Загрузка видео...

Не удалось загрузить видео

На главную

🎙️ 🚨 Latest State of Agentic Coding w/ special guest @mariozechner (Flask) is out: - Vibe-checking Fable & GLM 5.2 - Armin Ronacher ⇌ teaches us RL - How harnesses smooth out model jank - Loops, surviving AI fomo, and more Also on YT & Spotify ⬇️

bentlegen's profile picture

Ben Vinegar

12,545 subscribers

70,868 просмотров • 1 месяц назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🎙️ State of Agentic Coding with Armin Ronacher ⇌ and Ben returns In this episode: - how Armin teamed up w/ Mario Zechner on Pi - the end of subsidized tokens? - why coding traces are valuable - GitHub, what might come next, and more!
1:38:22

🎙️ State of Agentic Coding with Armin Ronacher ⇌ and Ben returns In this episode: - how Armin teamed up w/ Mario Zechner on Pi - the end of subsidized tokens? - why coding traces are valuable - GitHub, what might come next, and more!

Ben Vinegar

96,999 просмотров • 3 месяцев назад

🎙️ State of Agentic Coding w/ Armin Ronacher ⇌ and Ben Vinegar returns In this episode (#9): - how agents are getting more autonomous - the subsidies will continue until morale improves - herdr and VC-funded terminal apps - vibe coding from your car, and more!
1:24:43

🎙️ State of Agentic Coding w/ Armin Ronacher ⇌ and Ben Vinegar returns In this episode (#9): - how agents are getting more autonomous - the subsidies will continue until morale improves - herdr and VC-funded terminal apps - vibe coding from your car, and more!

Ben Vinegar

45,298 просмотров • 17 дней назад

Our latest episode of "Courtside conversations" is out, w/ Gigi Salmon & Alize Cornet 🎙️ Listen now on Spotify, Deezer and YouTube 🎧
1:47

Our latest episode of "Courtside conversations" is out, w/ Gigi Salmon & Alize Cornet 🎙️ Listen now on Spotify, Deezer and YouTube 🎧

Roland-Garros

11,623 просмотров • 8 месяцев назад

The future of ML is being built on W&B. Come find out how at our MLOps conference, Fully Connected on March 15! 🐝 Register at Featuring speakers from Stability AI, Spotify, NVIDIA AI, Openai; people like Jeremy Howard, Shreya Shankar, Hamel Husain & more!
0:30

The future of ML is being built on W&B. Come find out how at our MLOps conference, Fully Connected on March 15! 🐝 Register at Featuring speakers from Stability AI, Spotify, NVIDIA AI, Openai; people like Jeremy Howard, Shreya Shankar, Hamel Husain & more!

Lavanya

14,464 просмотров • 3 лет назад

Serving GLM5.2 NVFP4 Agentic Workload with SGLang: How We Reached 500 TPS on 8xB300 at bs=1 In this deep dive, we explain how SGLang reaches 500+ tok/s/user at bs=1 on 8xB300, with 18 to 34% higher single-user interactivity within two weeks since day-0, and 6 to 11% better peak throughput at high concurrency, benchmarked on a real multi-turn agentic coding workload. Our new TopK-V2 kernel is 2.33x faster at 80K ISL, scaling to 10.17x at 1M ISL, keeping interactivity essentially flat out to 1M tokens. Part of the story is the architecture itself. GLM-5.2 applies IndexShare to its DSA layers and ships a stronger MTP head reusing IndexShare and KVShare. The rest comes from our serving optimizations. Special thanks to NVIDIA AI for the help in day-0 support of GLM-5.2 NVFP4, and to Z.ai for IndexShare in SGLang!
0:47

Serving GLM5.2 NVFP4 Agentic Workload with SGLang: How We Reached 500 TPS on 8xB300 at bs=1 In this deep dive, we explain how SGLang reaches 500+ tok/s/user at bs=1 on 8xB300, with 18 to 34% higher single-user interactivity within two weeks since day-0, and 6 to 11% better peak throughput at high concurrency, benchmarked on a real multi-turn agentic coding workload. Our new TopK-V2 kernel is 2.33x faster at 80K ISL, scaling to 10.17x at 1M ISL, keeping interactivity essentially flat out to 1M tokens. Part of the story is the architecture itself. GLM-5.2 applies IndexShare to its DSA layers and ships a stronger MTP head reusing IndexShare and KVShare. The rest comes from our serving optimizations. Special thanks to NVIDIA AI for the help in day-0 support of GLM-5.2 NVFP4, and to Z.ai for IndexShare in SGLang!

