正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

GPT-5.5 + OpenMed Agent planning a 64-step clinical workflow. Watch plans, sub-plans, and tool calls materialize, every step visible, every finalization gated. Medical intelligence on Hugging Face. The loop is the product.

Maziyar PANAHI

19,263 subscribers

25,518 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Agent Traces on the Hugging Face hub now come with a receipt 🧾 Every trace shows tokens, cache hit rate, and cost for every run!

Agent Traces on the Hugging Face hub now come with a receipt 🧾 Every trace shows tokens, cache hit rate, and cost for every run!

Caleb

27,415 次观看 • 8 天前

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Daniel San

12,514 次观看 • 3 个月前

Daemon Lite is our next step toward simpler onboarding. Builders now get the power of Daemon in a focused workbench, without being dropped into every advanced tool at once. Open a project. Ask the agent. Build on Solana.

Daemon Lite is our next step toward simpler onboarding. Builders now get the power of Daemon in a focused workbench, without being dropped into every advanced tool at once. Open a project. Ask the agent. Build on Solana.

Daemon

18,799 次观看 • 2 个月前

Strength, discipline, and determination on display. Watch these commando recruits undergo rigorous medical checks as they take another step toward serving their nation. Every challenge is a test of courage and commitment. 🇮🇳💪

Strength, discipline, and determination on display. Watch these commando recruits undergo rigorous medical checks as they take another step toward serving their nation. Every challenge is a test of courage and commitment. 🇮🇳💪

Fabrice K

66,525 次观看 • 3 个月前

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!

ben

40,192 次观看 • 2 个月前

Get ready for the #OasisLive25 tour. Unlock wallpapers for your phone and Apple watch—city exclusive ones for every stop on the tour. Here’s how to get yours: Step 1: Start playing any Oasis song. Open the Shazam app and tap the big blue button. Step 2: Tap the special message that appears at the bottom of the song result. Step 3: Pick a city from the tour and unlock your wallpaper and Apple Watch face.

Get ready for the #OasisLive25 tour. Unlock wallpapers for your phone and Apple watch—city exclusive ones for every stop on the tour. Here’s how to get yours: Step 1: Start playing any Oasis song. Open the Shazam app and tap the big blue button. Step 2: Tap the special message that appears at the bottom of the song result. Step 3: Pick a city from the tour and unlock your wallpaper and Apple Watch face.

Shazam

218,430 次观看 • 1 年前

AI coding agents re-explore the same codebase every single session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.

AI coding agents re-explore the same codebase every single session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.

Simplifying AI

17,561 次观看 • 1 个月前

Skills are so much fun. I wrote 70+ for OpenMed and gave one to Kimi K3 🔥 It just read a patient chart it was never allowed to see. 25 identifiers masked on my Mac, 0 left the machine, and it still got every call right. Everything open on Hugging Face 🤗

Skills are so much fun. I wrote 70+ for OpenMed and gave one to Kimi K3 🔥 It just read a patient chart it was never allowed to see. 25 identifiers masked on my Mac, 0 left the machine, and it still got every call right. Everything open on Hugging Face 🤗

Maziyar PANAHI

14,092 次观看 • 2 个月前

Keep your AI agents running through process crashes and network drops. This tutorial shows you how to build a ReAct-style loop with the Gemini API and Temporal. Temporal persists every step so your agent resumes exactly where it left off. Learn more →

Keep your AI agents running through process crashes and network drops. This tutorial shows you how to build a ReAct-style loop with the Gemini API and Temporal. Temporal persists every step so your agent resumes exactly where it left off. Learn more →

Google for Developers

21,924 次观看 • 6 个月前

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK. THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK. THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.

kocer

12,740 次观看 • 1 个月前

Kimi K3 + GPT-6 Astra can become something bigger than two agents: a Two-Brain AI Operating System the formula: Two-Brain OS = Research Brain + Execution Brain + Shared State + Router + Tools + Verification not two models doing the same job. two specialized brains connected through one persistent system step 1 -> Kimi K3 becomes the research brain. complex research, source comparison, long-context synthesis and strategic planning happen here. its job is to explore the problem and compress the findings into a clear plan. step 2 -> GPT-6 Astra becomes the execution brain. it receives the plan, writes code, operates tools, creates artifacts and turns decisions into finished work. step 3 -> build a shared state layer. store the objective, evidence, decisions, constraints, failed attempts and next action outside the chat. both brains always know what happened and where the system should continue. step 4 -> add the router. uncertainty and open-ended questions move to Kimi K3. execution, tool use and deterministic tasks move to GPT-6 Astra. every job reaches the brain designed to handle it. step 5 -> create the handoff loop: research -> plan -> execute -> inspect -> update state -> continue. if execution reveals missing information, the task returns to Kimi. if the plan is ready, Astra takes control again. step 6 -> verify before completion. tests, source checks, constraints and explicit success criteria decide whether the result ships or returns to the correct brain with a clear failure signal. that is the difference between using two AI models and building a Two-Brain AI Operating System. Kimi K3 expands the search space. GPT-6 Astra converts it into action. shared state preserves progress, the router controls every handoff, tools execute the work and verification decides when the system is actually finished. one model can generate an answer. two specialized brains connected through memory, routing and verification can run an entire workflow. the full Kimi K3 + GPT-6 Astra Two-Brain OS breakdown is below ↓

