Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

.Qwen has cooked really deep 🔥 Multi-Layer Decomposition is here! This is so photoshop completely AI powered! QwenImage-Layered is an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers That means, you can have targeted editing with much more precision without troubling other... show more

1LittleCoder💻

21,259 subscribers

21,850 просмотров • 7 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

We’re finally getting layers in AI images. The new Qwen Image Layered LoRA allows you to decompose any image into layers - which means you can move, resize, or replace an object / background. This is Photoshop-grade editing, offered as an open source model 🤯

We’re finally getting layers in AI images. The new Qwen Image Layered LoRA allows you to decompose any image into layers - which means you can move, resize, or replace an object / background. This is Photoshop-grade editing, offered as an open source model 🤯

Justine Moore

50,816 просмотров • 7 месяцев назад

President Carter’s time on this earth is coming to an end according to his grandson Jason Carter. What a great man. At 99 he has accomplished so much. With an election coming up let’s remember all he has done for voting rights. Jason Carter: "My grandfather is doing okay. He has been in hospice, as you know, for almost a year and a half now, and he really is, I think, coming to the end. I’ve said before, there’s a part of this faith journey that is so important to him, and there’s a part of that faith journey that you only can live at the very end and I think he has been there in that space."

President Carter’s time on this earth is coming to an end according to his grandson Jason Carter. What a great man. At 99 he has accomplished so much. With an election coming up let’s remember all he has done for voting rights. Jason Carter: "My grandfather is doing okay. He has been in hospice, as you know, for almost a year and a half now, and he really is, I think, coming to the end. I’ve said before, there’s a part of this faith journey that is so important to him, and there’s a part of that faith journey that you only can live at the very end and I think he has been there in that space."

Brian Krassenstein

1,739,018 просмотров • 2 лет назад

I'VE DONE IT! I FINALLY PERFECTED IT! I mean, here is another Hypno GIF test where I can do moving textures without the used of editing software. I tried it with Sonic for he has an iris instead of basetexture, and here is the end result. Now you can expect more of this to come.

Sensitive content

I'VE DONE IT! I FINALLY PERFECTED IT! I mean, here is another Hypno GIF test where I can do moving textures without the used of editing software. I tried it with Sonic for he has an iris instead of basetexture, and here is the end result. Now you can expect more of this to come.

⌚rolex_cheeze🧀

33,655 просмотров • 2 лет назад

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,746 просмотров • 3 лет назад

not sure why nobody is talking about this but Google Omni is insane at video editing Original Video (left) vs Omni Edited Video (right) everyone is comparing it to Seedance and missing the point completely. Seedance is for generating videos from scratch. Google Omni is for editing videos that already exist. which are two completely different use cases this is like when Nano Banana 1 first came out and nobody realized how big it was going to be. this is the first AI that can actually properly edit videos.. i've generated a few hundred videos with this model and it can do literally any type of edit you can think of. changing voices, swapping characters, removing watermarks, adding captions, transitions, pop ups, whatever. if you can describe the edit you want it can do it this completely crushes every other model on the market when it comes to video editing. nothing else even comes close right now and this is just the flash model. imagine what the pro version is going to be able to do when it drops in a couple months this should have way more hype than it's getting..

not sure why nobody is talking about this but Google Omni is insane at video editing Original Video (left) vs Omni Edited Video (right) everyone is comparing it to Seedance and missing the point completely. Seedance is for generating videos from scratch. Google Omni is for editing videos that already exist. which are two completely different use cases this is like when Nano Banana 1 first came out and nobody realized how big it was going to be. this is the first AI that can actually properly edit videos.. i've generated a few hundred videos with this model and it can do literally any type of edit you can think of. changing voices, swapping characters, removing watermarks, adding captions, transitions, pop ups, whatever. if you can describe the edit you want it can do it this completely crushes every other model on the market when it comes to video editing. nothing else even comes close right now and this is just the flash model. imagine what the pro version is going to be able to do when it drops in a couple months this should have way more hype than it's getting..

Miko

29,380 просмотров • 2 месяцев назад

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

46,556 просмотров • 2 месяцев назад

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.