LMSYS Org

107,317 просмотров • 1 месяц назад

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.
28:28

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Movez

16,536 просмотров • 1 месяц назад

Episode 2 of How I AI is live, featuring farhad manjoo (former bluecheck), writer & former columnist for the NYT and the WSJ. Farhad walks us through how he *improves* the quality of his writing with AI, by using ChatGPT to - do deep research on topics - act as a “super thesaurus” - be his “always on” writing companion I love this ep because it’s an accessible example of AI in practice for the less technical out there (no vibe coding!) Plus, my little liberal arts heart loves finding a good idiom. Check it out (25 mins): YT: Spotify: Apple: And a true thanks to our sponsors for supporting the show 🧠 Enterpret - SuperIntelligence for Product and CX teams ☑️ Vanta - Simplify AI compliance
1:11

Episode 2 of How I AI is live, featuring farhad manjoo (former bluecheck), writer & former columnist for the NYT and the WSJ. Farhad walks us through how he *improves* the quality of his writing with AI, by using ChatGPT to - do deep research on topics - act as a “super thesaurus” - be his “always on” writing companion I love this ep because it’s an accessible example of AI in practice for the less technical out there (no vibe coding!) Plus, my little liberal arts heart loves finding a good idiom. Check it out (25 mins): YT: Spotify: Apple: And a true thanks to our sponsors for supporting the show 🧠 Enterpret - SuperIntelligence for Product and CX teams ☑️ Vanta - Simplify AI compliance

claire vo 🖤

22,740 просмотров • 1 год назад

Always enjoy getting to chat with swyx 🇸🇬 AIE Singapore! on our annual cross-episode with Latent.Space on the state of AI. We hit on what’s shifted, what surprised us and what’s next. We covered: ▪️ Whether AI infrastructure has finally stabilized ▪️ Implications of agents buying developer tools ▪️ The AI coding wars ▪️ The foundation model vibe shift ▪️ Why Swyx reversed his view on open models ▪️ When to train your own model ▪️ What's top of mind for the best AI engineers YouTube: Spotify: Apple: 0:00 Intro 1:17 What the Top AI Engineers Are Thinking About 2:13 Has AI Infra Finally Stabilized? 6:39 When Does Doing RL In-House Make Sense? 11:26 Why Selling Dev Tools to Agents is Different 17:18 AI Coding Wars 29:04 Consumer AI Plateau 30:22 Codex vs Claude Code 44:52 Future of Open Models
54:52

Always enjoy getting to chat with swyx 🇸🇬 AIE Singapore! on our annual cross-episode with Latent.Space on the state of AI. We hit on what’s shifted, what surprised us and what’s next. We covered: ▪️ Whether AI infrastructure has finally stabilized ▪️ Implications of agents buying developer tools ▪️ The AI coding wars ▪️ The foundation model vibe shift ▪️ Why Swyx reversed his view on open models ▪️ When to train your own model ▪️ What's top of mind for the best AI engineers YouTube: Spotify: Apple: 0:00 Intro 1:17 What the Top AI Engineers Are Thinking About 2:13 Has AI Infra Finally Stabilized? 6:39 When Does Doing RL In-House Make Sense? 11:26 Why Selling Dev Tools to Agents is Different 17:18 AI Coding Wars 29:04 Consumer AI Plateau 30:22 Codex vs Claude Code 44:52 Future of Open Models

