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

RL post-training on Macs 14 Macs across 4 countries generate every rollout for the run. Everything's running over the internet. No wire between any of them. As far as we can tell, this is the first RL post-training run with its whole rollout fleet on consumer Macs.

Pluralis Research

13,407 subscribers

34,606 просмотров • 29 дней назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🥳Big news: Rewind is coming to Windows! Today I shared the keynote stage with Intel CEO Pat Gelsinger to demo Rewind on Windows. The demo includes Ask Rewind powered by Llama 2 running entirely locally! Bonus: As of today, Rewind can also run on Intel-based Macs! (1/4)

🥳Big news: Rewind is coming to Windows! Today I shared the keynote stage with Intel CEO Pat Gelsinger to demo Rewind on Windows. The demo includes Ask Rewind powered by Llama 2 running entirely locally! Bonus: As of today, Rewind can also run on Intel-based Macs! (1/4)

Dan Siroker

399,591 просмотров • 2 лет назад

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

h100envy

39,620 просмотров • 1 месяц назад

UNITED AIRLINES GOES ALL-IN ON STARLINK—FULL FLEET UPGRADE BY 2026 United Airlines is aiming high—every one of its 300 regional jets will be rocking Starlink internet by 2026! Rollout begins in May, following FAA approval for its first Starlink-equipped aircraft. •⁠ ⁠Free Wi-Fi at 35,000 Feet – MileagePlus members get blazing-fast internet with zero fees. •⁠ ⁠50x Faster Speeds – Stream, shop, and game like you’re on the ground. •⁠ ⁠Full-Throttle Rollout – 40 aircraft a month will join the Starlink fleet. This is just the beginning—United Airlines is taking off into a new era of connectivity! Source: NY Post

UNITED AIRLINES GOES ALL-IN ON STARLINK—FULL FLEET UPGRADE BY 2026 United Airlines is aiming high—every one of its 300 regional jets will be rocking Starlink internet by 2026! Rollout begins in May, following FAA approval for its first Starlink-equipped aircraft. •⁠ ⁠Free Wi-Fi at 35,000 Feet – MileagePlus members get blazing-fast internet with zero fees. •⁠ ⁠50x Faster Speeds – Stream, shop, and game like you’re on the ground. •⁠ ⁠Full-Throttle Rollout – 40 aircraft a month will join the Starlink fleet. This is just the beginning—United Airlines is taking off into a new era of connectivity! Source: NY Post

Mario Nawfal

16,500,405 просмотров • 1 год назад

Total War: ROME II - Emperor Edition returns to macOS on May 29th! This Apple Silicon-native port makes the game playable on modern Macs for the first time. Owners of ROME II on Steam can upgrade at no extra cost! Learn more:

Total War: ROME II - Emperor Edition returns to macOS on May 29th! This Apple Silicon-native port makes the game playable on modern Macs for the first time. Owners of ROME II on Steam can upgrade at no extra cost! Learn more:

Feral Interactive

27,010 просмотров • 1 год назад

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

gensyn

228,906 просмотров • 1 год назад

Wake the world's sleeping compute. Look at the Mac nearest to you. What's it doing? Probably nothing. There are 100M+ Macs with Apple Silicon out there. Apple quietly made them *really* good at inference. A $3k Mac runs a 60B model at 30 watts. Most sit idle most of the day. Meanwhile every AI API call passes through three layers of margin before reaching the hardware. We call this the Inference Tax. We got curious: what happens if you connect idle Macs directly to inference demand? This is Darkbloom. Private inference network for idle Macs. darkbloom [dot] dev -- paper + code open. Reply for invite + free credits ↓

Wake the world's sleeping compute. Look at the Mac nearest to you. What's it doing? Probably nothing. There are 100M+ Macs with Apple Silicon out there. Apple quietly made them really good at inference. A $3k Mac runs a 60B model at 30 watts. Most sit idle most of the day. Meanwhile every AI API call passes through three layers of margin before reaching the hardware. We call this the Inference Tax. We got curious: what happens if you connect idle Macs directly to inference demand? This is Darkbloom. Private inference network for idle Macs. darkbloom [dot] dev -- paper + code open. Reply for invite + free credits ↓