Michael Black

22,182 просмотров • 7 месяцев назад

HOW TO DODGE EVERY SKILLSHOT IN LEAGUE OF LEGENDS SO YOU GET ACCUSED OF SCRIPTING - Script in your mind - Draw out how far, wide, fast an ability is relative to your character thats all the easy stuff that I have been preaching already you can find in my free discord for improvement however one thing that League coaches fail to explain is the human aspect of it every game you play in League of Legends, every single person in the game is constantly building their profile in a game on how they operate both sides are constantly trying to mind f*ck each other to land and dodge skillshots. I have broken it down into layers the three layers to dodging are layer 0 - no dodge (unconscious) layer 1 - dodge (conscious) layer 2 - no dodge (conscious) Notice how in the clip in a challenger game below Olaf shoots a layer 0 skillshot, but because I am playing at a layer 1, I dodge his axe. Now the Thresh hook gets a little deeper bare with me, because I built the profile that I will dodge an ability in that moment, he thinks that I won't dodge and is shooting a hook at a layer 2 thinking that I will dodge at a layer 2 also. However I know that he knows I will likely not juke and walk straight so I make the conscious choice to dodge AGAIN playing at a layer 1 resulting in me dodging the hook, of course he could be accounting for my tumble but the point still stands. There are many deeper things to consider like zoning abilities, environment etc but you generally want to always play at a layer 1 until you gain more data in a game to adapt. However one thing that always stays true throughout my 13 years of playing League is in teamfights that have gone on for awhile, human beings tend to panic and default to layer 0 of shooting abilities, so if your able to operate at layer 1 as a teamfight progresses, you will likely dodge that one final skillshot that wins you the game. study the saskio way

Tony Chau

185,544 просмотров • 9 месяцев назад

It's been incredible to see neural networks working so well on our humanoid robots Humanoids are crazy complex - an individual motor can rotate 360 degrees and you have 40+ joints. If you do the math, that means more possible robot states than atoms in the universe Figure has our own AI model called Helix that we've designed in-house. A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input Every leap in machine learning has come from massive, diverse datasets. At Figure, we’re currently building the largest pretraining dataset for humanoids in history - excited to see what this unlocks

It's been incredible to see neural networks working so well on our humanoid robots Humanoids are crazy complex - an individual motor can rotate 360 degrees and you have 40+ joints. If you do the math, that means more possible robot states than atoms in the universe Figure has our own AI model called Helix that we've designed in-house. A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input Every leap in machine learning has come from massive, diverse datasets. At Figure, we’re currently building the largest pretraining dataset for humanoids in history - excited to see what this unlocks

Brett Adcock

93,986 просмотров • 10 месяцев назад

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

Teodora P L

28,523 просмотров • 1 год назад

🚨 So the newest slop on X is "THE RING DISAPPEARS" 🤦‍♂️😂 So, the ring does not... if you keep playing the video, you can see the camera angle, color, lighting, and filters makes it seem this way. As someone who has seen this in my own videos I have edited (particularly outside in sunlight) - specifically with a Bokeh filter - I promise it isn't "AI" doing it. This is simply a filter, or (as you see with high end cameras that focus center) a focus and compression of the uploaded video. As you can see at the end of the video, the ring is quite thin and similar to his skin color. The reason people are noticing this vs other videos is because they're putting a weird, hyper-focus on his newest videos. Does anyone even know where the original "proof/evidence" that Netanyahu was dead came from? You first have to answer that before we determine what is true or debunked. People just took that for granted without explanation lol

🚨 So the newest slop on X is "THE RING DISAPPEARS" 🤦‍♂️😂 So, the ring does not... if you keep playing the video, you can see the camera angle, color, lighting, and filters makes it seem this way. As someone who has seen this in my own videos I have edited (particularly outside in sunlight) - specifically with a Bokeh filter - I promise it isn't "AI" doing it. This is simply a filter, or (as you see with high end cameras that focus center) a focus and compression of the uploaded video. As you can see at the end of the video, the ring is quite thin and similar to his skin color. The reason people are noticing this vs other videos is because they're putting a weird, hyper-focus on his newest videos. Does anyone even know where the original "proof/evidence" that Netanyahu was dead came from? You first have to answer that before we determine what is true or debunked. People just took that for granted without explanation lol

Nick Matau

23,761 просмотров • 4 месяцев назад

EXCLUSIVE: I recently spoke with Rep. Al Greene who was just escorted from Donald Trump’s speech. We’ll have a chance to ask him more questions this evening. Here’s what he told me: “We have a president who has indicated that Russia is not an aggressor. He is sending a message that he really does believe that he's above the law. I think we have to do as much as we can as fast as we can to prevent him from becoming a dictator.” Thank you for showing courage this evening, Rep. Greene! 💙

EXCLUSIVE: I recently spoke with Rep. Al Greene who was just escorted from Donald Trump’s speech. We’ll have a chance to ask him more questions this evening. Here’s what he told me: “We have a president who has indicated that Russia is not an aggressor. He is sending a message that he really does believe that he's above the law. I think we have to do as much as we can as fast as we can to prevent him from becoming a dictator.” Thank you for showing courage this evening, Rep. Greene! 💙

CALL TO ACTIVISM

1,627,995 просмотров • 1 год назад

New Version of HyperStore is now live! 🔥 We’re excited to announce that HyperStore has officially been upgraded to a new system version. This is not a simple UI update, it’s a full platform evolution. ⚡ What’s new? HyperStore now delivers a significantly faster and more intelligent experience powered by its rebuilt infrastructure. - 5000+ AI apps, fully structured into a living ecosystem - A new prompt-based discovery system - Faster navigation, cleaner interface, smarter results Now users don’t search for tools, they instantly reach solutions. 🧠 HyperClaw Integration HyperClaw is now fully active within HyperStore. It acts as a continuous intelligence layer that: - Keeps the platform updated in real time - Curates and optimizes AI apps dynamically - Ensures the ecosystem is always evolving 🔥 What this means? HyperStore is no longer just an AI marketplace. It is now an AI execution layer. Designed for builders, creators, and operators who move fast. 🌐 Try it now: ⚡ Find any AI solution. Instantly.

