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

Introducing Core Sandbox Alpha, the first inference-time learning coding assistant. Every interaction affects reasoning immediately. No RL. No retraining. No fine-tuning.

Rei

15,972 subscribers

52,875 просмотров • 9 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🔥 INTRODUCING: ACE >>> The Agentic Context Engineer ACE is an AI Agent that improves context for any AI Agent. Context gets better every time you use ACE. No fine-tuning. No manual prompt editing. Just use ACE and your AI Agents get smarter. 🧵 👇

🔥 INTRODUCING: ACE >>> The Agentic Context Engineer ACE is an AI Agent that improves context for any AI Agent. Context gets better every time you use ACE. No fine-tuning. No manual prompt editing. Just use ACE and your AI Agents get smarter. 🧵 👇

Dan McAteer

21,259 просмотров • 6 месяцев назад

introducing Dreamspace: the first vibe coding canvas for crypto's creatives. drag, drop, chat, and ship your dream app on your dream chain. no coding required. alpha preview is live. here's how to get in early ✨

introducing Dreamspace: the first vibe coding canvas for crypto's creatives. drag, drop, chat, and ship your dream app on your dream chain. no coding required. alpha preview is live. here's how to get in early ✨

Dreamspace

72,975 просмотров • 1 год назад

What do we really need for social navigation?🤖 Deep RL? No❌ Imitation learning? No❌ LLMs? No❌ 📊Turns out for over 80% of the time, classical methods >> learning-based solutions! In new work, we rethink social navigation. Thread🧶

What do we really need for social navigation?🤖 Deep RL? No❌ Imitation learning? No❌ LLMs? No❌ 📊Turns out for over 80% of the time, classical methods >> learning-based solutions! In new work, we rethink social navigation. Thread🧶

Rohan Chandra

14,066 просмотров • 2 лет назад

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

495,491 просмотров • 1 месяц назад

Inspired by the new o1 model, I hacked together g1, powered by Llama-3.1 on Groq Inc. It uses reasoning chains to solve problems. It solves the Strawberry problem ~70% of the time, with no fine tuning or few shot techniques. A thread 🧵 (with GitHub repo!)

Inspired by the new o1 model, I hacked together g1, powered by Llama-3.1 on Groq Inc. It uses reasoning chains to solve problems. It solves the Strawberry problem ~70% of the time, with no fine tuning or few shot techniques. A thread 🧵 (with GitHub repo!)

Ben Klieger

260,684 просмотров • 1 год назад

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

264,495 просмотров • 5 месяцев назад

No longer a mystery. Introducing… the Assistant Manager chip. 👔 Available from #FPL Gameweek 24.

No longer a mystery. Introducing… the Assistant Manager chip. 👔 Available from #FPL Gameweek 24.

Fantasy Premier League

7,622,575 просмотров • 1 год назад

Self-Refining Video Sampling: inference-time method using a video generator as its own refiner to correct physics and motion. no retraining needed; scores >70% human preference; is validated on Wan2.2 & Cosmos.

Self-Refining Video Sampling: inference-time method using a video generator as its own refiner to correct physics and motion. no retraining needed; scores >70% human preference; is validated on Wan2.2 & Cosmos.

Wildminder

32,133 просмотров • 7 месяцев назад

MARCH 7TH 2026 THE GREAT SANDBOX SYMPOSIUM SAN FRANCISCO, CA real builders, getting together to try all the sandbox tech, comparing them across different dimensions + sharing research with each other at the end + no credits, no prizes, no judging, just hacking and learning see you there Joe Heitzeberg AI Tinkerers Blaxel E2B Daytona

MARCH 7TH 2026 THE GREAT SANDBOX SYMPOSIUM SAN FRANCISCO, CA real builders, getting together to try all the sandbox tech, comparing them across different dimensions + sharing research with each other at the end + no credits, no prizes, no judging, just hacking and learning see you there Joe Heitzeberg AI Tinkerers Blaxel E2B Daytona

dex

20,574 просмотров • 6 месяцев назад

I tried vibe coding for the first time and, well... ideas are no longer cheap this is the story of what happened:

I tried vibe coding for the first time and, well... ideas are no longer cheap this is the story of what happened:

nev

47,118 просмотров • 7 месяцев назад

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,466 просмотров • 2 лет назад

A glimpse into one of our core features 👀 Chat, Search, Compare, & Run #Inference for all AI models on ONE Platform: No more complicated setups, just seamless #AI magic. 💫 Be the first to experience - join waitlist now: #Inferium #AI #Inference

