Loading video...

Video Failed to Load

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

🌘 Meet Kimi K2.7 Code HighSpeed! A high-speed mode of our latest open-source multimodal coding model, Kimi K2.7 Code. ⚡️ Up to 6× faster: Around 180 tok/s on coding tasks with median-length inputs, and up to 260 tok/s on shorter-context tasks. 🔷 Rolling out to Kimi Code Beta Program... show more

Kimi.ai

353,346 subscribers

569,488 views • 1 month ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🆕 Kimi.ai's Kimi K2.7 Code is now generally available in GitHub Copilot. This is the first open-weight model offered as a selectable option in the Copilot model picker. 🎉 Early testing shows Kimi K2.7 is a lower-cost option with strong performance comparable to highly popular frontier models. Try it out now in Visual Studio Code and look out for it in more GitHub Copilot surfaces. 👇

🆕 Kimi.ai's Kimi K2.7 Code is now generally available in GitHub Copilot. This is the first open-weight model offered as a selectable option in the Copilot model picker. 🎉 Early testing shows Kimi K2.7 is a lower-cost option with strong performance comparable to highly popular frontier models. Try it out now in Visual Studio Code and look out for it in more GitHub Copilot surfaces. 👇

GitHub

199,983 views • 1 month ago

Cline has launched ClinePass, a flat monthly subscription that opens access to a curated set of open-weight coding models across its IDE extensions, CLI, and SDK. The current lineup includes GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, MiniMax-M3, and Qwen3.7, with a subscription replacing separate API keys across providers.

Cline has launched ClinePass, a flat monthly subscription that opens access to a curated set of open-weight coding models across its IDE extensions, CLI, and SDK. The current lineup includes GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, MiniMax-M3, and Qwen3.7, with a subscription replacing separate API keys across providers.

🚨 AI News | TestingCatalog

54,728 views • 1 month ago

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

110,057 views • 3 months ago

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below

Paul Couvert

88,333 views • 5 months ago

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Mr. Buzzoni

120,637 views • 25 days ago

My honest take on Kimi.ai K3 👀 As soon as I got access to Kimi, I put it through the exact same 3D football stadium challenge I had previously given Claude Fable 5. Fable 5 finished in under an hour. Kimi took almost 3 hours 🥵 At first, that was a very bad impression but i decided to see what's taking it this much of time. It was running E2E tests, validating desktop, tablet, and mobile, taking screenshots, finding failures, fixing them, even adapting for low end hardware and low FPS before moving on. All these that Fable 5 never did. None of it because it wasn't able to run this WebGL app on a headless browser. Kimi also shipped a clean React + Three.js codebase with proper components while Fable, as you might have checked codebase, generated one big HTML file with everything stuffed in. With all of this happening, it felt like I was doing more "Vibe Coding" with Fable 5 and more "Vibe Engineering" with Kimi K3. It feels like it's spending more time making sure the code actually works and easily scalable. Really impressed so far. More Kimi K3 experiments coming soon. Code (Kimi): Code (Fable): Live (Kimi hosted):

My honest take on Kimi.ai K3 👀 As soon as I got access to Kimi, I put it through the exact same 3D football stadium challenge I had previously given Claude Fable 5. Fable 5 finished in under an hour. Kimi took almost 3 hours 🥵 At first, that was a very bad impression but i decided to see what's taking it this much of time. It was running E2E tests, validating desktop, tablet, and mobile, taking screenshots, finding failures, fixing them, even adapting for low end hardware and low FPS before moving on. All these that Fable 5 never did. None of it because it wasn't able to run this WebGL app on a headless browser. Kimi also shipped a clean React + Three.js codebase with proper components while Fable, as you might have checked codebase, generated one big HTML file with everything stuffed in. With all of this happening, it felt like I was doing more "Vibe Coding" with Fable 5 and more "Vibe Engineering" with Kimi K3. It feels like it's spending more time making sure the code actually works and easily scalable. Really impressed so far. More Kimi K3 experiments coming soon. Code (Kimi): Code (Fable): Live (Kimi hosted):

The Bugged Dev

576,495 views • 19 days ago

With Kimi K3 Day-0 on vLLM: Open Frontier Intelligence for Everyone 🚀 At 2.8 trillion parameters, Moonshot AI's Kimi K3 is one of the most powerful open-weight models ever released. Starting today, you can serve it on vLLM the moment the weights are public. What K3 brings: 🧠 2.8T-parameter Mixture-of-Experts (16 of 896 experts active per token) 📚 1M-token context window 🛠️ Native multimodal understanding, including vision ⚡ Kimi Delta Attention: a hybrid of linear and full attention that makes million-token context affordable Huge thank you to Kimi.ai AI for the model release and partnership, Inferact for leading the vLLM optimizations, and to our partners at NVIDIA, AMD, and the broader vLLM community. 1/6