Jacob Effron

18,282 просмотров • 4 месяцев назад

🎙️ New Deployed episode with Ryan Carson, "Builder in Residence" at Amp. It's a great convo about building code agents and building as a solo founder at the same time, and it's refreshingly honest. Case in point, on evals for coding agents: "We do not have a set of evals that we programmatically run to decide if GPT-5 is better than Sonnet-4 yet... everybody in the trenches building these agentic coding tools understands that it is so dynamic, and so frustrating." Great conversation about building with AI, developer experience, and what happens when everyone can code. Check it out. 👇
2:02

🎙️ New Deployed episode with Ryan Carson, "Builder in Residence" at Amp. It's a great convo about building code agents and building as a solo founder at the same time, and it's refreshingly honest. Case in point, on evals for coding agents: "We do not have a set of evals that we programmatically run to decide if GPT-5 is better than Sonnet-4 yet... everybody in the trenches building these agentic coding tools understands that it is so dynamic, and so frustrating." Great conversation about building with AI, developer experience, and what happens when everyone can code. Check it out. 👇

Ian Cairns

250,866 просмотров • 11 месяцев назад

Claude Fable 5 early tester: "If you're using Fable 5 for everything, that is almost 100% overkill." in 10 minutes, Nate breaks down the six prompting habits that actually get the most out of it here's what he covers: > always give the why, not just the what > negative prompting: tell it exactly what not to do > baking verification loops into every agent and skill file > the one prompt type that silently downgrades you to a weaker model most people are just throwing longer prompts at a more expensive model the ones getting real results changed how they prompt, not how much they spend an article on how to build a fully automated AI company with Claude Fable 5 👇
10:44

Claude Fable 5 early tester: "If you're using Fable 5 for everything, that is almost 100% overkill." in 10 minutes, Nate breaks down the six prompting habits that actually get the most out of it here's what he covers: > always give the why, not just the what > negative prompting: tell it exactly what not to do > baking verification loops into every agent and skill file > the one prompt type that silently downgrades you to a weaker model most people are just throwing longer prompts at a more expensive model the ones getting real results changed how they prompt, not how much they spend an article on how to build a fully automated AI company with Claude Fable 5 👇

rewind

11,868 просмотров • 2 месяцев назад

New course to bring you up to state-of-the-art at using AI to help you code: Build Apps with Windsurf's AI Coding Agents, built in partnership with WIndsurf (Codeium) and taught by Anshul Ramachandran! AI-assisted IDEs (Integrated Development Environments) make developers’ workflows faster, more efficient, and much more fun. Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Although a lot of coding assistants share the same underlying large language models for planning and reasoning, a major point of distinction is how they handle tools, keep track of context, and stay aligned with your intent as a developer. For instance, if you make modifications to a class definition in your code and make the same modifications to other classes in the same directory, you might tell the AI agent "Do the same thing in similar places in this directory." Here, tracking your intent means understanding that “the same thing" refers to that recent edit you just made, which must be followed by appropriate search and tool-calling to implement the changes. In this course, you'll learn the inner workings of coding agents, their strengths and limitations, and how to use Windsurf to quickly build several applications. In detail, you'll: - Build a mental model of how agents work by combining human-action tracking, tool integration, and context awareness to carry out an agentic coding workflow. - Learn the challenges of code search and discovery and how a multi-step retrieval approach helps coding agents address them. - Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. - Build a Wikipedia data analysis app that retrieves, parses, and analyzes word frequencies. - Enhance the performance of your Wikipedia analysis app by adding caching, and through this, also learn how to course-correct when the AI agent produces unexpected results. - Learn tips and tricks such as keyboard shortcuts, autocomplete, and @ mentions to quickly call on agentic capabilities. - Use image/multimodal capabilities of the AI agent to increase your development velocity; you'll see an example of uploading a mockup with sketched-out UI features, and ask the agent to use that to build new functionality to an app. By the end of this course, you’ll understand agentic coding in-depth and know how to use it to make your development process much faster, more efficient, and enjoyable. Please sign up here!
4:01

