Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

I tested GLM 5.3 Flash vs Kimi K3. Same prompts, both capped at $2 per scene. > Same cost, but GLM Flash couldn't build realistic scenes with proper physics. > Kimi K3 nailed it. It actually seemed to understand how objects should move and interact. What are your thoughts?

Bhavy☄️

6,874 subscribers

27,723 görüntüleme • 5 gün önce •via X (Twitter)

Bilim & Teknoloji Oyun

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

I tested Gemini 3.7 Flash vs Qwen 3.8 vs Grok 4.6 vs GLM 5.3 Same prompt, 2 scenes: a harvester and farmers working. honestly? Qwen 3.8 impressed me. it just did what I asked. Grok 4.6 failed on coloring. Qwen>GLM> Grok> Gemini which one did better for you?

I tested Gemini 3.7 Flash vs Qwen 3.8 vs Grok 4.6 vs GLM 5.3 Same prompt, 2 scenes: a harvester and farmers working. honestly? Qwen 3.8 impressed me. it just did what I asked. Grok 4.6 failed on coloring. Qwen>GLM> Grok> Gemini which one did better for you?

Bhavy☄️

108,713 görüntüleme • 16 gün önce

I gave Kimi K3 and Opus 5 the exact same prompt to build a car racing game. I expected Opus 5 to take the lead. Instead, Kimi K3 finished in ~25 min for ~$8.9, while Opus 5 took 19 min and cost $14. The biggest surprise wasn’t the speed or the price. Kimi K3 built the better game. Smoother controls, better physics, and a driving experience that felt ready from the start. Opus 5 looked cleaner visually but Kimi won where it actually mattered. Nearly half the cost and the better gameplay.

I gave Kimi K3 and Opus 5 the exact same prompt to build a car racing game. I expected Opus 5 to take the lead. Instead, Kimi K3 finished in ~25 min for ~$8.9, while Opus 5 took 19 min and cost $14. The biggest surprise wasn’t the speed or the price. Kimi K3 built the better game. Smoother controls, better physics, and a driving experience that felt ready from the start. Opus 5 looked cleaner visually but Kimi won where it actually mattered. Nearly half the cost and the better gameplay.

Aman

111,571 görüntüleme • 1 ay önce

I tested Kimi K3 vs Claude Opus 4.8 Same prompt, an armory bay with lighting, props, and detail. Top is Kimi K3, bottom is Opus 4.8. It's not even close. Kimi K3 built a full scene with textures, proper lighting, ammo crates, weapon racks, working detail everywhere. Opus 4.8 gave me a near empty room with a couple of floating tables. No doubt it beats Opus 4.8. Kimi K3 is Fable 5 level, and it's clearly better than GPT-5.6 Sol at 3D and games. An open weight model just matched the best closed models on the market. Let that sink in.

I tested Kimi K3 vs Claude Opus 4.8 Same prompt, an armory bay with lighting, props, and detail. Top is Kimi K3, bottom is Opus 4.8. It's not even close. Kimi K3 built a full scene with textures, proper lighting, ammo crates, weapon racks, working detail everywhere. Opus 4.8 gave me a near empty room with a couple of floating tables. No doubt it beats Opus 4.8. Kimi K3 is Fable 5 level, and it's clearly better than GPT-5.6 Sol at 3D and games. An open weight model just matched the best closed models on the market. Let that sink in.

Bhavy☄️

475,642 görüntüleme • 1 ay önce

I tested Qwen 3.8 Max vs Kimi K3 Same scene, lighting, props, detail requirements. Qwen's output is decent, but it's not close to Kimi K3. Qwen's output came out messy, text handling was off, and the composition felt unorganized next to Kimi's version. In my opinion, Qwen isn't second to Fable 5 either, and it's also below GPT-5.6 Sol. It's a solid model, but not at that tier. Kimi K3 is still clearly ahead here.

I tested Qwen 3.8 Max vs Kimi K3 Same scene, lighting, props, detail requirements. Qwen's output is decent, but it's not close to Kimi K3. Qwen's output came out messy, text handling was off, and the composition felt unorganized next to Kimi's version. In my opinion, Qwen isn't second to Fable 5 either, and it's also below GPT-5.6 Sol. It's a solid model, but not at that tier. Kimi K3 is still clearly ahead here.

