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

Kimi K2.7 Code just dropped from Moonshot AI. GLM 5.2 is faster, smarter, and cheaper. I purchased both the $39 and $99 plans to test it. I zapped my usage in 30 minutes. The horror game didn't work The Minecraft clone was unplayable The model got stuck outputting thousands... show more

BridgeMind

57,175 subscribers

48,073 просмотров • 3 месяцев назад •via X (Twitter)

Игры Искусство Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 29

Фото профиля Bridgebench

Bridgebench3 месяцев назад

Kimi K2.7 Code is a terrible model.

Фото профиля Matthew Miller

Matthew Miller3 месяцев назад

I am not going to be using Kimi K2.7 Code.

Фото профиля Alberto Nunez-Garcia

Alberto Nunez-Garcia3 месяцев назад

Stats teacher in shambles from all the unsubstantiated bullshit 😂 6th time crying about quota after buying the inexpensive plans? Bench site my ass — pay the money and test properly... Sweater in summer + random ‘no stamp’ nobody asked for is funny though, ngl.

Фото профиля ShinZo

ShinZo3 месяцев назад

even GPT-5.5 has 292k context window

Фото профиля Abhinav Kumar

Abhinav Kumar3 месяцев назад

yep k2.7 code isn't good. mimo v2.5 pro is better than it

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack3 месяцев назад

@bridgemindai sounds rough. was thinking of trying it but maybe i'll wait for a better patch. thanks for the heads up!

Фото профиля Mert Kaya

Mert Kaya3 месяцев назад

Kimi and GLM will get better with time but do not count on the vibe capabilities of Chinese models yet.

Фото профиля Qwinah

Qwinah3 месяцев назад

Yea fully felt like I was buying the hype here when I tried it out. Fell extremely short from what I expected

Фото профиля vuong

vuong3 месяцев назад

i agree! I feel like it's actually minimax model wrapper, it got struggled to do poem with a strictly rule, it took me like 4mins to complete with a terrible result. Any other model could at least following the standard, result could be low or high quality but within 5s-1min.

Фото профиля byrdo

byrdo3 месяцев назад

Fair criticism on the vibe coding demos — those failed tasks are real. But the 262K context complaint is a bit off base. K2.7 Code isn't a general assistant, it's a coding agent built for long-horizon multi-file work. At $0.95/$4 per million tokens with open weights under MIT, the efficiency gains (30% fewer reasoning tokens vs K2.6) matter more than the consumer demos suggest.

Фото профиля Evan W Rowe

Evan W Rowe3 месяцев назад

Any indications of Chinese models starting to lag under the US pressure cooker? @tphuang ?

Фото профиля Ankit Srivastava

Ankit Srivastava3 месяцев назад

Gpt 5.5 at max settings vs glm 5.2 ; which one?

Фото профиля GW IS NOT REAL / rue.onl

GW IS NOT REAL / rue.onl3 месяцев назад

I been saying Kimi isn't that good.. Mimo much better

Фото профиля bitslix

bitslix3 месяцев назад

As we said, results we didn't expect 😁

Фото профиля Rainy&Hero

Rainy&Hero3 месяцев назад

Thanks for your share，Only complex scenarios can truly test the capabilities of those open-source models. Benchmarks aren’t very reliable.

Фото профиля Mikron

Mikron3 месяцев назад

What u think about composer 2.5?

Фото профиля Anton

Anton3 месяцев назад

Thank you for the real info.

Фото профиля Wyatt Cupp

Wyatt Cupp3 месяцев назад

Yep, noticing k2.7 code is actually terrible at listening to its system prompt and tool descriptions. The hype is totally false.

Фото профиля 💫 Dor 🎗️

💫 Dor 🎗️3 месяцев назад

Well done again @bridgemindai

Фото профиля Dkalashtv

Dkalashtv3 месяцев назад

@matthewmillerai Why would I want to win a POS plan ?

Фото профиля Erkin Askarbekov

Erkin Askarbekov3 месяцев назад

So glm 5.2 better? And glm 5.2 which model level claude, gpt?

Фото профиля 安叫兽|Bird🕊️ 🔶 BNB

安叫兽|Bird🕊️ 🔶 BNB3 месяцев назад

30分钟烧完额度也太真实了

Фото профиля nick

nick3 месяцев назад

spending $138 to watch an llm get stuck in a loop while failing a minecraft clone is the peak 2026 dev experience. the horror game failing was just foreshadowing for the bill

Фото профиля Koray Bıyık

Koray Bıyık3 месяцев назад

When will you share the results?

Фото профиля Irbaaz Kadri

Irbaaz Kadri3 месяцев назад

Nah mate nah they need budget to make it happen.

Фото профиля Alex Boudot

Alex Boudot3 месяцев назад

context window is not intelligence. sometimes it’s just a bigger room to fail in.

Фото профиля Glen | Tyne

Glen | Tyne3 месяцев назад

Correct. Something happened with 2.6 not long ago that made it unusable. Even simple tasks inside Kimi Code just resulted in madness. They have dropped the ball.