New course to bring you up to state-of-the-art at using AI to help you code: Build Apps with Windsurf's AI Coding Agents, built in partnership with WIndsurf (Codeium) and taught by Anshul Ramachandran! AI-assisted IDEs (Integrated Development Environments) make developers’ workflows faster, more efficient, and much more fun. Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Although a lot of coding assistants share the same underlying large language models for planning and reasoning, a major point of distinction is how they handle tools, keep track of context, and stay aligned with your intent as a developer. For instance, if you make modifications to a class definition in your code and make the same modifications to other classes in the same directory, you might tell the AI agent "Do the same thing in similar places in this directory." Here, tracking your intent means understanding that “the same thing" refers to that recent edit you just made, which must be followed by appropriate search and tool-calling to implement the changes. In this course, you'll learn the inner workings of coding agents, their strengths and limitations, and how to use Windsurf to quickly build several applications. In detail, you'll: - Build a mental model of how agents work by combining human-action tracking, tool integration, and context awareness to carry out an agentic coding workflow. - Learn the challenges of code search and discovery and how a multi-step retrieval approach helps coding agents address them. - Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. - Build a Wikipedia data analysis app that retrieves, parses, and analyzes word frequencies. - Enhance the performance of your Wikipedia analysis app by adding caching, and through this, also learn how to course-correct when the AI agent produces unexpected results. - Learn tips and tricks such as keyboard shortcuts, autocomplete, and @ mentions to quickly call on agentic capabilities. - Use image/multimodal capabilities of the AI agent to increase your development velocity; you'll see an example of uploading a mockup with sketched-out UI features, and ask the agent to use that to build new functionality to an app. By the end of this course, you’ll understand agentic coding in-depth and know how to use it to make your development process much faster, more efficient, and enjoyable. Please sign up here!

Andrew Ng

139,978 просмотров • 1 год назад

Announcing Superblocks on Snowflake: Secure Enterprise Vibe Coding on the AI Data Cloud This couldn't be more timely. Vibe coding is exploding inside the enterprise. It’s also becoming the fastest path to a data breach. Every CEO is trying to accelerate adoption of vibe coding for business users automate, without blocking on engineering. Every VP of Data and CIO is trying to figure out how to lock down their data, harden their permissions, and gain centralized visibility. That’s exactly what this partnership unlocks. Superblocks becomes the enterprise platform for governed vibe coding across business teams, deeply embedded within Snowflake: > Snowflake Postgres becomes your secure vibe coding database. Superblocks spins it up in every app for fast writes and net new operational workflow data >Snowflake Cortex becomes the inference engine for Superblocks. Your prompts and vibe coded AI features run within your trusted security perimeter >Snowflake Warehouse governance is enforced. AI apps use federated token passthrough so your existing row level access policies, dynamic data masking, tag-based-access controls are respected “With Superblocks on Snowflake, any business team can safely build AI applications governed on their Snowflake data. It’s a dream come true.” -Unmesh Jagtap, Director of Product, Snowflake Now enterprises can stop playing whack-a-mole, and move your organization past the AI prototype graveyard. If you’re a Snowflake customer, book a demo (link in comments) Thanks to the Snowflake team for the partnership: Christian Kleinerman, Vivek Raghunathan, Bala Kasiviswanathan, Unmesh Jagtap, and Myles Borins for helping shape how the industry democratizes governed AI app development while centralizing control on the AI Data Cloud.
2:39

Announcing Superblocks on Snowflake: Secure Enterprise Vibe Coding on the AI Data Cloud This couldn't be more timely. Vibe coding is exploding inside the enterprise. It’s also becoming the fastest path to a data breach. Every CEO is trying to accelerate adoption of vibe coding for business users automate, without blocking on engineering. Every VP of Data and CIO is trying to figure out how to lock down their data, harden their permissions, and gain centralized visibility. That’s exactly what this partnership unlocks. Superblocks becomes the enterprise platform for governed vibe coding across business teams, deeply embedded within Snowflake: > Snowflake Postgres becomes your secure vibe coding database. Superblocks spins it up in every app for fast writes and net new operational workflow data >Snowflake Cortex becomes the inference engine for Superblocks. Your prompts and vibe coded AI features run within your trusted security perimeter >Snowflake Warehouse governance is enforced. AI apps use federated token passthrough so your existing row level access policies, dynamic data masking, tag-based-access controls are respected “With Superblocks on Snowflake, any business team can safely build AI applications governed on their Snowflake data. It’s a dream come true.” -Unmesh Jagtap, Director of Product, Snowflake Now enterprises can stop playing whack-a-mole, and move your organization past the AI prototype graveyard. If you’re a Snowflake customer, book a demo (link in comments) Thanks to the Snowflake team for the partnership: Christian Kleinerman, Vivek Raghunathan, Bala Kasiviswanathan, Unmesh Jagtap, and Myles Borins for helping shape how the industry democratizes governed AI app development while centralizing control on the AI Data Cloud.