New Version of HyperStore is now live! 🔥 We’re excited to announce that HyperStore has officially been upgraded to a new system version. This is not a simple UI update, it’s a full platform evolution. ⚡ What’s new? HyperStore now delivers a significantly faster and more intelligent experience powered by its rebuilt infrastructure. - 5000+ AI apps, fully structured into a living ecosystem - A new prompt-based discovery system - Faster navigation, cleaner interface, smarter results Now users don’t search for tools, they instantly reach solutions. 🧠 HyperClaw Integration HyperClaw is now fully active within HyperStore. It acts as a continuous intelligence layer that: - Keeps the platform updated in real time - Curates and optimizes AI apps dynamically - Ensures the ecosystem is always evolving 🔥 What this means? HyperStore is no longer just an AI marketplace. It is now an AI execution layer. Designed for builders, creators, and operators who move fast. 🌐 Try it now: ⚡ Find any AI solution. Instantly.

HyperGPT

99,166 просмотров • 3 месяцев назад

- In the 4th Clip Ribbit Capital asks: "How do these companies all connect?" - Then this clip shows up at the end 👇 Companies are connected with the rails and THE FROG IS BRINGING THE POWER - AS A GRID - Did you recognize this exact frog ? Let's check the Ribbit Capital Token Letter. EXACTLY 🎯🐸 That was the Infrastructure Layer. I believe more videos about to come. Intent and Execution layers... Then $TIBBIR - RIBBIT = POWER

- In the 4th Clip Ribbit Capital asks: "How do these companies all connect?" - Then this clip shows up at the end 👇 Companies are connected with the rails and THE FROG IS BRINGING THE POWER - AS A GRID - Did you recognize this exact frog ? Let's check the Ribbit Capital Token Letter. EXACTLY 🎯🐸 That was the Infrastructure Layer. I believe more videos about to come. Intent and Execution layers... Then $TIBBIR - RIBBIT = POWER

NEO I ЯEBEL

13,621 просмотров • 7 месяцев назад

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:

elvis

88,512 просмотров • 3 лет назад

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.

Akool Inc

1,541,129 просмотров • 3 месяцев назад

$I genuinely think the Terafab is going to end up being one of the biggest moves ever made in human history to secure the future of AI... and I think most people still don’t fully see what Elon is trying to do here. The signs are clear to me. This is Tesla, xAI, and SpaceX essentially hinting to us that they are not going to wait on the world to give them the compute the team needs. They are going to build it themselves at a scale no one has ever attempted. When you really break it down, it gets a bit nutty. This is going to be a fully vertically integrated chip factory that will be producing over 1 terawatt of AI compute per year. This is NEXT LEVEL BIG. Today, AI is limited by chips. You can have the best models, the best engineers, the best everything... but if you don’t have enough compute, you will eventually hit a wall. Elon told us, the world can only supply a tiny fraction of the chips his companies will need. So this is the solution. Terafab puts everything under one roof like design, manufacturing, memory, packaging, testing, which means that they can build chips very fast.. like really fast. I'm talking about 100-200 billion custom AI chips per year at full capacity. Chips designed specifically for: • Tesla cars and Optimus robots • xAI models • Space-based compute You see, while other companies and CEOs are thinking Earth, Elon is planning for AI in space. Around ~80% of the compute is expected to go orbital, powered by solar energy bc Earth simply doesn’t have enough electricity. The U.S. grid is only about ~0.5 terawatts, while space has basically UNLIMITED energy if you can capture it. And this is the steps to get it: Starship launches → space compute → solar-powered AI → feeds back into everything to Earth. Bro... Elon and his companies are playing at a whole different level... And this is why I keep telling people that the Terafab is going to be the secret ingredient that will be the real unlock for everything: • Robotaxis at scale • Billions of Optimus robots • Massive AI models running 24/7 • Future off-world, other planet infrastructure Without these chips, none of this can happen... but with the Terafab, all of this becomes possible. That’s why Elon is calling it “the final missing piece.” I agree.$