Фото профиля AI Mastery Guide

AI Mastery Guide3 месяцев назад

zapping $99 in 30 minutes just to get a minecraft clone that doesn't work is a tough review to come back from

Фото профиля Prince does AI

Prince does AI3 месяцев назад

Kimi speedrun ate the credits and the Minecraft save

Похожие видео

Kimi K3 is the first open source model to earn the BridgeMind stamp of approval. One shot Horror House game. One shot full-stack app. Beating Fable 5 in early BridgeBench arena matches. #3 on the Intelligence Index. Moonshot AI just caught the frontier. Full Kimi K3 review below.

Kimi K3 is the first open source model to earn the BridgeMind stamp of approval. One shot Horror House game. One shot full-stack app. Beating Fable 5 in early BridgeBench arena matches. #3 on the Intelligence Index. Moonshot AI just caught the frontier. Full Kimi K3 review below.

BridgeMind

31,965 просмотров • 2 месяцев назад

Ran two prompts in Kimi K2.7 Code HighSpeed, Kimi K2.7 Code, and GLM 5.2 HighSpeed is 2.5 to 4.2 times faster than Kimi K2.7 Code while producing comparable quality 4.5 to 15 times faster than GLM 5.2, and half the price (or less) These are simple tests, so the pricing difference is small and speed difference could diverge a lot But definitely a hell of a lot faster with good output

Ran two prompts in Kimi K2.7 Code HighSpeed, Kimi K2.7 Code, and GLM 5.2 HighSpeed is 2.5 to 4.2 times faster than Kimi K2.7 Code while producing comparable quality 4.5 to 15 times faster than GLM 5.2, and half the price (or less) These are simple tests, so the pricing difference is small and speed difference could diverge a lot But definitely a hell of a lot faster with good output

GMI Cloud

38,174 просмотров • 3 месяцев назад

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:

Ivan Fioravanti ᯅ

21,604 просмотров • 3 месяцев назад

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

BridgeMind

24,681 просмотров • 3 месяцев назад

I tested MiniMax M3 so you do not have to. It is free in OpenCode right now and it claims to beat GPT 5.5 on SWE-bench. So I put it on real production code. It broke my push-to-talk. It glitched a game through the floor. It took two tries to render a video and still looked rough. The benchmark said one thing. The real work said another. The one thing it has going for it is price. I ran all of BridgeBench for $4.09. If budget is your only constraint, it is the cheapest Chinese model out there. But cheap is not free when it breaks your codebase. No BridgeMind stamp of approval. Full breakdown in the video.

I tested MiniMax M3 so you do not have to. It is free in OpenCode right now and it claims to beat GPT 5.5 on SWE-bench. So I put it on real production code. It broke my push-to-talk. It glitched a game through the floor. It took two tries to render a video and still looked rough. The benchmark said one thing. The real work said another. The one thing it has going for it is price. I ran all of BridgeBench for $4.09. If budget is your only constraint, it is the cheapest Chinese model out there. But cheap is not free when it breaks your codebase. No BridgeMind stamp of approval. Full breakdown in the video.

BridgeMind

46,557 просмотров • 4 месяцев назад

New Z.ai GLM-5.2 beats Kimi K2.7 Code on physics contest! We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Pool break 2. Block on a bed of springs 3. Galton board Outputs: GLM-5.2: 12,640 tokens Kimi K2.7 Code: 7,420 tokens GLM 5.2 nailed all three, and it did it with way more detail and polish. The break conserved momentum, the block bounced off the springs and the Galton beads spread into a clean bell curve. Kimi struggled on every scene: its block fell straight through the springs, its break didn't look realistic with the balls colliding all wrong, and on the Galton board its balls overlapped and piled into each other instead of spreading out

New Z.ai GLM-5.2 beats Kimi K2.7 Code on physics contest! We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Pool break 2. Block on a bed of springs 3. Galton board Outputs: GLM-5.2: 12,640 tokens Kimi K2.7 Code: 7,420 tokens GLM 5.2 nailed all three, and it did it with way more detail and polish. The break conserved momentum, the block bounced off the springs and the Galton beads spread into a clean bell curve. Kimi struggled on every scene: its block fell straight through the springs, its break didn't look realistic with the balls colliding all wrong, and on the Galton board its balls overlapped and piled into each other instead of spreading out

atomic.chat

60,899 просмотров • 3 месяцев назад

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇

Md Riyazuddin

31,199 просмотров • 3 месяцев назад

🚨API IS CHEAPER THAN SUBSCRIPTION. I ONE-SHOT A PLAYABLE MARIO CLONE WITH ONLY $2 OF API CREDITS. Yesterday I posted that Claude MAX 20x gave me less than 4 hours of actual Fable 5.1 usage before I was already at ~77% of my weekly limit. I was genuinely asking how “45% cheaper” mattered if I could barely use the model. MixRoute AI saw the post and reached out to let me stress-test their API for a full day. So I thought why dont we make a comparision between both of them Claude Code session: $10.25 cache hit 97% MixRoute AI API usage: $2.00 Claude Code: ~25 min → $10.25 MixRoute: ~32 min → $2.00 ~6 minutes slower. ~80% cheaper. Both built a playable Mario clone. Full run sped up ~60x ↓