Bhavy☄️

34,045 görüntüleme • 1 ay önce

1-bit Kimi K3 performs at Opus 5 level on 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all the same task, to build a giant anvil drop test as a single HTML file with real physics Outputs: K3 1bit (local): 15.8K tokens, $0 API cost Kimi K3 (API): 15.3K tokens, $0.30 API cost Opus 5: 22.8K tokens, $0.77 API cost GPT 5.6: 14.5K tokens, $0.72 API cost All four got the physics right. But only Kimi made a working winch. The drum turns and the chain drags the flat car off the pad. Opus 5 drew the most detail, road markings and sparks on the hit. And you can run a model at this level on your own box now. That still feels insane to us

1-bit Kimi K3 performs at Opus 5 level on 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all the same task, to build a giant anvil drop test as a single HTML file with real physics Outputs: K3 1bit (local): 15.8K tokens, $0 API cost Kimi K3 (API): 15.3K tokens, $0.30 API cost Opus 5: 22.8K tokens, $0.77 API cost GPT 5.6: 14.5K tokens, $0.72 API cost All four got the physics right. But only Kimi made a working winch. The drum turns and the chain drags the flat car off the pad. Opus 5 drew the most detail, road markings and sparks on the hit. And you can run a model at this level on your own box now. That still feels insane to us

atomic.chat

53,845 görüntüleme • 1 ay önce

holy sh*t this is f**king dangerous i just figured out how to run Opencode in Codex It has Deepseek V4 Flash which replaces Opus 5 at 1/4th price You can get 10,000 request in only $10/month along with Kimi K3 and Qwen 3.5 Max [here is how you set it up] 1. install the 'codex-router' 2. Put in the Opencode Go API key 3. Done that's it Save this no matter what. This will be the best thing you do this week

holy sh*t this is f**king dangerous i just figured out how to run Opencode in Codex It has Deepseek V4 Flash which replaces Opus 5 at 1/4th price You can get 10,000 request in only $10/month along with Kimi K3 and Qwen 3.5 Max [here is how you set it up] 1. install the 'codex-router' 2. Put in the Opencode Go API key 3. Done that's it Save this no matter what. This will be the best thing you do this week

Avid

117,270 görüntüleme • 26 gün önce

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

Rina

45,651 görüntüleme • 1 ay önce

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇

Ziwen

145,018 görüntüleme • 1 ay önce

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.

atomic.chat

2,839,221 görüntüleme • 2 ay önce

THIS GUY IS BUILDING INSANE CUSTOM SITES FOR $0.23 IN API COSTS WITH THE NEW KIMI K3 currently #1 on the coding arena. the video attached shows a complex, highly detailed website. it was coded entirely by a new model called Kimi K3. early testers are calling it scarily good because it quietly removes the need for complex agent swarms. here is the instant breakdown of what makes it terrifying. 1. native vision in the loop it iterates code while analyzing live screenshots of its own output. it literally looks at the site it builds and corrects the styling autonomously. 2. massive sparse architecture it has 2.8 trillion parameters but only activates 50b per token. this makes it insanely fast and allows for a native 1,000,000 token context window. 3. recursive self-improvement it spends a massive amount of compute on self-verification. it runs unit tests and simulates environments before giving you the final frontend code. 4. brutal economics it costs exactly $3 per million input tokens. the entire custom site in the video cost around $0.23 to generate. the era of orchestrating 12 dumb agents to build a simple web app is over. one smart instance is all you need.

THIS GUY IS BUILDING INSANE CUSTOM SITES FOR $0.23 IN API COSTS WITH THE NEW KIMI K3 currently #1 on the coding arena. the video attached shows a complex, highly detailed website. it was coded entirely by a new model called Kimi K3. early testers are calling it scarily good because it quietly removes the need for complex agent swarms. here is the instant breakdown of what makes it terrifying. 1. native vision in the loop it iterates code while analyzing live screenshots of its own output. it literally looks at the site it builds and corrects the styling autonomously. 2. massive sparse architecture it has 2.8 trillion parameters but only activates 50b per token. this makes it insanely fast and allows for a native 1,000,000 token context window. 3. recursive self-improvement it spends a massive amount of compute on self-verification. it runs unit tests and simulates environments before giving you the final frontend code. 4. brutal economics it costs exactly $3 per million input tokens. the entire custom site in the video cost around $0.23 to generate. the era of orchestrating 12 dumb agents to build a simple web app is over. one smart instance is all you need.