With Kimi K3 Day-0 on vLLM: Open Frontier Intelligence for Everyone 🚀 At 2.8 trillion parameters, Moonshot AI's Kimi K3 is one of the most powerful open-weight models ever released. Starting today, you can serve it on vLLM the moment the weights are public. What K3 brings: 🧠 2.8T-parameter Mixture-of-Experts (16 of 896 experts active per token) 📚 1M-token context window 🛠️ Native multimodal understanding, including vision ⚡ Kimi Delta Attention: a hybrid of linear and full attention that makes million-token context affordable Huge thank you to Kimi.ai AI for the model release and partnership, Inferact for leading the vLLM optimizations, and to our partners at NVIDIA, AMD, and the broader vLLM community. 1/6

vLLM

101,621 views • 12 days ago

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Ricardo

47,784 views • 19 days ago

$SITUATION EXPLAINED: Kimi K3 just beat Fable on a major coding benchmark, at a fraction of the price. • Kimi K3 beat Fable on Frontend Code Arena • The gap between Kimi and Fable is bigger than the gap between Fable and Sol • It also smashes Opus outright, while being priced the same as Sonnet, $3/$15 per million tokens • Sonnet 5 High currently sits in 10th place on this leaderboard at that same price point • The generational jump is dramatic: Kimi K2.6 ranked 18th on this benchmark, K3 jumped 17 spots to take the top spot • K3 ranked #1 in 6 of 7 tested domains: brand and marketing, reference-based design, data and analytics, consumer products, simulations, and content creation tools, it placed #2, only in gaming, behind Fable • Full model weights are set to release July 27th Theo Jaffee: "Imagine if Anthropic were a public company today, their stock would be down 20%, maybe more, enterprises are probably not gonna be spending $10 and $50 on Fable when they can instead be spending $3 and $15 on Kimi K3."$

SITUATION EXPLAINED: Kimi K3 just beat Fable on a major coding benchmark, at a fraction of the price. • Kimi K3 beat Fable on Frontend Code Arena • The gap between Kimi and Fable is bigger than the gap between Fable and Sol • It also smashes Opus outright, while being priced the same as Sonnet, $3/$15 per million tokens • Sonnet 5 High currently sits in 10th place on this leaderboard at that same price point • The generational jump is dramatic: Kimi K2.6 ranked 18th on this benchmark, K3 jumped 17 spots to take the top spot • K3 ranked #1 in 6 of 7 tested domains: brand and marketing, reference-based design, data and analytics, consumer products, simulations, and content creation tools, it placed #2, only in gaming, behind Fable • Full model weights are set to release July 27th Theo Jaffee: "Imagine if Anthropic were a public company today, their stock would be down 20%, maybe more, enterprises are probably not gonna be spending $10 and $50 on Fable when they can instead be spending $3 and $15 on Kimi K3."

MTS

132,633 views • 23 days ago

The Kimi AI Model And What If This Carnegie Mellon, PhD student was incentivized to open source AI in the US? The answer is Kimi would have been an open source US model. Yang Zhilin Moonshot’s founder and maker of the Kimi series turned his deep research expertise into one of the world’s most capable open AI systems. After earning his PhD at Carnegie Mellon under leading researchers and interning at Google Brain and Meta, he returned to China and co-founded Moonshot AI in March 2023 with Tsinghua classmates Zhou Xinyu and Wu Yuxin. Why? The US VC world and tax structure did not favor Zhilin’s proposal to open source the AI models as a strategy. So he left. He named the company after his favorite Pink Floyd album, reflecting his ambitious vision for scalable. Yang assembled a core technical team of inventors behind breakthroughs like Transformer-XL and RoPE. Together they focused on turning massive compute into efficient intelligence through innovative architectures. The journey began with the Kimi chatbot in October 2023, rapidly scaling context from 200,000 to millions of characters. This evolved into the Kimi series: K1.5 matched top reasoning models, K2 introduced a 1-trillion-parameter Mixture-of-Experts design trained on 15.5 trillion tokens and released openly, and K2 Thinking added advanced agentic capabilities. Kimi K3 represents the pinnacle, this 2.8-trillion-parameter model uses a sparse MoE architecture with 896 experts (only 16 active per token), new Kimi Delta Attention and attention residuals for efficiency, and a 1-million-token context window. It delivers frontier performance in long-horizon coding, reasoning, and multimodal tasks at competitive cost, with weights set for open release. Yang’s approach emphasizes openness, efficiency, and continuous self-improvement — enabling solo developers and teams to achieve what once required massive resources. By sharing technical insights in public talks, he has accelerated global progress toward more accessible, powerful AI. Imagine if we held open source higher than the fear theater games of Anthropic? We are chasing out some of the best minds. This is how you lose…