🚨API IS CHEAPER THAN SUBSCRIPTION. I ONE-SHOT A PLAYABLE MARIO CLONE WITH ONLY $2 OF API CREDITS. Yesterday I posted that Claude MAX 20x gave me less than 4 hours of actual Fable 5.1 usage before I was already at ~77% of my weekly limit. I was genuinely asking how “45% cheaper” mattered if I could barely use the model. MixRoute AI saw the post and reached out to let me stress-test their API for a full day. So I thought why dont we make a comparision between both of them Claude Code session: $10.25 cache hit 97% MixRoute AI API usage: $2.00 Claude Code: ~25 min → $10.25 MixRoute: ~32 min → $2.00 ~6 minutes slower. ~80% cheaper. Both built a playable Mario clone. Full run sped up ~60x ↓

Abdelrahman Alkerdawy

21,929 просмотров • 26 дней назад

last week I talked about claude code being my video editor, but it was only a small 30 second clip - here is my FULL workflow on how i have claude code edit ~30 minutes of raw video into a tight 10 minutes it uses STT for captions, then uses remotion to add the captions & cut!

last week I talked about claude code being my video editor, but it was only a small 30 second clip - here is my FULL workflow on how i have claude code edit ~30 minutes of raw video into a tight 10 minutes it uses STT for captions, then uses remotion to add the captions & cut!

BOOTOSHI 👑

14,107 просмотров • 8 месяцев назад

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

The Pragmatic Engineer

39,073 просмотров • 4 месяцев назад

cursor design mode + remotion is actually insane everything in remotion is code, so you can annotate changes directly on the video and cursor just updates it. having a lot of fun with this here's 15 minutes of me improving the agent swarm video

cursor design mode + remotion is actually insane everything in remotion is code, so you can annotate changes directly on the video and cursor just updates it. having a lot of fun with this here's 15 minutes of me improving the agent swarm video

eric zakariasson

156,913 просмотров • 4 месяцев назад

Composer 2.5 gets the BridgeMind stamp of approval. It doesn't have the design quality of GPT 5.5 or Opus 4.7. But for fast iteration and backend bug fixes, it delivers. Elon reposted it this morning. SpaceX is likely acquiring Cursor. This model is about to get a lot more attention. Full review and real vibe coding workflow test below.

Composer 2.5 gets the BridgeMind stamp of approval. It doesn't have the design quality of GPT 5.5 or Opus 4.7. But for fast iteration and backend bug fixes, it delivers. Elon reposted it this morning. SpaceX is likely acquiring Cursor. This model is about to get a lot more attention. Full review and real vibe coding workflow test below.

BridgeMind

12,671 просмотров • 4 месяцев назад

Claude Opus 4.7 is the best model in the world. It's also benchmaxed. Both are true. Built a first person shooter game, a full website redesign, and a marketing video in one session. The output is real. But it's not the giant leap the benchmarks suggest. Security got worse. Tokens burn 35% faster. 75% of the BridgeMind community agrees it's benchmaxed. Best model. Oversold improvement. Full breakdown below.

Claude Opus 4.7 is the best model in the world. It's also benchmaxed. Both are true. Built a first person shooter game, a full website redesign, and a marketing video in one session. The output is real. But it's not the giant leap the benchmarks suggest. Security got worse. Tokens burn 35% faster. 75% of the BridgeMind community agrees it's benchmaxed. Best model. Oversold improvement. Full breakdown below.

BridgeMind

19,570 просмотров • 5 месяцев назад

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

Alvaro Cintas

378,059 просмотров • 2 лет назад

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

MIKE

58,719 просмотров • 2 месяцев назад

IT JUST GOT CHEAPER FOR AI VIDEO! I've refined the Selfie AI Video Prompt to get accurate results 99% of the time. Want the prompt and tutorial? Comment PROPMT and I'll send it to you and show you IN DETAIL how I was able to get results like this 👇👇

IT JUST GOT CHEAPER FOR AI VIDEO! I've refined the Selfie AI Video Prompt to get accurate results 99% of the time. Want the prompt and tutorial? Comment PROPMT and I'll send it to you and show you IN DETAIL how I was able to get results like this 👇👇

Murray Frost

124,520 просмотров • 1 год назад

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

Melvin Vivas

45,749 просмотров • 1 год назад

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."

Chris

5,664,840 просмотров • 1 год назад

The creator of Claude Code, Boris Cherny: "Every night I have hundreds, sometimes thousands of agents running 5, 10, 20 hours. That's just how engineering is done now." Bloomberg just gave him an hour to unpack it: not better prompts, but loops. The same pattern runs on both Claude Code and Kimi K3. Watch the talk, and save the full setup below 👇

The creator of Claude Code, Boris Cherny: "Every night I have hundreds, sometimes thousands of agents running 5, 10, 20 hours. That's just how engineering is done now." Bloomberg just gave him an hour to unpack it: not better prompts, but loops. The same pattern runs on both Claude Code and Kimi K3. Watch the talk, and save the full setup below 👇

darkzodchi

221,779 просмотров • 2 месяцев назад