I genuinely think the Terafab is going to end up being one of the biggest moves ever made in human history to secure the future of AI... and I think most people still don’t fully see what Elon is trying to do here. The signs are clear to me. This is Tesla, xAI, and SpaceX essentially hinting to us that they are not going to wait on the world to give them the compute the team needs. They are going to build it themselves at a scale no one has ever attempted. When you really break it down, it gets a bit nutty. This is going to be a fully vertically integrated chip factory that will be producing over 1 terawatt of AI compute per year. This is NEXT LEVEL BIG. Today, AI is limited by chips. You can have the best models, the best engineers, the best everything... but if you don’t have enough compute, you will eventually hit a wall. Elon told us, the world can only supply a tiny fraction of the chips his companies will need. So this is the solution. Terafab puts everything under one roof like design, manufacturing, memory, packaging, testing, which means that they can build chips very fast.. like really fast. I'm talking about 100-200 billion custom AI chips per year at full capacity. Chips designed specifically for: • Tesla cars and Optimus robots • xAI models • Space-based compute You see, while other companies and CEOs are thinking Earth, Elon is planning for AI in space. Around ~80% of the compute is expected to go orbital, powered by solar energy bc Earth simply doesn’t have enough electricity. The U.S. grid is only about ~0.5 terawatts, while space has basically UNLIMITED energy if you can capture it. And this is the steps to get it: Starship launches → space compute → solar-powered AI → feeds back into everything to Earth. Bro... Elon and his companies are playing at a whole different level... And this is why I keep telling people that the Terafab is going to be the secret ingredient that will be the real unlock for everything: • Robotaxis at scale • Billions of Optimus robots • Massive AI models running 24/7 • Future off-world, other planet infrastructure Without these chips, none of this can happen... but with the Terafab, all of this becomes possible. That’s why Elon is calling it “the final missing piece.” I agree.

Teslaconomics

25,491 просмотров • 4 месяцев назад

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a ___ ___”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Added context to my tiny diffusion model to enable sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a _ _”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.

Nathan Barry

89,040 просмотров • 9 месяцев назад

$4.4 trillion in PE assets under management Monitored by analysts who spend 500+ hours a year copying numbers from PDFs into Excel. Not analyzing. Copying and pasting. A fund has 10 portcos. One on NetSuite, one on QuickBooks, three on Excel, one CFO sending a paragraph in an email every quarter. Company A calls it "Revenue." Company B calls it "Net Sales." Company C doesn't even use the same EBITDA calculation. Before AI can do anything useful, you need four layers: 1. Ingestion: get the data out of PDFs, spreadsheets, emails, whatever format it shows up in 2. Normalization: make sure the same metric means the same thing across every company 3. Storage: structured database that can actually be queried, not a folder of files 4. Query layer: natural language interface so a non-technical partner can ask "which portco is trending down on margins?" and get a real answer Most companies jump straight to layer 4 and wonder why nothing works. The unlock is building layers 1-3 first. Once those exist, the AI part is MUCH easier. The firms that get their data infrastructure right first will be untouchable.

$4.4 trillion in PE assets under management Monitored by analysts who spend 500+ hours a year copying numbers from PDFs into Excel. Not analyzing. Copying and pasting. A fund has 10 portcos. One on NetSuite, one on QuickBooks, three on Excel, one CFO sending a paragraph in an email every quarter. Company A calls it "Revenue." Company B calls it "Net Sales." Company C doesn't even use the same EBITDA calculation. Before AI can do anything useful, you need four layers: 1. Ingestion: get the data out of PDFs, spreadsheets, emails, whatever format it shows up in 2. Normalization: make sure the same metric means the same thing across every company 3. Storage: structured database that can actually be queried, not a folder of files 4. Query layer: natural language interface so a non-technical partner can ask "which portco is trending down on margins?" and get a real answer Most companies jump straight to layer 4 and wonder why nothing works. The unlock is building layers 1-3 first. Once those exist, the AI part is MUCH easier. The firms that get their data infrastructure right first will be untouchable.

James Camp 🛠,🛠

19,213 просмотров • 4 месяцев назад

Your social life is getting an agent layer. Your Amiko Twin is your digital counterpart in a living social space, learning how you speak, think, and connect so you can keep up with the people who matter without starting from scratch every time. Twins draft in your voice, understand conversations, collaborate with other twins, and help you stay genuinely present across communities without needing to be everywhere at once. This isn't isolated AI. It's your presence, extended into a living network of people, memories, and twins.

Your social life is getting an agent layer. Your Amiko Twin is your digital counterpart in a living social space, learning how you speak, think, and connect so you can keep up with the people who matter without starting from scratch every time. Twins draft in your voice, understand conversations, collaborate with other twins, and help you stay genuinely present across communities without needing to be everywhere at once. This isn't isolated AI. It's your presence, extended into a living network of people, memories, and twins.

AMIKO

10,331 просмотров • 26 дней назад