ard

91,882 görüntüleme • 1 ay önce

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.

atomic.chat

70,490 görüntüleme • 1 ay önce

OpenCode Go is now wired into Codex!! The pricing is insane. $10 gets you 10,000 DeepSeek requests every 5 hours (no weekly limits). I converted that into DeepSeek API dollars because I thought I was reading it wrong, and the same 5 hours of usage would run somewhere between $10 and $30 depending on how big your context gets. So one afternoon of use already covers the whole sub. It comes with Kimi K3 as well. Both sit in the picker next to my other models now. Next time we hit a limit in the middle of a loop, we can grab it and keep going.

OpenCode Go is now wired into Codex!! The pricing is insane. $10 gets you 10,000 DeepSeek requests every 5 hours (no weekly limits). I converted that into DeepSeek API dollars because I thought I was reading it wrong, and the same 5 hours of usage would run somewhere between $10 and $30 depending on how big your context gets. So one afternoon of use already covers the whole sub. It comes with Kimi K3 as well. Both sit in the picker next to my other models now. Next time we hit a limit in the middle of a loop, we can grab it and keep going.

Ziwen

431,395 görüntüleme • 26 gün önce

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 görüntüleme • 12 gün önce

GLM 5.2 INPUT FELL FROM $1.40 TO SEVEN CENTS PER MILLION IN NINETY DAYS • what it costs now > $0.07 per million input at the cheapest of 20 providers, a 95% drop in three months. > direct still lists $1.40 in and $4.40 out, with cached input at $0.26. > Same model, same weights, twenty-fold spread depending on the door you walk through. • the free way in > New accounts on get 20M tokens: > 744B MoE, 1M context, MIT weights you can also just download and self-host. Nobody announced this. It happened one provider at a time -> and the model itself never changed. Check which provider you are actually routed through before you top up anywhere ↓

GLM 5.2 INPUT FELL FROM $1.40 TO SEVEN CENTS PER MILLION IN NINETY DAYS • what it costs now > $0.07 per million input at the cheapest of 20 providers, a 95% drop in three months. > direct still lists $1.40 in and $4.40 out, with cached input at $0.26. > Same model, same weights, twenty-fold spread depending on the door you walk through. • the free way in > New accounts on get 20M tokens: > 744B MoE, 1M context, MIT weights you can also just download and self-host. Nobody announced this. It happened one provider at a time -> and the model itself never changed. Check which provider you are actually routed through before you top up anywhere ↓

slash1s

30,117 görüntüleme • 20 gün önce

Gemini Omni is changing video creation and most people still don't know what it can actually do. Here are 7 things you can do with it right now: 1. Image to Video in multiple styles: Upload a photo. describe the style. Gemini Omni turns it into a video. cinematic, anime, realistic. 2. Reimagine camera angles: Take any image and visualize it from a completely different angle. no reshooting. just describe it. 3. Change backgrounds: Swap the background of any video through plain conversation. no green screen. no editing software. 4. Change hairstyle: Describe a new hairstyle. Gemini Omni applies it. characters stay consistent across every frame. 5. visualize with moodboards: feed it a moodboard, audio, and a brief. it builds the video around the full creative reference — not just a text prompt. 6. swap characters and objects mid-scene: replace people, props, and objects in an existing video. the scene stays consistent. the physics hold up. 7. edit physics: describe how you want things to move. Gemini Omni adjusts the physics of the scene through conversation.

Gemini Omni is changing video creation and most people still don't know what it can actually do. Here are 7 things you can do with it right now: 1. Image to Video in multiple styles: Upload a photo. describe the style. Gemini Omni turns it into a video. cinematic, anime, realistic. 2. Reimagine camera angles: Take any image and visualize it from a completely different angle. no reshooting. just describe it. 3. Change backgrounds: Swap the background of any video through plain conversation. no green screen. no editing software. 4. Change hairstyle: Describe a new hairstyle. Gemini Omni applies it. characters stay consistent across every frame. 5. visualize with moodboards: feed it a moodboard, audio, and a brief. it builds the video around the full creative reference — not just a text prompt. 6. swap characters and objects mid-scene: replace people, props, and objects in an existing video. the scene stays consistent. the physics hold up. 7. edit physics: describe how you want things to move. Gemini Omni adjusts the physics of the scene through conversation.