The Kimi AI Model And What If This Carnegie Mellon, PhD student was incentivized to open source AI in the US? The answer is Kimi would have been an open source US model. Yang Zhilin Moonshot’s founder and maker of the Kimi series turned his deep research expertise into one of the world’s most capable open AI systems. After earning his PhD at Carnegie Mellon under leading researchers and interning at Google Brain and Meta, he returned to China and co-founded Moonshot AI in March 2023 with Tsinghua classmates Zhou Xinyu and Wu Yuxin. Why? The US VC world and tax structure did not favor Zhilin’s proposal to open source the AI models as a strategy. So he left. He named the company after his favorite Pink Floyd album, reflecting his ambitious vision for scalable. Yang assembled a core technical team of inventors behind breakthroughs like Transformer-XL and RoPE. Together they focused on turning massive compute into efficient intelligence through innovative architectures. The journey began with the Kimi chatbot in October 2023, rapidly scaling context from 200,000 to millions of characters. This evolved into the Kimi series: K1.5 matched top reasoning models, K2 introduced a 1-trillion-parameter Mixture-of-Experts design trained on 15.5 trillion tokens and released openly, and K2 Thinking added advanced agentic capabilities. Kimi K3 represents the pinnacle, this 2.8-trillion-parameter model uses a sparse MoE architecture with 896 experts (only 16 active per token), new Kimi Delta Attention and attention residuals for efficiency, and a 1-million-token context window. It delivers frontier performance in long-horizon coding, reasoning, and multimodal tasks at competitive cost, with weights set for open release. Yang’s approach emphasizes openness, efficiency, and continuous self-improvement — enabling solo developers and teams to achieve what once required massive resources. By sharing technical insights in public talks, he has accelerated global progress toward more accessible, powerful AI. Imagine if we held open source higher than the fear theater games of Anthropic? We are chasing out some of the best minds. This is how you lose…

Brian Roemmele

37,185 views • 19 days ago

$THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system$

THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system

Gipp 🦅

16,989 views • 2 months ago

✨ Expansion Phase: Get your Access Code to the Closed Beta We’ve successfully completed the first phase of testing, and now it’s time for new players to enter the Pixelverse. Access Codes are being released—are you ready to claim yours? 🔓 How to get access? - Be Engaged! We’re rewarding our most active community members across Discord, Twitter, and PixelTap starting right now! - Stay Alert! Keep an eye on official announcements, the fastest and most engaged users will be rewarded with codes. - Redeem & Enter: Activate your Access Code in the Dashboard and jump into the Pixelverse! 🖼 NFT Holders Get Priority: Holding a Pixelverse NFT gives you a higher chance of securing an Access Code. ⏳ Act Fast and claim your place in Pixelverse! Only a limited number of Access Codes are being distributed. 🧠 And don’t forget—the Quest-Based Airdrop is coming soon! Secure your access now and get ready to unlock $PIXFI through in-game quests! ➡ Join Discord: DISCORD

✨ Expansion Phase: Get your Access Code to the Closed Beta We’ve successfully completed the first phase of testing, and now it’s time for new players to enter the Pixelverse. Access Codes are being released—are you ready to claim yours? 🔓 How to get access? - Be Engaged! We’re rewarding our most active community members across Discord, Twitter, and PixelTap starting right now! - Stay Alert! Keep an eye on official announcements, the fastest and most engaged users will be rewarded with codes. - Redeem & Enter: Activate your Access Code in the Dashboard and jump into the Pixelverse! 🖼 NFT Holders Get Priority: Holding a Pixelverse NFT gives you a higher chance of securing an Access Code. ⏳ Act Fast and claim your place in Pixelverse! Only a limited number of Access Codes are being distributed. 🧠 And don’t forget—the Quest-Based Airdrop is coming soon! Secure your access now and get ready to unlock $PIXFI through in-game quests! ➡ Join Discord: DISCORD

Pixelverse

294,275 views • 1 year ago

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 views • 9 months ago

Announcing Opcode Everyone's favorite Claude Code GUI Claudia is now Opcode... with a complete revamp. And we just hit 15K+ stars on GitHub! The support from the community has been immense! ❤️ What's new: - Feature parity with all new Claude Code features in the CLI. - A complete UI revamp, faster and cleaner. What's coming: - Opcode's own coding agent that exclusively uses open models while achieving SOTA performance on coding benchmarks. We're currently piloting this at companies requiring fully local on-prem coding agents. If you're one of them, reach out to us and we'll set this up for you! Try Opcode at opcode [dot] sh Like/retweet and reply to this tweet with "join" to get an invite to the Discord server and beta test our coding agent for free.