A glimpse into one of our core features 👀 Chat, Search, Compare, & Run #Inference for all AI models on ONE Platform: No more complicated setups, just seamless #AI magic. 💫 Be the first to experience - join waitlist now: #Inferium #AI #Inference

Inferium

1,079,374 просмотров • 2 лет назад

🆕Scaling Test Time Compute to Multi-Agent Civilizations, with Noam Brown We're excited to publish our full conversation with Noam Brown on the frontiers of the new reasoning paradigm at OpenAI! - first principles for starting the "Multi-Agents" team - what's not captured by the "System 1/System 2" analogy for inference time compute - how Ilya Sutskever convinced him that reasoning was closer than he thought - Deep Research is existence proof that RL generalizes beyond verifiable rewards - the relationship between AI for imperfect information games (like Poker, Stratego, Diplomacy) and reasoning Enjoy! on youtube, or wherever fine podcasts are sold.

🆕Scaling Test Time Compute to Multi-Agent Civilizations, with Noam Brown We're excited to publish our full conversation with Noam Brown on the frontiers of the new reasoning paradigm at OpenAI! - first principles for starting the "Multi-Agents" team - what's not captured by the "System 1/System 2" analogy for inference time compute - how Ilya Sutskever convinced him that reasoning was closer than he thought - Deep Research is existence proof that RL generalizes beyond verifiable rewards - the relationship between AI for imperfect information games (like Poker, Stratego, Diplomacy) and reasoning Enjoy! on youtube, or wherever fine podcasts are sold.

Latent.Space

105,923 просмотров • 1 год назад

Yesterday, we live demo-ed a “generalist” VLA for (I think) the first time ever to a broad audience Robotics: Science and Systems. Bring any object. Ask anything. New environment, new instructions, no fine-tuning. Just impeccable vibes! ✨

Yesterday, we live demo-ed a “generalist” VLA for (I think) the first time ever to a broad audience Robotics: Science and Systems. Bring any object. Ask anything. New environment, new instructions, no fine-tuning. Just impeccable vibes! ✨

Dhruv Shah

56,734 просмотров • 1 год назад

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Zhen Wu

821,791 просмотров • 11 месяцев назад

Introducing PorTAL: Portable Task Adapters for LLMs. A novel recipe to cheaply port fine-tuning between models. It matches per task LoRA accuracy at half the cost, lowering the switching overhead of adapting tasks across LLMs. At Ramp, every new model release used to mean retraining our fine-tunes from scratch. PorTAL learns the task once, then efficiently refits it onto any new base model, even across model families.

Introducing PorTAL: Portable Task Adapters for LLMs. A novel recipe to cheaply port fine-tuning between models. It matches per task LoRA accuracy at half the cost, lowering the switching overhead of adapting tasks across LLMs. At Ramp, every new model release used to mean retraining our fine-tunes from scratch. PorTAL learns the task once, then efficiently refits it onto any new base model, even across model families.

Ramp Labs

172,328 просмотров • 2 месяцев назад

Introducing the mint mcp Your coding agent can now generate fully immersive 3D worlds and 3D models No Blender required :)

Introducing the mint mcp Your coding agent can now generate fully immersive 3D worlds and 3D models No Blender required :)

tamrat

135,494 просмотров • 4 месяцев назад

Introducing Dreamspace, the first vibe coding canvas for crypto’s creatives. Ship your dream app in minutes and monetize it onchain with no code. Powered by Microsoft AI, , and @Base. 🧵

Introducing Dreamspace, the first vibe coding canvas for crypto’s creatives. Ship your dream app in minutes and monetize it onchain with no code. Powered by Microsoft AI, , and @Base. 🧵

Dreamspace

319,573 просмотров • 1 год назад

Instead of asking a VLM to output progress, it reads the model’s internal belief directly from token logits. No in-context learning. No fine-tuning. No reward training. 📈 We introduce: TOPReward, a zero-shot reward modeling approach for robotics using token probabilities from pretrained video VLMs. The simplest way of doing reward modelling for robotics! Project: 🧵👇

Instead of asking a VLM to output progress, it reads the model’s internal belief directly from token logits. No in-context learning. No fine-tuning. No reward training. 📈 We introduce: TOPReward, a zero-shot reward modeling approach for robotics using token probabilities from pretrained video VLMs. The simplest way of doing reward modelling for robotics! Project: 🧵👇

Jiafei Duan

107,926 просмотров • 6 месяцев назад