Kimi K3 + GPT-6 Astra can become something bigger than two agents: a Two-Brain AI Operating System the formula: Two-Brain OS = Research Brain + Execution Brain + Shared State + Router + Tools + Verification not two models doing the same job. two specialized brains connected through one persistent system step 1 -> Kimi K3 becomes the research brain. complex research, source comparison, long-context synthesis and strategic planning happen here. its job is to explore the problem and compress the findings into a clear plan. step 2 -> GPT-6 Astra becomes the execution brain. it receives the plan, writes code, operates tools, creates artifacts and turns decisions into finished work. step 3 -> build a shared state layer. store the objective, evidence, decisions, constraints, failed attempts and next action outside the chat. both brains always know what happened and where the system should continue. step 4 -> add the router. uncertainty and open-ended questions move to Kimi K3. execution, tool use and deterministic tasks move to GPT-6 Astra. every job reaches the brain designed to handle it. step 5 -> create the handoff loop: research -> plan -> execute -> inspect -> update state -> continue. if execution reveals missing information, the task returns to Kimi. if the plan is ready, Astra takes control again. step 6 -> verify before completion. tests, source checks, constraints and explicit success criteria decide whether the result ships or returns to the correct brain with a clear failure signal. that is the difference between using two AI models and building a Two-Brain AI Operating System. Kimi K3 expands the search space. GPT-6 Astra converts it into action. shared state preserves progress, the router controls every handoff, tools execute the work and verification decides when the system is actually finished. one model can generate an answer. two specialized brains connected through memory, routing and verification can run an entire workflow. the full Kimi K3 + GPT-6 Astra Two-Brain OS breakdown is below ↓

Alex

23,962 次观看 • 19 天前

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

Teodora P L

28,523 次观看 • 2 年前

Portal Pay is a cornerstone of our product suite as we build the infra powering apps and games on every chain. Effortless cross-chain payment is a key step toward taking Web3 UX to the next level. All fees from Pay are used to buy $PORTAL.

Portal Pay is a cornerstone of our product suite as we build the infra powering apps and games on every chain. Effortless cross-chain payment is a key step toward taking Web3 UX to the next level. All fees from Pay are used to buy $PORTAL.

Portal

27,389 次观看 • 1 年前

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.

CDG

15,388 次观看 • 1 个月前

Man, I used to spend forever throwing random prompts at AI and getting inconsistent junk every time. Now I actually have this smooth 6-step workflow same influencer character every video. GPT Image 2 for the first frame, Seedance 2.0 for the motion, then killer lip-sync. Feels like I’ve got a whole production crew in my laptop My Reels are finally hitting different 🤞

Man, I used to spend forever throwing random prompts at AI and getting inconsistent junk every time. Now I actually have this smooth 6-step workflow same influencer character every video. GPT Image 2 for the first frame, Seedance 2.0 for the motion, then killer lip-sync. Feels like I’ve got a whole production crew in my laptop My Reels are finally hitting different 🤞

@ZoAina_AI

18,608 次观看 • 4 个月前

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

37,936 次观看 • 1 个月前

Egypt Petroleum Ministry Calls Damietta Port Blaze an ACCIDENT, Not a Drone Attack A fire broke out Wednesday on two vessels docked at Egypt's Damietta port, a fuel ship and a storage tanker, and was contained under emergency plans with NO casualties. The Ministry of Petroleum confirms it is a fire accident and said an investigation was launched to determine the cause. Every Western wire calls it a drone strike. Cairo, sitting on the actual port, calls it an accident.

Egypt Petroleum Ministry Calls Damietta Port Blaze an ACCIDENT, Not a Drone Attack A fire broke out Wednesday on two vessels docked at Egypt's Damietta port, a fuel ship and a storage tanker, and was contained under emergency plans with NO casualties. The Ministry of Petroleum confirms it is a fire accident and said an investigation was launched to determine the cause. Every Western wire calls it a drone strike. Cairo, sitting on the actual port, calls it an accident.

Ryan Rozbiani

31,598 次观看 • 2 个月前

A line of climbers heading for the summit push seen between Camp III and Camp IV on Everest – 17.05.2025. The death zone awaits, and every step is a test of will, weather, and patience. Video ©: Gyalzean Sherpa.

A line of climbers heading for the summit push seen between Camp III and Camp IV on Everest – 17.05.2025. The death zone awaits, and every step is a test of will, weather, and patience. Video ©: Gyalzean Sherpa.

Everest Today

42,642 次观看 • 1 年前

holy sh*t, someone mapped an entire company into 388 AI agent skills every solo builder can steal the workflow this repo covers 20 domains across engineering, product, marketing, finance, sales, compliance and research the patterns: → challenge your architecture with a CTO persona → turn customer research into a product spec → build with engineering and DevOps skills → run QA and security checks before launch → plan content, SEO, pricing and distribution → model budgets and SaaS metrics → prepare compliance evidence as you grow the architecture: skills define how → agents define the job → personas shape decisions → orchestration connects the work the part solo builders should steal: idea → research → spec → build → test → launch → sell one person can run the whole sequence with a clear job for their agent at every step save this, then build a second brain for your company⭣

holy sh*t, someone mapped an entire company into 388 AI agent skills every solo builder can steal the workflow this repo covers 20 domains across engineering, product, marketing, finance, sales, compliance and research the patterns: → challenge your architecture with a CTO persona → turn customer research into a product spec → build with engineering and DevOps skills → run QA and security checks before launch → plan content, SEO, pricing and distribution → model budgets and SaaS metrics → prepare compliance evidence as you grow the architecture: skills define how → agents define the job → personas shape decisions → orchestration connects the work the part solo builders should steal: idea → research → spec → build → test → launch → sell one person can run the whole sequence with a clear job for their agent at every step save this, then build a second brain for your company⭣

beamnxw ./

96,499 次观看 • 4 天前