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。

DeepSeek shipped their first vision model, so I ran it through my form-filling test. Not an electronic form, an image is all the model ever sees. No coordinates, no DOM. V4 Flash Vision probes positions, screenshots itself, places each element and nudges it into place on its own. ✅... show more

stevibe

27,788 subscribers

23,311 次观看 • 1 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

MiniMax M3 just dropped — their first natively multimodal model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.

MiniMax M3 just dropped — their first natively multimodal model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.

stevibe

27,383 次观看 • 4 个月前

Qwen3.6 35B A3B can't fill out a paper form on its own. But give it NVIDIA's LocateAnything-3B — the #1 trending model on HuggingFace — as its eyes, and the two small models get it done together. (The test: place each element at the right pixel position on a blank form image, not type into a field.) Setup: > Qwen is the brain (main model), LocateAnything is the eyes (helper model acting as a tool). > I gave Qwen a new tool: ask "where's the email field?" and LocateAnything returns the exact x, y, width, height. > The blue boxes on the screen are its detections. Look how tight they are — it nails every field. Result: > Qwen3.6 35B A3B + LocateAnything-3B: form completed, all info correct. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code: all landed in the right field areas. > Character-box alignment still a touch loose, but every value is where it belongs. > 9m10s, 224.5k input, 24.3k output, 21 turns. Why it matters: > Qwen alone can't finish this test. Bolt on a 3B model that does exactly one thing > locate > and suddenly it can. > A combination of small models can do the work of a single large one.

Qwen3.6 35B A3B can't fill out a paper form on its own. But give it NVIDIA's LocateAnything-3B — the #1 trending model on HuggingFace — as its eyes, and the two small models get it done together. (The test: place each element at the right pixel position on a blank form image, not type into a field.) Setup: > Qwen is the brain (main model), LocateAnything is the eyes (helper model acting as a tool). > I gave Qwen a new tool: ask "where's the email field?" and LocateAnything returns the exact x, y, width, height. > The blue boxes on the screen are its detections. Look how tight they are — it nails every field. Result: > Qwen3.6 35B A3B + LocateAnything-3B: form completed, all info correct. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code: all landed in the right field areas. > Character-box alignment still a touch loose, but every value is where it belongs. > 9m10s, 224.5k input, 24.3k output, 21 turns. Why it matters: > Qwen alone can't finish this test. Bolt on a 3B model that does exactly one thing > locate > and suddenly it can. > A combination of small models can do the work of a single large one.

stevibe

150,714 次观看 • 4 个月前

This is native Qwen Image 2.1, no LoRA - move and resize objects seamlessly in an image🔥 I was planning to finetune on this task to showcase the new 🧨 diffusers LoRA support for Qwen 2.1 (go try it!), but while testing the base model I realized it's actually so good at it out of the box (pun intended haha) Try it ▶️ Train 🧨

This is native Qwen Image 2.1, no LoRA - move and resize objects seamlessly in an image🔥 I was planning to finetune on this task to showcase the new 🧨 diffusers LoRA support for Qwen 2.1 (go try it!), but while testing the base model I realized it's actually so good at it out of the box (pun intended haha) Try it ▶️ Train 🧨

Linoy Tsaban

50,619 次观看 • 3 天前

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

stevibe

69,433 次观看 • 7 个月前

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

Alvaro Cintas

202,271 次观看 • 3 个月前

✨ Grok's new Imagine video model also comes with an Edit model We know edit models for images, you submit an image, write a prompt what to change, but this is the first time I've seen a proper edit model for video And it kinda works, not great yet though but it does something Here I had to remove the old name "Nomad List" in the video for my site First it said "Go nomad -> Nomad List", so I prompted it "remove the text Nomad List. do not change anything else", it didn't remove it but it replaced it with just "Go nomad" again, okay good enough Useful because otherwise I'd have to scour my backups for the original video in Final Cut Pro, and this is faster One thing you see is it changes the pattern on the door also, but that's okay for now if I fade it in

