Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

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

18,090 subscribers

25,417 görüntüleme • 3 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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 görüntüleme • 2 ay önce

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 görüntüleme • 1 ay önce

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 görüntüleme • 2 ay önce

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

39,382 görüntüleme • 26 gün önce

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

218,012 görüntüleme • 1 yıl önce

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 görüntüleme • 8 gün önce

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 görüntüleme • 5 ay önce

2025 is the year of ItCoin. New year, same mission. Every step forward is a reminder of the potential of ItCoin. Get ready and hodl on for the ride!

2025 is the year of ItCoin. New year, same mission. Every step forward is a reminder of the potential of ItCoin. Get ready and hodl on for the ride!

ItCoin

16,917 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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 görüntüleme • 3 ay önce

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

36,159 görüntüleme • 10 gün önce

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

30,514 görüntüleme • 17 gün önce

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 görüntüleme • 1 yıl önce

Seedance 2.0 + Claude Code is f*cking insane 🤯 I built a Claude skill that creates UGC ads on demand. One product + one prompt = the AI creator, the script, the scene-by-scene shot list, and the finished video. All inside Claude Code. Perfect for DTC brands and agencies who can't afford to keep paying $500-$1,500 per UGC video and waiting 2 weeks for revisions. This skill eliminates the entire loop: → Tell Claude the product, ad angle, and length → Skill writes the GPT Image 2.0 prompt to generate the AI creator from scratch → Skill writes every scene prompt, dialogue line, and delivery direction → Pipes it into Seedance 2.0 with character + product + voice locked → Speed up + caption in CapCut → Ship the ad in 20 minutes No more paying $11 per video on Arcads. No more 2-week revision cycles. No more PR boxes to creators who ghost you. What you get: → Perfect character consistency across every scene → Voice consistency that holds clip-to-clip → Real product fidelity using your actual product photo as a reference → Multi-scene day-in-life, testimonial, and action-shot formats out of the box Built 100% with a Claude skill + Seedance 2.0. I recorded a full step-by-step tutorial showing the exact workflow so you can build these AI UGC ads yourself. Want the full breakdown? > Like this post > Comment "UGC" And I'll send it over (must be following so I can DM)

Seedance 2.0 + Claude Code is f*cking insane 🤯 I built a Claude skill that creates UGC ads on demand. One product + one prompt = the AI creator, the script, the scene-by-scene shot list, and the finished video. All inside Claude Code. Perfect for DTC brands and agencies who can't afford to keep paying $500-$1,500 per UGC video and waiting 2 weeks for revisions. This skill eliminates the entire loop: → Tell Claude the product, ad angle, and length → Skill writes the GPT Image 2.0 prompt to generate the AI creator from scratch → Skill writes every scene prompt, dialogue line, and delivery direction → Pipes it into Seedance 2.0 with character + product + voice locked → Speed up + caption in CapCut → Ship the ad in 20 minutes No more paying $11 per video on Arcads. No more 2-week revision cycles. No more PR boxes to creators who ghost you. What you get: → Perfect character consistency across every scene → Voice consistency that holds clip-to-clip → Real product fidelity using your actual product photo as a reference → Multi-scene day-in-life, testimonial, and action-shot formats out of the box Built 100% with a Claude skill + Seedance 2.0. I recorded a full step-by-step tutorial showing the exact workflow so you can build these AI UGC ads yourself. Want the full breakdown? > Like this post > Comment "UGC" And I'll send it over (must be following so I can DM)

Mike Futia

39,787 görüntüleme • 3 ay önce

Traditional factory automation follows three rules: 1. Minimise degrees of freedom 2. Minimise actuation 3. Minimise the requirement for feedback Let geometry and gravity do the hard work. This is a step feeder. Reciprocating plates push parts upward, one step at a time. Parts that sit stable on the ledge rise to the top. Parts that don't? They tip off and fall back into the hopper. A chain conveyor carries the parts along and a simple tool knocks off any that are misaligned. No robot. No vision. No gripper. Just continuous circulation until every part finds its perfect orientation. Bowl feeders, gravity slides, step feeders, escapements—all built on the same principle. Constrain movement. Let shape and weight do the sorting. Modern robotics throws sensors, actuators, and computing at every problem. Sometimes the smarter move is less.

Traditional factory automation follows three rules: 1. Minimise degrees of freedom 2. Minimise actuation 3. Minimise the requirement for feedback Let geometry and gravity do the hard work. This is a step feeder. Reciprocating plates push parts upward, one step at a time. Parts that sit stable on the ledge rise to the top. Parts that don't? They tip off and fall back into the hopper. A chain conveyor carries the parts along and a simple tool knocks off any that are misaligned. No robot. No vision. No gripper. Just continuous circulation until every part finds its perfect orientation. Bowl feeders, gravity slides, step feeders, escapements—all built on the same principle. Constrain movement. Let shape and weight do the sorting. Modern robotics throws sensors, actuators, and computing at every problem. Sometimes the smarter move is less.