Announcing Opcode Everyone's favorite Claude Code GUI Claudia is now Opcode... with a complete revamp. And we just hit 15K+ stars on GitHub! The support from the community has been immense! ❤️ What's new: - Feature parity with all new Claude Code features in the CLI. - A complete UI revamp, faster and cleaner. What's coming: - Opcode's own coding agent that exclusively uses open models while achieving SOTA performance on coding benchmarks. We're currently piloting this at companies requiring fully local on-prem coding agents. If you're one of them, reach out to us and we'll set this up for you! Try Opcode at opcode [dot] sh Like/retweet and reply to this tweet with "join" to get an invite to the Discord server and beta test our coding agent for free.

winfunc

38,833 views • 11 months ago

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,593 views • 2 months ago

Kimi K2.7-Code is now available on AI/ML API! Moonshot's latest is built for long-horizon agentic coding that self-corrects instead of one-shotting. So we gave it a hard one. SpaceX is going public, a company built on one habit: fly, fail, fix, fly again. That loop carried Falcon to the droneship and Starship toward orbit. We wanted to see if a model could run that same loop on its own. We gave four Kimi agents a 2D flight-physics sim they can't modify and one goal: reach orbit and land the booster on a droneship. Flight 1 broke up at max-Q. Flight 2 cleared max-Q but staged too early and fell back short of orbit. Flight 3 made orbit, then missed the droneship and hit the water. Flight 4 fixed the landing math and put the booster on the ship. Four flights, each failure feeding the next fix. The interesting result isn't the rocket, it's the closed-loop debugging. Architecture in the comments. Got any ideas for droneship name?

Kimi K2.7-Code is now available on AI/ML API! Moonshot's latest is built for long-horizon agentic coding that self-corrects instead of one-shotting. So we gave it a hard one. SpaceX is going public, a company built on one habit: fly, fail, fix, fly again. That loop carried Falcon to the droneship and Starship toward orbit. We wanted to see if a model could run that same loop on its own. We gave four Kimi agents a 2D flight-physics sim they can't modify and one goal: reach orbit and land the booster on a droneship. Flight 1 broke up at max-Q. Flight 2 cleared max-Q but staged too early and fell back short of orbit. Flight 3 made orbit, then missed the droneship and hit the water. Flight 4 fixed the landing math and put the booster on the ship. Four flights, each failure feeding the next fix. The interesting result isn't the rocket, it's the closed-loop debugging. Architecture in the comments. Got any ideas for droneship name?

AI/ML API

23,966 views • 1 month ago

I'm giving away Claude Code for FREE. Yes, you read that right -- the world's best AI, now completely FREE. My mission is to get the next billion people to write great software. I believe EVERYONE should have access to the best AI, but so many are constrained by costs. I'm solving this by: disrupting the world's fastest growing industry = AI + with the most proven business model = Ads You can actually try it out now -- just one line of code, and you unlock all the powers of Claude Code, for free. how it works: 1. sign up on Giga AI Free 2. change Claude Code env variables to use our inference endpoint 2. to support the free usage, we'll add ads inside the AI responses (only contextual and relevant ads, no spam) Since we get too many signups, there's a waitlist, but we'll be rolling it out to the maximum people as we can. Watch the video to get started & comment and retweet to get access first.

I'm giving away Claude Code for FREE. Yes, you read that right -- the world's best AI, now completely FREE. My mission is to get the next billion people to write great software. I believe EVERYONE should have access to the best AI, but so many are constrained by costs. I'm solving this by: disrupting the world's fastest growing industry = AI + with the most proven business model = Ads You can actually try it out now -- just one line of code, and you unlock all the powers of Claude Code, for free. how it works: 1. sign up on Giga AI Free 2. change Claude Code env variables to use our inference endpoint 2. to support the free usage, we'll add ads inside the AI responses (only contextual and relevant ads, no spam) Since we get too many signups, there's a waitlist, but we'll be rolling it out to the maximum people as we can. Watch the video to get started & comment and retweet to get access first.