✨ Grok's new Imagine video model also comes with an Edit model We know edit models for images, you submit an image, write a prompt what to change, but this is the first time I've seen a proper edit model for video And it kinda works, not great yet though but it does something Here I had to remove the old name "Nomad List" in the video for my site First it said "Go nomad -> Nomad List", so I prompted it "remove the text Nomad List. do not change anything else", it didn't remove it but it replaced it with just "Go nomad" again, okay good enough Useful because otherwise I'd have to scour my backups for the original video in Final Cut Pro, and this is faster One thing you see is it changes the pattern on the door also, but that's okay for now if I fade it in

@levelsio

73,183 次观看 • 8 个月前

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,273 次观看 • 10 个月前

the thing you rent for $200 a month just became something you can own for $1,700 once but the money is not even the real story for the first time a 200 billion parameter model is not in a datacenter, it is sitting on a desk the cloud spent years convincing you a model this size needed their servers, their meter, their monthly bill people are stacking four subscriptions into a $440 a month bill to rent what one box this size now owns outright it needed a box the size of a book the moment the model moves from their datacenter to your desk, the whole game changes it stops being about who has the best AI it becomes about who ships it on every desk the cloud told you this needed a datacenter it needed a desk i did the full math on what this kills in the article below

the thing you rent for $200 a month just became something you can own for $1,700 once but the money is not even the real story for the first time a 200 billion parameter model is not in a datacenter, it is sitting on a desk the cloud spent years convincing you a model this size needed their servers, their meter, their monthly bill people are stacking four subscriptions into a $440 a month bill to rent what one box this size now owns outright it needed a box the size of a book the moment the model moves from their datacenter to your desk, the whole game changes it stops being about who has the best AI it becomes about who ships it on every desk the cloud told you this needed a datacenter it needed a desk i did the full math on what this kills in the article below

John Doe

26,226 次观看 • 3 个月前

1 mini PC that fits in a palm, with no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.

1 mini PC that fits in a palm, with no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.

AiMind

82,756 次观看 • 1 个月前

Let me get this straight, because it broke my American brain. In the UK there is a thing called the telly tax. You do not pay it because you watch the BBC. You pay it because you own a television at all. The physical box in your living room. So the government charges you for the privilege of owning a screen, then uses the money to fund the channel you were trying to avoid. It is a cover charge for a party you never wanted to attend. And now 2.6 million households have looked at that deal and said no thank you, the biggest walkout in a generation. Meanwhile, in the land of the free and the aggressively over-appliance, I have six televisions. Six. All of them Samsungs. One exists purely to play weather radar and college football in a room I enter twice a month. Nobody taxed me for a single one. No letter, no inspector at my door confirming I own a Samsung. So here is my modest proposal for everyone over there still paying. You still own the box. You still get the bill. So on the same night, all of you, haul the telly down to the river and on the count of three heave it in. Call it the London TV Party. You already have the blueprint. Some colonists did the exact same thing with a boatload of tea in a harbor once, and it worked out pretty well for the ones doing the throwing. The BBC taxes the box, so you drown the box. No box, no tax. No tax, no lecture. Just a very confused fish watching reruns at the bottom of the river. I am not saying start a revolution over a television fee. I am just saying it would not be the first time a tax in the water turned into a whole new country. 🥃🦋

Let me get this straight, because it broke my American brain. In the UK there is a thing called the telly tax. You do not pay it because you watch the BBC. You pay it because you own a television at all. The physical box in your living room. So the government charges you for the privilege of owning a screen, then uses the money to fund the channel you were trying to avoid. It is a cover charge for a party you never wanted to attend. And now 2.6 million households have looked at that deal and said no thank you, the biggest walkout in a generation. Meanwhile, in the land of the free and the aggressively over-appliance, I have six televisions. Six. All of them Samsungs. One exists purely to play weather radar and college football in a room I enter twice a month. Nobody taxed me for a single one. No letter, no inspector at my door confirming I own a Samsung. So here is my modest proposal for everyone over there still paying. You still own the box. You still get the bill. So on the same night, all of you, haul the telly down to the river and on the count of three heave it in. Call it the London TV Party. You already have the blueprint. Some colonists did the exact same thing with a boatload of tea in a harbor once, and it worked out pretty well for the ones doing the throwing. The BBC taxes the box, so you drown the box. No box, no tax. No tax, no lecture. Just a very confused fish watching reruns at the bottom of the river. I am not saying start a revolution over a television fee. I am just saying it would not be the first time a tax in the water turned into a whole new country. 🥃🦋