Brad Menezes

13,209 просмотров • 4 месяцев назад

Dylan Patel says GPUs are no longer the biggest bottleneck. According to Dylan Patel, now CPUs are the constraint. In the early AI era, CPUs were the laggers. You used them for storage, checkpointing, pre-processing, etc. (pretty light workloads) The models weren't agentic and couldn't go step by step. Just string in and string out (simple inference) Then OpenAI launched O1 preview in September '24, and RL training loops have since tightened every month. - initially it was checking model output with regex - then running classifiers - followed by code unit tests + compilation - and finally agentic flows calling databases & scientific simulations The model outputs to an environment, gets verified, and trains on it. Coding agent revenue went from a couple billion to north of $10B in roughly 6 months. Something like Codex 5.4 can work agentically on its own for 6-7 hrs straight - doing all sorts of calls (databases, cron servers, scraping) That requires insane CPU capabilities. And over the last two quarters, the entire cloud market ran out of CPUs. - GitHub has been really unstable lately - Amazon's CPU server installations 3x'd year over year - Microsoft sold all of its spare CPUs to Anthropic & OpenAI Earlier, it was 100 megawatts of GPUs served by 1 megawatt of CPUs. Now that ratio is getting much closer for both RL training and agentic inference. There's simply no capacity anywhere, and it's causing massive instability.
3:54

Dylan Patel says GPUs are no longer the biggest bottleneck. According to Dylan Patel, now CPUs are the constraint. In the early AI era, CPUs were the laggers. You used them for storage, checkpointing, pre-processing, etc. (pretty light workloads) The models weren't agentic and couldn't go step by step. Just string in and string out (simple inference) Then OpenAI launched O1 preview in September '24, and RL training loops have since tightened every month. - initially it was checking model output with regex - then running classifiers - followed by code unit tests + compilation - and finally agentic flows calling databases & scientific simulations The model outputs to an environment, gets verified, and trains on it. Coding agent revenue went from a couple billion to north of $10B in roughly 6 months. Something like Codex 5.4 can work agentically on its own for 6-7 hrs straight - doing all sorts of calls (databases, cron servers, scraping) That requires insane CPU capabilities. And over the last two quarters, the entire cloud market ran out of CPUs. - GitHub has been really unstable lately - Amazon's CPU server installations 3x'd year over year - Microsoft sold all of its spare CPUs to Anthropic & OpenAI Earlier, it was 100 megawatts of GPUs served by 1 megawatt of CPUs. Now that ratio is getting much closer for both RL training and agentic inference. There's simply no capacity anywhere, and it's causing massive instability.

Ivan Burazin

303,474 просмотров • 4 месяцев назад

MiniMax M2.1 is really good for writing code. It's open source, and you can connect Visual Studio Code to it and start coding right away. The model is especially good for those who don't use Python as a primary language. It's currently the best multilingual model out there. The model hits 72.5% on SWE-Multilingual and 88.6% on VIBE-Bench (best!) This means the model is also really good at performing real engineering work and does very well at agentic tasks: • Long tool chains • Structured agent scaffolding • Following repo-level rules and slash commands • Working inside existing agent frameworks without falling apart And obviously, it's faster, cheaper, and more concise than M2, which was already really good. I recorded a video to show you how to run MiniMax (official)'s 2.1 using Visual Studio Code.
5:45

MiniMax M2.1 is really good for writing code. It's open source, and you can connect Visual Studio Code to it and start coding right away. The model is especially good for those who don't use Python as a primary language. It's currently the best multilingual model out there. The model hits 72.5% on SWE-Multilingual and 88.6% on VIBE-Bench (best!) This means the model is also really good at performing real engineering work and does very well at agentic tasks: • Long tool chains • Structured agent scaffolding • Following repo-level rules and slash commands • Working inside existing agent frameworks without falling apart And obviously, it's faster, cheaper, and more concise than M2, which was already really good. I recorded a video to show you how to run MiniMax (official)'s 2.1 using Visual Studio Code.