Gajesh

510,200 просмотров • 4 месяцев назад

FX+ is finally here. We did our first 4 cases this morning as part of the worldwide rollout with valve in valve cases and CAD cases where coronary access is key. All cases had easy post deployment coronary access. #UABStructural

FX+ is finally here. We did our first 4 cases this morning as part of the worldwide rollout with valve in valve cases and CAD cases where coronary access is key. All cases had easy post deployment coronary access. #UABStructural

Mustafa Ahmed

11,524 просмотров • 2 лет назад

Today, we're excited to release Archil's native, local application for Macs. You can now, for the first time, get access to the same files as your cloud applications and sandboxes are using, so that you can locally debug, edit, and inspect what's going on with tools like Claude.

Today, we're excited to release Archil's native, local application for Macs. You can now, for the first time, get access to the same files as your cloud applications and sandboxes are using, so that you can locally debug, edit, and inspect what's going on with tools like Claude.

Archil

12,122 просмотров • 4 месяцев назад

DPO Debate: Is RL needed for RLHF? All things as we cannot settle if DPO or RL is better. At least it is a good exercise. 1. Derivations in the DPO paper. Hint, the authors are good at math 2. cDPO, IPO, and related equations 3. Speculation on potential oddities of DPO vs RL 4. Reminders on the state of open RLHF tldr: we have more limitations with data and tooling and evaluation than optimizer choice Slides: Recent blog post of mine on DPO (more next Wed.): DPO Paper: On youtube:

DPO Debate: Is RL needed for RLHF? All things as we cannot settle if DPO or RL is better. At least it is a good exercise. 1. Derivations in the DPO paper. Hint, the authors are good at math 2. cDPO, IPO, and related equations 3. Speculation on potential oddities of DPO vs RL 4. Reminders on the state of open RLHF tldr: we have more limitations with data and tooling and evaluation than optimizer choice Slides: Recent blog post of mine on DPO (more next Wed.): DPO Paper: On youtube:

Nathan Lambert

100,027 просмотров • 2 лет назад

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 просмотров • 1 год назад

Sol from OpenAI one-shotted a multi-tentacled creature morphology and RL training harness, launched and monitored the run on vast.ai on an H200 and created a Three.js + WebGL / WebGPU browser environment for the harvested policy to crawl around in. I woke up and this guy was running on my computer

Sol from OpenAI one-shotted a multi-tentacled creature morphology and RL training harness, launched and monitored the run on vast.ai on an H200 and created a Three.js + WebGL / WebGPU browser environment for the harvested policy to crawl around in. I woke up and this guy was running on my computer

Aaron Lemke

27,453 просмотров • 1 месяц назад

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has *all* the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has all the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Sonya Huang 🐥

79,834 просмотров • 2 месяцев назад

HILARIOUS: Training camp for the #Browns security team started as they are working on TACKLING STREAKERS running across the field. 🤣🤣🤣 This is great.

HILARIOUS: Training camp for the #Browns security team started as they are working on TACKLING STREAKERS running across the field. 🤣🤣🤣 This is great.

MLFootball

441,361 просмотров • 1 год назад

On Friday, Figure completed a 20-hour run of back-to-back shifts on the BMW X3 production line! We’ve been running 10-hour shifts for several weeks now and as far as we know, Figure and BMW are the first in the world to do this with humanoid robots

On Friday, Figure completed a 20-hour run of back-to-back shifts on the BMW X3 production line! We’ve been running 10-hour shifts for several weeks now and as far as we know, Figure and BMW are the first in the world to do this with humanoid robots