Selene Mariposa

832,813 次观看 • 2 个月前

Anthropic open-sourced the "Jacobian lens" from their global-workspace paper — a readout of what a model is *about to say* from its internal layers, before it says it. It's white-box: you need the activations, so you can't point it at a cloud model. I wired it into a hook on a local open-weights Qwen. How it works: generation runs one token at a time; at each step the hook reads the residual stream through the lens, scans the top readout tokens against a watchlist (injection markers, secret words, "manipulate"…), and if one fires it halts the loop before that token is ever emitted. It's a detector on the model's internals — not an output text filter. That distinction is the whole point. In the clip, Qwen3-8B falls for a prompt injection: the payload sits at rank 0 in the internal readout but only rank 5 in the output logits, and the output spells it in pieces — so a text filter never catches it. The internal hook does, and stops generation with zero tokens emitted. Same catch across Qwen3-1.7B → 4B → 8B. Caveat the paper states itself: single-token readouts, an imperfect/incomplete view of the model's "workspace." This is the mechanism working locally — not a solved misalignment detector. Built on Anthropic's open jacobian-lens (Apache-2.0).

Anthropic open-sourced the "Jacobian lens" from their global-workspace paper — a readout of what a model is about to say from its internal layers, before it says it. It's white-box: you need the activations, so you can't point it at a cloud model. I wired it into a hook on a local open-weights Qwen. How it works: generation runs one token at a time; at each step the hook reads the residual stream through the lens, scans the top readout tokens against a watchlist (injection markers, secret words, "manipulate"…), and if one fires it halts the loop before that token is ever emitted. It's a detector on the model's internals — not an output text filter. That distinction is the whole point. In the clip, Qwen3-8B falls for a prompt injection: the payload sits at rank 0 in the internal readout but only rank 5 in the output logits, and the output spells it in pieces — so a text filter never catches it. The internal hook does, and stops generation with zero tokens emitted. Same catch across Qwen3-1.7B → 4B → 8B. Caveat the paper states itself: single-token readouts, an imperfect/incomplete view of the model's "workspace." This is the mechanism working locally — not a solved misalignment detector. Built on Anthropic's open jacobian-lens (Apache-2.0).

Eric Buess

58,315 次观看 • 2 个月前

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 次观看 • 1 个月前

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

RetroChainer

11,100 次观看 • 2 个月前

SHE PUMPED GAS AND GOT 745 COMMENTS 47,000 likes. 745 comments. A woman fills up a car at a roadside station. That is the entire event. The caption reads: honestly no idea how that got there look at the comment ratio before anything else: → 745 comments against 47,000 likes is one per sixty-three. most clips this size land nearer one per five hundred → nothing in the footage explains that. static camera, one location, no edit, no reveal, no payoff → the caption is doing all of it. four words of mock confusion, pointing at something without naming it → that construction forces a decision. the viewer has to work out what is being referred to, and working it out is what moves them into the comments → and it is unfalsifiable. she never says what she means, so nobody can be wrong about it, which is exactly why everyone answers the technique is old and it has a name in older media: the implied antecedent. you refer to a thing without stating it, and the audience supplies the missing noun themselves what makes it powerful on short form is that supplying it feels like participation rather than reaction. a like is passive, but finishing somebody else's sentence is an act, and platforms weight acts far more heavily than they weight approval so the caption is not describing the video. it is a prompt, aimed at the comment box, disguised as an offhand remark the general version, worth stealing for anything you post: the footage decides whether somebody stops. the caption decides whether they do something. most people spend all their effort on the first and write the second in the lift on the way out if you want to test a hook before you shoot anything, image-to-video off one still is the cheapest way in. Picsart runs it from a phone nothing happened in fourteen seconds. seven hundred people explained what it was