Santiago

47,879 просмотров • 7 месяцев назад

Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–Snorkel AI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D! --- Snorkel Evaluate is our new data-centric agentic AI evaluation platform for specialized, mission-critical enterprise settings where vibe checks and out-of-the-box metrics driven by simple LLM prompts are not enough. Snorkel Expert Data-as-a-Service is our white glove service for expert-level AI datasets, powering frontier LLM developers in areas like expert knowledge, reasoning, agentic action and tool use, and more! Both built on top of Snorkel AI’s Data Development Platform, using our programmatic technology to drive higher-quality expert data, faster– for getting specialized AI to real production value. If you’re building enterprise AI and want to partner around the key ingredient in AI today–the data–book a demo and let's talk! Finally, see thread for details on 🧵👇 - 📽️ A walkthrough of Snorkel Evaluate and Expert Data-as-a-Service on an agentic AI enterprise task - 📅 An upcoming event on Enterprise Agentic AI with innovators from Accenture @BNY Comcast Stanford University QBE & others - 📊 An upcoming series of benchmark datasets and model artifact releases 👀 Want early access to the full agentic AI dataset? Retweet this post and we'll send you the link!
5:42

Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–Snorkel AI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D! --- Snorkel Evaluate is our new data-centric agentic AI evaluation platform for specialized, mission-critical enterprise settings where vibe checks and out-of-the-box metrics driven by simple LLM prompts are not enough. Snorkel Expert Data-as-a-Service is our white glove service for expert-level AI datasets, powering frontier LLM developers in areas like expert knowledge, reasoning, agentic action and tool use, and more! Both built on top of Snorkel AI’s Data Development Platform, using our programmatic technology to drive higher-quality expert data, faster– for getting specialized AI to real production value. If you’re building enterprise AI and want to partner around the key ingredient in AI today–the data–book a demo and let's talk! Finally, see thread for details on 🧵👇 - 📽️ A walkthrough of Snorkel Evaluate and Expert Data-as-a-Service on an agentic AI enterprise task - 📅 An upcoming event on Enterprise Agentic AI with innovators from Accenture @BNY Comcast Stanford University QBE & others - 📊 An upcoming series of benchmark datasets and model artifact releases 👀 Want early access to the full agentic AI dataset? Retweet this post and we'll send you the link!

Alex Ratner

50,043 просмотров • 1 год 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 👇
0:33

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 • 2 месяцев назад

BREAKING: GPT-5.6 Sol is out—AND Codex has been merged into ChatGPT Desktop as ChatGPT Codex. This combo model and desktop app harness are the gold-standard for knowledge work in AI. 5.6 is powerful, fast, half the price of Fable, and my default for almost everything. We’ve been testing it internally Every 🪨 for about a month across coding, writing, design, and knowledge work. Here’s our day-zero vibe check: - An A-tier coder—but it’s not Fable. Sol scored 56/100 on our Senior Engineer benchmark compared to a 91 for Fable. I think the 56/100 undersells it, it's an excellent implementor, and very smart. But Fable just writes conceptually cleaner code and works better at the top end of task complexity. PRO-TIP: Use GPT-5.6 as Fable's subagent for the most goated combo in AI coding. - The best writer of the frontier models. It’s clearer and more concise than Fable or Opus 4.8, without the overexplaining or weird private language. It can one-shot marketing emails, help you workshop taglines, and explain complex concepts clearly. It's also super fast, which makes it easy to collaborate with. - Design is better, but not top-tier. It has noticeably more taste than 5.5, but Fable and Opus 4.8 are still playing at a different level. See examples in the video and vibe check below. - The real leap is knowledge work. Sol is the first model I’ve trusted to run whole loops of knowledge work—not just help with individual tasks. I use it to process email, surface decisions from meetings and Slack, find job candidates, scan Facebook Marketplace for furniture, and log my meals. It has shifted my job from doing the work to tending the system that does it. - The merged app is fine. I was extremely worried about this because I love the Codex app. OpenAI was caught in an interesting position: How to make an agent orchestration app for regular ChatGPT consumers, coders, and businesses all in one app. They now split the interface between ChatGPT Work and ChatGPT Codex. They're basically the same except Work hides code. And "Chat" has been demoted to 2nd tier status for quick questions in either one. It's not a big leap, but it's not a huge setback either. And it remains my favorite of the desktop agent orchestration apps. Verdict: If I really had to put my finger on it, I'd say Fable has way more big model smell. But that means it's a skill in itself to get value out of it—99% of people are still not there yet. GPT-5.6 is almost as powerful, but is easy to use, fast, and relatively cheap. It should give you an early sense of where model work is going. Full Every 🪨 Vibe Check:
13:34