Poonam Soni

11,682 görüntüleme • 1 ay önce

anthropic will sell you opus 5 at $200 a month. openai will sell you gpt-5.6 at $200 a month. neither will tell you stanford and berkeley published the 5 principles to build a $100k/mo ai company on kimi k3 for $10 stanford and berkeley spent years figuring out what actually separates ai systems that work in production from ai systems that die in demos. they published the findings. anthropic and openai priced their frontier subs like nobody would read the papers. the papers are free this is dspy plus verifiers plus decomposition plus skills plus mcp. five principles from stanford, berkeley and moonshot that turn a $10/mo kimi k3 sub into an ai analyst that runs unattended. the model is public. the system is the moat five moves that turn kimi k3 into the $100k/mo company: P1 don't prompt, program (stanford dspy) -> stanford proved hand-tuned prompts don't scale. define a pipeline as modules, let the optimizer tune them -> the compiled pipeline beat expert few-shot on multi-step tasks. one line of dspy replaces a month of prompt engineering P2 don't trust the model, build verifiers (berkeley 2026) -> a compiler either accepts or rejects. a test either passes or fails. that is a verifier -> berkeley: test-suite reward hit 42.2% pass@1 on swe-bench. hybrid verifiers hit 51.0% best@26. no bigger model, just a real check P3 don't scale agents, decompose them (stanford ai index 2026) -> stanford found multi-agent gains only 2-4 percentage points. two coding agents sometimes did worse than one -> the win is role decomposition, not count. researcher, writer, reviewer, verifier, clear input, clear output, no overlap P4 don't repeat expertise, encode it as skills (kimi code) -> every session starting from zero is institutional knowledge you lost. a skill.md file makes kimi activate the workflow automatically -> week one you write the skill. month six it encodes more institutional memory than most junior employees carry P5 don't keep ai in chat, connect it to tools (mcp) -> a model that only sees what you paste is a consultant working blindfolded. mcp connects kimi to your crm, db, github, linear, slack -> the model is public. the data is yours. the connections are your moat my position, and it is the arguable one: the next $100k/mo ai company will not win because it got early access to a frontier model. it will win because it followed 5 papers that anthropic and openai are quietly hoping you never read drop your $200/mo ai sub to $10. the swarm above is what 300 kimi k3 agents look like running those 5 principles. the full playbook is in the article below

anthropic will sell you opus 5 at $200 a month. openai will sell you gpt-5.6 at $200 a month. neither will tell you stanford and berkeley published the 5 principles to build a $100k/mo ai company on kimi k3 for $10 stanford and berkeley spent years figuring out what actually separates ai systems that work in production from ai systems that die in demos. they published the findings. anthropic and openai priced their frontier subs like nobody would read the papers. the papers are free this is dspy plus verifiers plus decomposition plus skills plus mcp. five principles from stanford, berkeley and moonshot that turn a $10/mo kimi k3 sub into an ai analyst that runs unattended. the model is public. the system is the moat five moves that turn kimi k3 into the $100k/mo company: P1 don't prompt, program (stanford dspy) -> stanford proved hand-tuned prompts don't scale. define a pipeline as modules, let the optimizer tune them -> the compiled pipeline beat expert few-shot on multi-step tasks. one line of dspy replaces a month of prompt engineering P2 don't trust the model, build verifiers (berkeley 2026) -> a compiler either accepts or rejects. a test either passes or fails. that is a verifier -> berkeley: test-suite reward hit 42.2% pass@1 on swe-bench. hybrid verifiers hit 51.0% best@26. no bigger model, just a real check P3 don't scale agents, decompose them (stanford ai index 2026) -> stanford found multi-agent gains only 2-4 percentage points. two coding agents sometimes did worse than one -> the win is role decomposition, not count. researcher, writer, reviewer, verifier, clear input, clear output, no overlap P4 don't repeat expertise, encode it as skills (kimi code) -> every session starting from zero is institutional knowledge you lost. a skill.md file makes kimi activate the workflow automatically -> week one you write the skill. month six it encodes more institutional memory than most junior employees carry P5 don't keep ai in chat, connect it to tools (mcp) -> a model that only sees what you paste is a consultant working blindfolded. mcp connects kimi to your crm, db, github, linear, slack -> the model is public. the data is yours. the connections are your moat my position, and it is the arguable one: the next $100k/mo ai company will not win because it got early access to a frontier model. it will win because it followed 5 papers that anthropic and openai are quietly hoping you never read drop your $200/mo ai sub to $10. the swarm above is what 300 kimi k3 agents look like running those 5 principles. the full playbook is in the article below