SHE PUMPED GAS AND GOT 745 COMMENTS 47,000 likes. 745 comments. A woman fills up a car at a roadside station. That is the entire event. The caption reads: honestly no idea how that got there look at the comment ratio before anything else: → 745 comments against 47,000 likes is one per sixty-three. most clips this size land nearer one per five hundred → nothing in the footage explains that. static camera, one location, no edit, no reveal, no payoff → the caption is doing all of it. four words of mock confusion, pointing at something without naming it → that construction forces a decision. the viewer has to work out what is being referred to, and working it out is what moves them into the comments → and it is unfalsifiable. she never says what she means, so nobody can be wrong about it, which is exactly why everyone answers the technique is old and it has a name in older media: the implied antecedent. you refer to a thing without stating it, and the audience supplies the missing noun themselves what makes it powerful on short form is that supplying it feels like participation rather than reaction. a like is passive, but finishing somebody else's sentence is an act, and platforms weight acts far more heavily than they weight approval so the caption is not describing the video. it is a prompt, aimed at the comment box, disguised as an offhand remark the general version, worth stealing for anything you post: the footage decides whether somebody stops. the caption decides whether they do something. most people spend all their effort on the first and write the second in the lift on the way out if you want to test a hook before you shoot anything, image-to-video off one still is the cheapest way in. Picsart runs it from a phone nothing happened in fourteen seconds. seven hundred people explained what it was

sopersone

120,390 次观看 • 4 天前

Brainrotting teens watching short form memes so much to the point that parts of the fragments of other memes become even more short form and get colluded in other memes to the point that it really doesnt make sense. However. Brain loves pattern recognition of these patterns and nonsensical randomly shown fragments of memes, because it is not long form reward, nor short form reward — but instantaneous; it is the only form of pleasure it can feel So brain tries to look for these patterns unconsciously, it sees patterns and similar resemblance in random things and adds a symbolical emotional labeling of truth to it. So everything becomes a piece of information and data. It gets stored in their subconscious brain and fires up everytime there is a resemblance. Extremely dangerous if weaponised but no one sees the patterns yet. However because of these pattern behaviours teens are split into two categories, the brainrots which God knows how it will end with them — consumers and slaves that later on might have no free will and be driven by pure chemical instinct. And those who see for truth in patterns. The latter is able to overcome modern day censoring and freedom of speech mechanisms, and possibly overcome the evil trying to control the world with pure silliness and having fun. (67 is part of a random pattern that someone said during a match score, and it became viral, nothing more but a collective participation to which youth finds identity by being and acting in it; “performing”) Its beauty lies not in the act but in those individuals that look beyond the chemical instincts of the lower mind. Example of the video below. It shows many fragmental elements of history, symbolism, that is collaged into art. Which by being seen individually or collectively it shows the expression on how man uses its own soul for these kind of co-creations he choses to participate in creation. Symbolism that can leave a person ask for its meaning and search for it, only by questioning himself not by a direct answer (short or long form). Of course which extreme beauty there is also extreme ugliness which are out there which I wont show here Lets see how it really turns out to be honest, West has no protection toward the subjective, the feminine, the subconscious. To which the inner sins of man try to exploit.