BREAKING: GPT-5.6 Sol is out—AND Codex has been merged into ChatGPT Desktop as ChatGPT Codex. This combo model and desktop app harness are the gold-standard for knowledge work in AI. 5.6 is powerful, fast, half the price of Fable, and my default for almost everything. We’ve been testing it internally Every 🪨 for about a month across coding, writing, design, and knowledge work. Here’s our day-zero vibe check: - An A-tier coder—but it’s not Fable. Sol scored 56/100 on our Senior Engineer benchmark compared to a 91 for Fable. I think the 56/100 undersells it, it's an excellent implementor, and very smart. But Fable just writes conceptually cleaner code and works better at the top end of task complexity. PRO-TIP: Use GPT-5.6 as Fable's subagent for the most goated combo in AI coding. - The best writer of the frontier models. It’s clearer and more concise than Fable or Opus 4.8, without the overexplaining or weird private language. It can one-shot marketing emails, help you workshop taglines, and explain complex concepts clearly. It's also super fast, which makes it easy to collaborate with. - Design is better, but not top-tier. It has noticeably more taste than 5.5, but Fable and Opus 4.8 are still playing at a different level. See examples in the video and vibe check below. - The real leap is knowledge work. Sol is the first model I’ve trusted to run whole loops of knowledge work—not just help with individual tasks. I use it to process email, surface decisions from meetings and Slack, find job candidates, scan Facebook Marketplace for furniture, and log my meals. It has shifted my job from doing the work to tending the system that does it. - The merged app is fine. I was extremely worried about this because I love the Codex app. OpenAI was caught in an interesting position: How to make an agent orchestration app for regular ChatGPT consumers, coders, and businesses all in one app. They now split the interface between ChatGPT Work and ChatGPT Codex. They're basically the same except Work hides code. And "Chat" has been demoted to 2nd tier status for quick questions in either one. It's not a big leap, but it's not a huge setback either. And it remains my favorite of the desktop agent orchestration apps. Verdict: If I really had to put my finger on it, I'd say Fable has way more big model smell. But that means it's a skill in itself to get value out of it—99% of people are still not there yet. GPT-5.6 is almost as powerful, but is easy to use, fast, and relatively cheap. It should give you an early sense of where model work is going. Full Every 🪨 Vibe Check:

