 months ago

David Sacks on How Anthropic is Ironically Running Surveillance on Their Latest Models “This is the company that said that it was against government surveillance. They are now retaining for 30 days every prompt and every output you send to one of these Mythos class models.”

David Sacks on How Anthropic is Ironically Running Surveillance on Their Latest Models “This is the company that said that it was against government surveillance. They are now retaining for 30 days every prompt and every output you send to one of these Mythos class models.”

Chief Nerd

277,546 views • 1 month ago

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

340,097 views • 5 months ago

Qullamaggie on Discipline vs. Confidence in Trading "It's not a discipline problem; it's a confidence problem, guys. Discipline is the most overused word in trading. It's never a discipline problem; it's a confidence problem because you haven't put in enough effort to build your confidence. If you study enough, you will build confidence. How many of you have spent 500 hours studying one specific setup, like thousands of historical examples? Be honest; there's maybe I don't know 5% of you. The rest of you haven't put in any effort to build confidence, and that's why these things happen. You have no confidence holding for a big move. You get shaken out on one downtick. You have no confidence because you haven't built it. Most people do all they do is put on some random trades because they haven't internalized the setups yet, and that’s why they all do these random things. They promise to use the 10-day moving average as a trailing stop, then one downtick happens and they're out. We see it daily; people who are struggling to follow the rules. It happens to me too, but it happens less. You got to do both; you got to study hard. You got to out study most people, and you got to combine it with experience.”

Qullamaggie on Discipline vs. Confidence in Trading "It's not a discipline problem; it's a confidence problem, guys. Discipline is the most overused word in trading. It's never a discipline problem; it's a confidence problem because you haven't put in enough effort to build your confidence. If you study enough, you will build confidence. How many of you have spent 500 hours studying one specific setup, like thousands of historical examples? Be honest; there's maybe I don't know 5% of you. The rest of you haven't put in any effort to build confidence, and that's why these things happen. You have no confidence holding for a big move. You get shaken out on one downtick. You have no confidence because you haven't built it. Most people do all they do is put on some random trades because they haven't internalized the setups yet, and that’s why they all do these random things. They promise to use the 10-day moving average as a trailing stop, then one downtick happens and they're out. We see it daily; people who are struggling to follow the rules. It happens to me too, but it happens less. You got to do both; you got to study hard. You got to out study most people, and you got to combine it with experience.”

Lone

20,681 views • 1 year ago

We live on the remains of a much larger past. It is hard for the ant to have perspective of the much larger world it is a part of when it only sees what’s right in front of it. We are the ants, most are oblivious to how much larger beyond the ant hill this world of ours is.

We live on the remains of a much larger past. It is hard for the ant to have perspective of the much larger world it is a part of when it only sees what’s right in front of it. We are the ants, most are oblivious to how much larger beyond the ant hill this world of ours is.

The Improbable Dreamer

13,989 views • 1 year ago

OpenAI just killed the idea of one best model. GPT-5.6 is three different jobs: - Sol for hard reasoning and long agent runs - Terra for everyday work - Luna for cheap high-volume tasks Most people will send every prompt to Sol, then complain about the cost. The edge is not having the flagship. It is knowing when you do not need it.

OpenAI just killed the idea of one best model. GPT-5.6 is three different jobs: - Sol for hard reasoning and long agent runs - Terra for everyday work - Luna for cheap high-volume tasks Most people will send every prompt to Sol, then complain about the cost. The edge is not having the flagship. It is knowing when you do not need it.

Fluixo

12,641 views • 1 month ago

"The problem with the Strait of #Hormuz is really not a military one. It is one of markets, shipping and insurance, and their confidence that passage through the Strait is safe. All Iran needs to do is fire a missile or drone from time to time to undermine this confidence. This confidence cannot be restored by the military but only through diplomacy. We have a number states coming forward now trying to open a backchannel with Iran to negotiate free passage through the Strait. We will see a gradual opening of the Strait for some countries who have agreements in place with the Iranians possibly brokered by Oman. My prediction would be that the US with a military-only President would be one of the last countries to get a free passage."

"The problem with the Strait of #Hormuz is really not a military one. It is one of markets, shipping and insurance, and their confidence that passage through the Strait is safe. All Iran needs to do is fire a missile or drone from time to time to undermine this confidence. This confidence cannot be restored by the military but only through diplomacy. We have a number states coming forward now trying to open a backchannel with Iran to negotiate free passage through the Strait. We will see a gradual opening of the Strait for some countries who have agreements in place with the Iranians possibly brokered by Oman. My prediction would be that the US with a military-only President would be one of the last countries to get a free passage."