Namanyay

487,668 views • 9 months ago

Inviting early beta testers for our upcoming SWE agent, Asteria. We're solving AI code comprehension, where the context window and the size of your codebase are no longer limitations, and reinventing the UX of how coding agents are currently implemented. We initially built this to address false positives and enhance accuracy for our SAST agent, which autonomously identifies security vulnerabilities, traces how a payload would flow through code, and ultimately demonstrates an actual exploit. The performance improved so significantly that we decided to test it on realistic engineering tasks on large codebases and witnessed SOTA results. Reply "access" if you'd like to be an early beta tester, a lot of quirks to fix.

Inviting early beta testers for our upcoming SWE agent, Asteria. We're solving AI code comprehension, where the context window and the size of your codebase are no longer limitations, and reinventing the UX of how coding agents are currently implemented. We initially built this to address false positives and enhance accuracy for our SAST agent, which autonomously identifies security vulnerabilities, traces how a payload would flow through code, and ultimately demonstrates an actual exploit. The performance improved so significantly that we decided to test it on realistic engineering tasks on large codebases and witnessed SOTA results. Reply "access" if you'd like to be an early beta tester, a lot of quirks to fix.

mufeed vh

12,422 views • 1 year ago

🚨 This tool just made every AI coding plugin look outdated. Cline CLI 2.0 is a completely rebuilt, open-source AI coding agent that runs entirely in the terminal. Model-agnostic, editor-agnostic, Apache 2.0 licensed, and trusted by over 5 million developers. Same core engine as the VS Code extension rebuilt for how serious development actually happens. The new interactive UI feels genuinely native. Redesigned navigation, real-time agent reasoning, model switching mid-session, all without leaving the terminal. Parallel agents let multiple Cline instances run across tmux panes simultaneously, each with fully isolated state, working different tasks on different branches without conflicts. Headless mode with the `-y` flag plugs Cline directly into CI/CD pipelines, pipe a git diff in, get a code review out. And the `--acp` flag connects to Zed, Neovim, Emacs, and any ACP-compatible editor, so there's no forced editor choice. At launch, Minimax M2.5 and Kimi K2.5 are completely free. No API key. No credit card. Zero barrier to try it. `npm install -g cline` Docs → GitHub → The future of AI coding isn't a plugin. It's infrastructure.

🚨 This tool just made every AI coding plugin look outdated. Cline CLI 2.0 is a completely rebuilt, open-source AI coding agent that runs entirely in the terminal. Model-agnostic, editor-agnostic, Apache 2.0 licensed, and trusted by over 5 million developers. Same core engine as the VS Code extension rebuilt for how serious development actually happens. The new interactive UI feels genuinely native. Redesigned navigation, real-time agent reasoning, model switching mid-session, all without leaving the terminal. Parallel agents let multiple Cline instances run across tmux panes simultaneously, each with fully isolated state, working different tasks on different branches without conflicts. Headless mode with the `-y` flag plugs Cline directly into CI/CD pipelines, pipe a git diff in, get a code review out. And the `--acp` flag connects to Zed, Neovim, Emacs, and any ACP-compatible editor, so there's no forced editor choice. At launch, Minimax M2.5 and Kimi K2.5 are completely free. No API key. No credit card. Zero barrier to try it. `npm install -g cline` Docs → GitHub → The future of AI coding isn't a plugin. It's infrastructure.

AI Frontliner

60,126 views • 5 months ago

Sam on Kimi, distillation, and open source: “I have always assumed that there are going to be great cheap models in the world, and we better be the greatest and the cheapest. You get a better deal today, at least at a particular latency, using OpenAI's models than Kimi. We distill our own models. That’s how we make smaller, cheaper models. That’s a very good thing to do. There will clearly be an important place for open source models in the world and people that will want their own weights. We have so much usage of our models that we do not need to be a gigantically high-margin business to be able to afford model training. I would rather people not distill from us, for sure. But this is not in my top ten list of worries.”

Sam on Kimi, distillation, and open source: “I have always assumed that there are going to be great cheap models in the world, and we better be the greatest and the cheapest. You get a better deal today, at least at a particular latency, using OpenAI's models than Kimi. We distill our own models. That’s how we make smaller, cheaper models. That’s a very good thing to do. There will clearly be an important place for open source models in the world and people that will want their own weights. We have so much usage of our models that we do not need to be a gigantically high-margin business to be able to afford model training. I would rather people not distill from us, for sure. But this is not in my top ten list of worries.”

Patrick OShaughnessy

267,170 views • 11 days ago