Brett Adcock

757,906 просмотров • 1 год назад

"One of the very confusing things about the models right now: how to reconcile the fact that they are doing so well on evals. And you look at the evals and you go, 'Those are pretty hard evals.' But the economic impact seems to be dramatically behind. There is [a possible] explanation. Back when people were doing pre-training, the question of what data to train on was answered, because that answer was everything. So you don't have to think if it's going to be this data or that data. When people do RL training, they say, 'Okay, we want to have this kind of RL training for this thing and that kind of RL training for that thing.' You say, 'Hey, I would love our model to do really well when we release it. I want the evals to look great. What would be RL training that could help on this task?' If you combine this with generalization of the models actually being inadequate, that has the potential to explain a lot of what we are seeing, this disconnect between eval performance and actual real-world performance"

"One of the very confusing things about the models right now: how to reconcile the fact that they are doing so well on evals. And you look at the evals and you go, 'Those are pretty hard evals.' But the economic impact seems to be dramatically behind. There is [a possible] explanation. Back when people were doing pre-training, the question of what data to train on was answered, because that answer was everything. So you don't have to think if it's going to be this data or that data. When people do RL training, they say, 'Okay, we want to have this kind of RL training for this thing and that kind of RL training for that thing.' You say, 'Hey, I would love our model to do really well when we release it. I want the evals to look great. What would be RL training that could help on this task?' If you combine this with generalization of the models actually being inadequate, that has the potential to explain a lot of what we are seeing, this disconnect between eval performance and actual real-world performance"

Dwarkesh Patel

502,249 просмотров • 8 месяцев назад

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!

Jiaxuan You

58,258 просмотров • 7 месяцев назад

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong

gongy

78,284 просмотров • 15 дней назад

5x'd our creator program. $10K cash per post. $15K in Viktor credits if you prefer. 83% of my creators take the credits. Less a creator program at this point. More a product loop. Highest-paying creator program on the internet. As far as we can tell.

5x'd our creator program. $10K cash per post. $15K in Viktor credits if you prefer. 83% of my creators take the credits. Less a creator program at this point. More a product loop. Highest-paying creator program on the internet. As far as we can tell.

Viktor

25,641 просмотров • 2 месяцев назад

The Arcee AI Podcast is here! In this episode, Lucas Atkins and stochasm join us to discuss the story of Trinity models and everything frontier. I can say, this talk has been one of the most amazing and technical conversations we've had on Ground Zero. 0:00:00 - Intro 0:00:59 - Varun's transition from SWE to Pre-Training Lead 0:04:20 - Trinity Manifesto, Openclaw Ecosystem 0:12:15 - Arcee's Post-Training to Pre-Training Pivot 0:23:45 - Varun's first Pre-Training run (you can just do things!) 0:27:33 - Saturation in Pre-Training?, Mid-Training 0:37:00 - Tweaking the Training Architecture, Adam vs Muon, Evals 01:09:07 - Inference Engineering, Quick Fire, Post-Training Recipe 01:18:02 - Alpha in RL Envs, Harness Design 01:23:00 - American Open Source is trailing Chinese Competitors, Trinity Adoption 01:29:25 - Hiring at Arcee, Advice to 20yo

The Arcee AI Podcast is here! In this episode, Lucas Atkins and stochasm join us to discuss the story of Trinity models and everything frontier. I can say, this talk has been one of the most amazing and technical conversations we've had on Ground Zero. 0:00:00 - Intro 0:00:59 - Varun's transition from SWE to Pre-Training Lead 0:04:20 - Trinity Manifesto, Openclaw Ecosystem 0:12:15 - Arcee's Post-Training to Pre-Training Pivot 0:23:45 - Varun's first Pre-Training run (you can just do things!) 0:27:33 - Saturation in Pre-Training?, Mid-Training 0:37:00 - Tweaking the Training Architecture, Adam vs Muon, Evals 01:09:07 - Inference Engineering, Quick Fire, Post-Training Recipe 01:18:02 - Alpha in RL Envs, Harness Design 01:23:00 - American Open Source is trailing Chinese Competitors, Trinity Adoption 01:29:25 - Hiring at Arcee, Advice to 20yo

himanshu

32,305 просмотров • 4 месяцев назад