starmex

31,358 görüntüleme • 14 gün önce

GLM 5.1 just went open-weight on Hugging Face, but how does it compare to GLM 5? I have tested both with the canvas tree challenge. 5.1 thinks longer, but delivers wind animation, sun, clouds, and way more detail. Prompt attached: Write a single HTML file with a full-page canvas, no libraries. Animate a tree that grows from the bottom center of the screen in real time. The trunk grows upward first, then branches split off recursively with slight randomness in angle and length. Each generation of branches should be thinner and slightly lighter in color. When branches reach their final size, add small leaves as soft green circles at the tips. The tree should take about 15 seconds to fully grow. Use warm brown for wood and varied greens for leaves against a soft sky-blue gradient background.

GLM 5.1 just went open-weight on Hugging Face, but how does it compare to GLM 5? I have tested both with the canvas tree challenge. 5.1 thinks longer, but delivers wind animation, sun, clouds, and way more detail. Prompt attached: Write a single HTML file with a full-page canvas, no libraries. Animate a tree that grows from the bottom center of the screen in real time. The trunk grows upward first, then branches split off recursively with slight randomness in angle and length. Each generation of branches should be thinner and slightly lighter in color. When branches reach their final size, add small leaves as soft green circles at the tips. The tree should take about 15 seconds to fully grow. Use warm brown for wood and varied greens for leaves against a soft sky-blue gradient background.

stevibe

46,657 görüntüleme • 4 ay önce

UPDATE: Charlie Kirk 🚨 Muzzle Flash: Second Shooter Location, Reflection, or Both? This video captures a flash on a window right as Charlie Kirk was shot. Let’s break this down… follow the numbers on the videos. #1. This video shows what appears to be a muzzle flash, just as Charlie is shot, leading people to believe the shooter was to Charlie’s right.. Notate the people to the left of the flash #2. This photo shows the location of the flash. Notate people to the left, on a middle-landing on a staircase. #3. This photo shows a clearer image showing both the middle-landing and the same location of the flash. It is a window. #4 . This video shows the building behind Charlie, which is a long hallway. This debunks any claims the shot came from here. — I zoom in where Charlie was — I zoom in on staircase — I zoom in on the window/flash — I zoom in on where suspected shooter was #5. I notate the flash reflection angles. — Video angle #1 notated — two reflection paths notated in relation to Video angle #1. 1. Reflection angle shows where we were told the shooter was. 2. Reflection angle shows mirrored angle, obviously where there is no reports of a shooter being in. 🔻 Final conclusion: This to me is very likely a muzzle flash reflection from a far off location. I am unsure of the reflection angle however, but this can be 100% proven if someone were to recreate the angles… maybe with a flash camera. If anyone is willing to, or has the means to do this (safely), this will either prove the shot came where the FBI said it came from, or it will prove there was a second shooter, in the direction of the mirrored angle.

UPDATE: Charlie Kirk 🚨 Muzzle Flash: Second Shooter Location, Reflection, or Both? This video captures a flash on a window right as Charlie Kirk was shot. Let’s break this down… follow the numbers on the videos. #1. This video shows what appears to be a muzzle flash, just as Charlie is shot, leading people to believe the shooter was to Charlie’s right.. Notate the people to the left of the flash #2. This photo shows the location of the flash. Notate people to the left, on a middle-landing on a staircase. #3. This photo shows a clearer image showing both the middle-landing and the same location of the flash. It is a window. #4 . This video shows the building behind Charlie, which is a long hallway. This debunks any claims the shot came from here. — I zoom in where Charlie was — I zoom in on staircase — I zoom in on the window/flash — I zoom in on where suspected shooter was #5. I notate the flash reflection angles. — Video angle #1 notated — two reflection paths notated in relation to Video angle #1. 1. Reflection angle shows where we were told the shooter was. 2. Reflection angle shows mirrored angle, obviously where there is no reports of a shooter being in. 🔻 Final conclusion: This to me is very likely a muzzle flash reflection from a far off location. I am unsure of the reflection angle however, but this can be 100% proven if someone were to recreate the angles… maybe with a flash camera. If anyone is willing to, or has the means to do this (safely), this will either prove the shot came where the FBI said it came from, or it will prove there was a second shooter, in the direction of the mirrored angle.