Brainrotting teens watching short form memes so much to the point that parts of the fragments of other memes become even more short form and get colluded in other memes to the point that it really doesnt make sense. However. Brain loves pattern recognition of these patterns and nonsensical randomly shown fragments of memes, because it is not long form reward, nor short form reward — but instantaneous; it is the only form of pleasure it can feel So brain tries to look for these patterns unconsciously, it sees patterns and similar resemblance in random things and adds a symbolical emotional labeling of truth to it. So everything becomes a piece of information and data. It gets stored in their subconscious brain and fires up everytime there is a resemblance. Extremely dangerous if weaponised but no one sees the patterns yet. However because of these pattern behaviours teens are split into two categories, the brainrots which God knows how it will end with them — consumers and slaves that later on might have no free will and be driven by pure chemical instinct. And those who see for truth in patterns. The latter is able to overcome modern day censoring and freedom of speech mechanisms, and possibly overcome the evil trying to control the world with pure silliness and having fun. (67 is part of a random pattern that someone said during a match score, and it became viral, nothing more but a collective participation to which youth finds identity by being and acting in it; “performing”) Its beauty lies not in the act but in those individuals that look beyond the chemical instincts of the lower mind. Example of the video below. It shows many fragmental elements of history, symbolism, that is collaged into art. Which by being seen individually or collectively it shows the expression on how man uses its own soul for these kind of co-creations he choses to participate in creation. Symbolism that can leave a person ask for its meaning and search for it, only by questioning himself not by a direct answer (short or long form). Of course which extreme beauty there is also extreme ugliness which are out there which I wont show here Lets see how it really turns out to be honest, West has no protection toward the subjective, the feminine, the subconscious. To which the inner sins of man try to exploit.

Rage ❉

332,451 次观看 • 9 个月前

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.

stevibe

44,248 次观看 • 4 个月前

"You've reached your rate limit. Try again after 7pm." every. fucking. day. $200/month - $2,400 a year - for Codex. then i opened the DeepSeek pricing page. Someone made DeepSeek a native subagent for Codex. Heavy work goes there, light stays on GPT-5. Same code out the other end. 35x cheaper. DeepSeek V4 Flash lives on its own API key, not on my Plus quota. One command: npx skills add oil-oil/codex-deepseek-subagent -g -y Restart Codex, tell it "set up DeepSeek as a subagent", done. First day in a month I'm still working in the evening instead of hitting the wall. save this before your next rate-limit ↓

"You've reached your rate limit. Try again after 7pm." every. fucking. day. $200/month - $2,400 a year - for Codex. then i opened the DeepSeek pricing page. Someone made DeepSeek a native subagent for Codex. Heavy work goes there, light stays on GPT-5. Same code out the other end. 35x cheaper. DeepSeek V4 Flash lives on its own API key, not on my Plus quota. One command: npx skills add oil-oil/codex-deepseek-subagent -g -y Restart Codex, tell it "set up DeepSeek as a subagent", done. First day in a month I'm still working in the evening instead of hitting the wall. save this before your next rate-limit ↓

Granite

71,728 次观看 • 1 个月前

This wallet did not exist yesterday. At 3 AM, I could not sleep. I was scrolling through the leaderboard and stumbled upon an anomaly that made me rub my eyes. It started with $213. That is the price of dinner for two. One day later, it had $54,871 on its balance. In just 36 hours, it earned enough to buy a car. I clicked on the transaction history, expecting to see a lucky all-in on some piece of news. Instead, I saw a machine gun burst. > 869 positions in a day and a half. > One trade every 2.5 minutes. > No breaks for sleep, food, or the bathroom. At 4:30 AM, while you were deep in your tenth dream, this address closed a $1,899 profit. That was when I realized I was not looking at a human. I was looking at a predator. This bot hunts on 15-minute BTC and ETH markets. Where most people see a casino and flip a coin on up or down, it sees flaws in your thinking. Here is how it works: > When Bitcoin drops 0.5%, the crowd panics. > The price of NO skyrockets to 75 cents. You sell out of fear. > But the bot knows the math. After such a drop, the actual probability of the trend continuing is only around 52%, not 75%. It buys your fear for 25 cents, when it is actually worth 45. It does not need to know the future. It just needs to buy dollars for 50 cents. But you know what scared me the most? There is a single trade in its history with a $3,213 loss. A normal person would freeze. Light a cigarette. Start doubting. This wallet opened its next position 54 seconds later. It has no ego. No tilt. No I need to win it back. Only an algorithm: if the probability is 55%, and the market pays as if it is 40%, press the button. This is the new form of mining. In 2017, you bought GPUs. In 2026, you write code that mines liquidity from other people’s emotions. Before you rush to search for scripts on GitHub, stop. The $213 starting point is an illusion. Behind it are servers next to the exchange, 50-millisecond latency, and a team of engineers. You will not beat them manually. You are not a player at this table. You are the food. While you were reading this post, it made another $50. Just watch.