Dr Andreas Krieg

30,224 views • 4 months ago

"Why are you asking about Party Politics only, ask about Development" Rare moment in Indian politics when a politician is ready to take question on development. That's the confidence of Mahayuti Government

"Why are you asking about Party Politics only, ask about Development" Rare moment in Indian politics when a politician is ready to take question on development. That's the confidence of Mahayuti Government

Facts

28,298 views • 11 months ago

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Inferium

12,332 views • 1 year ago

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a go! Video is 38min long, so you will need some time to watch that haha.

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a go! Video is 38min long, so you will need some time to watch that haha.

dome | Outlier

54,581 views • 1 year ago

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

Martin Nebelong

88,080 views • 2 years ago

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 views • 2 years ago

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:

Givros

14,794 views • 16 days ago

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 views • 2 years ago

Anthropic engineer: "Fable is one of those models you’ll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. We just removed 80% of Claude Code’s system prompt. A new class of models wants a smaller prompt." in 20-minute session, an Anthropic core engineer reveals the capabilities of Fable. Watch it now, then read how to use this frontier model in the article below.

Anthropic engineer: "Fable is one of those models you’ll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. We just removed 80% of Claude Code’s system prompt. A new class of models wants a smaller prompt." in 20-minute session, an Anthropic core engineer reveals the capabilities of Fable. Watch it now, then read how to use this frontier model in the article below.

Movez

550,433 views • 1 month ago

Mark Manson has a brutally simple way to spot a narcissist. On Raj Shamani’s podcast, he explained that narcissism isn’t real confidence — it’s fake confidence built on deep insecurity. Narcissists look confident to people who doubt themselves, but the difference becomes obvious when you disagree with them or tell them “no.” A narcissist will belittle you, argue, call you stupid, or refuse to accept it. A truly confident person will say “okay, let’s talk about it,” admit when they’re wrong, or even thank you for the feedback. This one is gold because it’s such an easy test that actually works in real life. Once you see it, you can’t unsee it. In a world full of loud voices and performative confidence, knowing how to tell the difference protects your time, energy, and peace. How do you spot the difference between real confidence and narcissism in people?

Mark Manson has a brutally simple way to spot a narcissist. On Raj Shamani’s podcast, he explained that narcissism isn’t real confidence — it’s fake confidence built on deep insecurity. Narcissists look confident to people who doubt themselves, but the difference becomes obvious when you disagree with them or tell them “no.” A narcissist will belittle you, argue, call you stupid, or refuse to accept it. A truly confident person will say “okay, let’s talk about it,” admit when they’re wrong, or even thank you for the feedback. This one is gold because it’s such an easy test that actually works in real life. Once you see it, you can’t unsee it. In a world full of loud voices and performative confidence, knowing how to tell the difference protects your time, energy, and peace. How do you spot the difference between real confidence and narcissism in people?

Camus

96,410 views • 3 months ago

Tom Brady says a sports psychologist at Michigan told him to 'quit bitching' “'Stop worrying about what the other quarterback's getting, stop worrying about what the coach is saying to you. Every time you get in there, you bring the juice. You bring the energy. You bring the enthusiasm. You treat practice like a game.'” “I started to change my attitude and I didn't have a lot of confidence in myself. And when you don't have a lot of confidence in yourself, you blame other people.” “And then all of a sudden when you gain confidence in yourself, you start pointing the finger at yourself. I would encourage every athlete to look in the mirror after every day of practice, of game, and say, 'What can I do better to help the team?'”

Tom Brady says a sports psychologist at Michigan told him to 'quit bitching' “'Stop worrying about what the other quarterback's getting, stop worrying about what the coach is saying to you. Every time you get in there, you bring the juice. You bring the energy. You bring the enthusiasm. You treat practice like a game.'” “I started to change my attitude and I didn't have a lot of confidence in myself. And when you don't have a lot of confidence in yourself, you blame other people.” “And then all of a sudden when you gain confidence in yourself, you start pointing the finger at yourself. I would encourage every athlete to look in the mirror after every day of practice, of game, and say, 'What can I do better to help the team?'”

Hribi

150,644 views • 26 days ago