MJTruthUltra

10,665,164 görüntüleme • 11 ay önce

Opus 4.6 vs GPT 5.4 (High) (1/9) prompt: Build a single-file HTML/CSS/JS (no libs) demo that uses SVG to simulate a plant growing: stem extends, leaves sprout + unfurl with springy/windy “physics”, then seamlessly loops forever. For the initial impressions I'm really impressed by GPT, for speed they both felt about the same, but gpt was still half cheaper than opus. I also much prefer the design and animation that gpt produced, physics on the leaves are super cool and it also loops pretty nicely whilst opus just fades out the plant. Still got a bunch of tests to run but this is really exciting.

Opus 4.6 vs GPT 5.4 (High) (1/9) prompt: Build a single-file HTML/CSS/JS (no libs) demo that uses SVG to simulate a plant growing: stem extends, leaves sprout + unfurl with springy/windy “physics”, then seamlessly loops forever. For the initial impressions I'm really impressed by GPT, for speed they both felt about the same, but gpt was still half cheaper than opus. I also much prefer the design and animation that gpt produced, physics on the leaves are super cool and it also loops pretty nicely whilst opus just fades out the plant. Still got a bunch of tests to run but this is really exciting.

Dev Ed

660,154 görüntüleme • 5 ay önce

A lesson for every Polymarket bot developer: I built a strategy that looked perfect on paper. Backtested it. Looked like a winner. Almost went live. Then i actually measured real costs. Strategy was dead before the first trade. And this is what bot building on Polymarket actually looks like. Here is what happened (and what you MUST know): Backtested mean reversion on crypto dips. SOL came back at +44% return and 70.5% win rate. Beautiful clean curve. Looked ready to ship. Then i measured real round-trip costs on SOL flash dips. Backtest assumed 0.45% in fees and slippage. Reality was 1.44%. Strategy stops working at 0.70%. Starting again. But the lesson was worth more than any profit the strategy could have made. Here is what i actually learned: Taking a dip with a market order means you eat the spread the dip just created. The volatility making your signal is the same volatility destroying your fill. You see the opportunity. You enter. You already lost. But resting a limit order below market and letting the dip come to you? You collect the maker rebate instead. Same thesis. Completely opposite execution. One bleeds money, one prints it. That one realization changed how i think about bot strategy entirely. 180 strategies tested to get there. 179 dead. That is not failure. That is how you find the 5 that actually work. Building a bot on Polymarket is not about finding a magic strategy. It is about eliminating every wrong answer until only the right one is left.

A lesson for every Polymarket bot developer: I built a strategy that looked perfect on paper. Backtested it. Looked like a winner. Almost went live. Then i actually measured real costs. Strategy was dead before the first trade. And this is what bot building on Polymarket actually looks like. Here is what happened (and what you MUST know): Backtested mean reversion on crypto dips. SOL came back at +44% return and 70.5% win rate. Beautiful clean curve. Looked ready to ship. Then i measured real round-trip costs on SOL flash dips. Backtest assumed 0.45% in fees and slippage. Reality was 1.44%. Strategy stops working at 0.70%. Starting again. But the lesson was worth more than any profit the strategy could have made. Here is what i actually learned: Taking a dip with a market order means you eat the spread the dip just created. The volatility making your signal is the same volatility destroying your fill. You see the opportunity. You enter. You already lost. But resting a limit order below market and letting the dip come to you? You collect the maker rebate instead. Same thesis. Completely opposite execution. One bleeds money, one prints it. That one realization changed how i think about bot strategy entirely. 180 strategies tested to get there. 179 dead. That is not failure. That is how you find the 5 that actually work. Building a bot on Polymarket is not about finding a magic strategy. It is about eliminating every wrong answer until only the right one is left.

Oracle Boar

14,379 görüntüleme • 4 ay önce