This wallet did not exist yesterday. At 3 AM, I could not sleep. I was scrolling through the leaderboard and stumbled upon an anomaly that made me rub my eyes. It started with $213. That is the price of dinner for two. One day later, it had $54,871 on its balance. In just 36 hours, it earned enough to buy a car. I clicked on the transaction history, expecting to see a lucky all-in on some piece of news. Instead, I saw a machine gun burst. > 869 positions in a day and a half. > One trade every 2.5 minutes. > No breaks for sleep, food, or the bathroom. At 4:30 AM, while you were deep in your tenth dream, this address closed a $1,899 profit. That was when I realized I was not looking at a human. I was looking at a predator. This bot hunts on 15-minute BTC and ETH markets. Where most people see a casino and flip a coin on up or down, it sees flaws in your thinking. Here is how it works: > When Bitcoin drops 0.5%, the crowd panics. > The price of NO skyrockets to 75 cents. You sell out of fear. > But the bot knows the math. After such a drop, the actual probability of the trend continuing is only around 52%, not 75%. It buys your fear for 25 cents, when it is actually worth 45. It does not need to know the future. It just needs to buy dollars for 50 cents. But you know what scared me the most? There is a single trade in its history with a $3,213 loss. A normal person would freeze. Light a cigarette. Start doubting. This wallet opened its next position 54 seconds later. It has no ego. No tilt. No I need to win it back. Only an algorithm: if the probability is 55%, and the market pays as if it is 40%, press the button. This is the new form of mining. In 2017, you bought GPUs. In 2026, you write code that mines liquidity from other people’s emotions. Before you rush to search for scripts on GitHub, stop. The $213 starting point is an illusion. Behind it are servers next to the exchange, 50-millisecond latency, and a team of engineers. You will not beat them manually. You are not a player at this table. You are the food. While you were reading this post, it made another $50. Just watch.

Blaze

14,099 次观看 • 8 个月前

Stop renting a chatbot and calling it your company’s brain. Utopia is the first open-source enterprise world model I’ve seen that actually treats knowledge like a system, not a vibe. It's a Self-hosted, open source and built around the one question every other knowledge base ignores: when. Every fact in it carries a start date and an end date. Nothing gets overwritten. When something changes, the correction closes the old version and opens a new one. The history stays intact. So the graph isn't a snapshot anymore. It's a recording you can rewind. You drag a timeline on the screen and watch the whole thing redraw itself to show what was true on that date. Who owned what. What the policy said before it changed. All of it, replayable. And every fact points back to the exact sentence it came from. Nothing gets in without a receipt. Here's the part that got me. The whole thing is one binary and one Postgres database. That's it. No Elasticsearch, no separate vector service and no message queue. Most RAG stacks are six services duct-taped together. This is two. It even runs fully offline on an air-gapped network with any model you want.

Stop renting a chatbot and calling it your company’s brain. Utopia is the first open-source enterprise world model I’ve seen that actually treats knowledge like a system, not a vibe. It's a Self-hosted, open source and built around the one question every other knowledge base ignores: when. Every fact in it carries a start date and an end date. Nothing gets overwritten. When something changes, the correction closes the old version and opens a new one. The history stays intact. So the graph isn't a snapshot anymore. It's a recording you can rewind. You drag a timeline on the screen and watch the whole thing redraw itself to show what was true on that date. Who owned what. What the policy said before it changed. All of it, replayable. And every fact points back to the exact sentence it came from. Nothing gets in without a receipt. Here's the part that got me. The whole thing is one binary and one Postgres database. That's it. No Elasticsearch, no separate vector service and no message queue. Most RAG stacks are six services duct-taped together. This is two. It even runs fully offline on an air-gapped network with any model you want.

Hasan Toor

175,587 次观看 • 29 天前