Dan Shipper 📧

146,015 просмотров • 1 месяц назад

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?
26:21

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

Pat Grady

65,994 просмотров • 22 дней назад

OpenClaw - the agentic software spreading like wildfire - was built on top of Pi, a minimalist, self-modifying agent. I sat down with Pi's creator, Mario Zechner and longtime Pi user (+ the creator of Flask) Armin Ronacher ⇌ to talk Pi, and their (very grounded!) takes on building with AI. Timestamps: 00:00 Intro 07:30 How Mario, Armin, and Peter Steinberger met 15:15 How 30 dev teams use AI agents: learnings 21:50 The importance of judgment 24:26 Challenges when non-engineers write code 28:30 Downsides of over-automation 32:18 Pi 48:09 OpenClaw + Pi 50:54 “Clankers” 57:32 Open source and AI 1:00:22 Complexity as the enemy 1:02:50 Building an AI-native startup 1:11:52 “Slow the F down” 1:16:40 MCPs vs. CLI 1:25:03 Predictions and staying up to date • YouTube: • Spotify: • Apple: Brought to you by: • Statsig – ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar — The makers of SonarQube, the industry standard for code verification and automated code review. Try it out for yourself. • WorkOS – WorkOS gives you APIs to ship enterprise features – SSO, directory sync, RBAC, audit logs – in days, not months. Visit learn more. --- Three parts I found especially interesting in this discussion: 1. New trend: AI makes it harder for senior engineers to reject pointless complexity. Historically, senior engineers kept software complexity at bay simply by saying “no” a lot. But Armin observes that these days, more junior engineers and product managers deploy agent-scripted counterarguments when a senior colleague kicks an idea to the curb. This makes decision-making exhausting, and more bad ideas make it into production as a result. 2. It should be MUCH easier to build specialized tools for specific tasks. Different projects need different harness types because, as Mario points out, the same hammer is not ideal for every single construction job. As such, Pi is built with the goal of allowing the creation of specialized harnesses. It can modify itself so that a user can create the bespoke harness needed for any task. Mario believes it’s a preview of how self-modifiable software might look in the future. 3. Automation bias is one of the biggest risks of working with AI agents. Once devs confirm that an AI agent can produce acceptable code, they start to review its output less often, even though agents can – and do! – produce slop. Mario advises being far more sceptical with agents, and cautions that the quality of their output isn’t guaranteed, however well they performed previously.
1:33:55

OpenClaw - the agentic software spreading like wildfire - was built on top of Pi, a minimalist, self-modifying agent. I sat down with Pi's creator, Mario Zechner and longtime Pi user (+ the creator of Flask) Armin Ronacher ⇌ to talk Pi, and their (very grounded!) takes on building with AI. Timestamps: 00:00 Intro 07:30 How Mario, Armin, and Peter Steinberger met 15:15 How 30 dev teams use AI agents: learnings 21:50 The importance of judgment 24:26 Challenges when non-engineers write code 28:30 Downsides of over-automation 32:18 Pi 48:09 OpenClaw + Pi 50:54 “Clankers” 57:32 Open source and AI 1:00:22 Complexity as the enemy 1:02:50 Building an AI-native startup 1:11:52 “Slow the F down” 1:16:40 MCPs vs. CLI 1:25:03 Predictions and staying up to date • YouTube: • Spotify: • Apple: Brought to you by: • Statsig – ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar — The makers of SonarQube, the industry standard for code verification and automated code review. Try it out for yourself. • WorkOS – WorkOS gives you APIs to ship enterprise features – SSO, directory sync, RBAC, audit logs – in days, not months. Visit learn more. --- Three parts I found especially interesting in this discussion: 1. New trend: AI makes it harder for senior engineers to reject pointless complexity. Historically, senior engineers kept software complexity at bay simply by saying “no” a lot. But Armin observes that these days, more junior engineers and product managers deploy agent-scripted counterarguments when a senior colleague kicks an idea to the curb. This makes decision-making exhausting, and more bad ideas make it into production as a result. 2. It should be MUCH easier to build specialized tools for specific tasks. Different projects need different harness types because, as Mario points out, the same hammer is not ideal for every single construction job. As such, Pi is built with the goal of allowing the creation of specialized harnesses. It can modify itself so that a user can create the bespoke harness needed for any task. Mario believes it’s a preview of how self-modifiable software might look in the future. 3. Automation bias is one of the biggest risks of working with AI agents. Once devs confirm that an AI agent can produce acceptable code, they start to review its output less often, even though agents can – and do! – produce slop. Mario advises being far more sceptical with agents, and cautions that the quality of their output isn’t guaranteed, however well they performed previously.

Gergely Orosz

172,936 просмотров • 4 месяцев назад