Jack 🤖

467,344 görüntüleme • 8 ay önce

Claude "Puzzling" while GPT 5.6 on GOD-MODE just bade a banger that's mindblowing. Here's the exact way to get a site like this, step by step: > open the desktop app, pick Sol, reasoning on High. taste work never goes to small models > drop it 3 sites with motion you love and one line: "reverse-engineer the art direction: mood, typography, pacing, and WHY each animation exists. save it as a style bible" > brief in one paragraph, goal not steps: "[your niche] site, cinematic scroll, every animation has a job. follow the bible" > house rules on top: no template hero, no stock gradients, nothing on the page moves without a reason > now the bar: "a motion designer can't tell this from an agency build." spin up a SECOND 5.6 with fresh context whose only job is to FAIL the build against that bar > /loop overnight: build, grade, close the biggest gap, again. you're asleep for all of it > when the verifier runs out of complaints: tag Sites. live URL, one click, zero hosting The deeper version of every step (the full contract, the house rules, the verifier trick, when Ultra is worth the bill) is in the article below. P.S. send the article to your GPT and tell it "we're doing this tonight".

Claude "Puzzling" while GPT 5.6 on GOD-MODE just bade a banger that's mindblowing. Here's the exact way to get a site like this, step by step: > open the desktop app, pick Sol, reasoning on High. taste work never goes to small models > drop it 3 sites with motion you love and one line: "reverse-engineer the art direction: mood, typography, pacing, and WHY each animation exists. save it as a style bible" > brief in one paragraph, goal not steps: "[your niche] site, cinematic scroll, every animation has a job. follow the bible" > house rules on top: no template hero, no stock gradients, nothing on the page moves without a reason > now the bar: "a motion designer can't tell this from an agency build." spin up a SECOND 5.6 with fresh context whose only job is to FAIL the build against that bar > /loop overnight: build, grade, close the biggest gap, again. you're asleep for all of it > when the verifier runs out of complaints: tag Sites. live URL, one click, zero hosting The deeper version of every step (the full contract, the house rules, the verifier trick, when Ultra is worth the bill) is in the article below. P.S. send the article to your GPT and tell it "we're doing this tonight".

Miraqle

206,109 görüntüleme • 1 ay önce

this Adaptive agent uses GPT's new image model to run your entire creative + marketing team, on autopilot. here's how any business can replace their whole marketing op with it: - generates fresh on-brand creatives for every platform, daily - writes and schedules the content across every channel - replies to every comment the second it drops - DMs every lead and turns cold interest into booked clients - boosts paid ads from your best-performing organic posts - doubles down on the creatives that win, kills the ones that don't - tracks performance + adjusts strategy automatically, 24/7 every step from brand → booked client is fully automated. reply "AGENT" + RT and I'll send you the full guide so you can set it up too

Chris

72,763 görüntüleme • 3 ay önce

OpenAI has introduced the ChatGPT Agent, which handles complex multi-step tasks from research to automation. Genspark goes further in some areas: In addition to user-friendly office tools (Slides, Docs, Sheets, AI Secretary, AI Drive), Genspark scores with dynamic tool orchestration and an intelligent feedback loop - a clear added value, especially for individuals and small teams. ChatGPT Agent Offers browser and API access, terminal control and deep search capabilities. Strengths include high security mechanisms, comprehensive user control and integration with productivity tools such as Gmail and Calendar. Ideal for end users and teams who need maximum control and data protection. Genspark Super Agent Enables no-code workflows, creates high-quality visual content (slides, videos) and automates entire workflows. With tool calling, the agent automatically selects the best solution from over 80 integrated tools - e.g. for CRM queries, task management or API access. The feedback loop allows the agent to monitor the use of a tool during execution and dynamically switch to another tool or adapt the workflow if necessary. Thanks to this multi-model architecture, Genspark often works more precisely and efficiently in benchmarks than comparable systems.

OpenAI has introduced the ChatGPT Agent, which handles complex multi-step tasks from research to automation. Genspark goes further in some areas: In addition to user-friendly office tools (Slides, Docs, Sheets, AI Secretary, AI Drive), Genspark scores with dynamic tool orchestration and an intelligent feedback loop - a clear added value, especially for individuals and small teams. ChatGPT Agent Offers browser and API access, terminal control and deep search capabilities. Strengths include high security mechanisms, comprehensive user control and integration with productivity tools such as Gmail and Calendar. Ideal for end users and teams who need maximum control and data protection. Genspark Super Agent Enables no-code workflows, creates high-quality visual content (slides, videos) and automates entire workflows. With tool calling, the agent automatically selects the best solution from over 80 integrated tools - e.g. for CRM queries, task management or API access. The feedback loop allows the agent to monitor the use of a tool during execution and dynamically switch to another tool or adapt the workflow if necessary. Thanks to this multi-model architecture, Genspark often works more precisely and efficiently in benchmarks than comparable systems.

Chubby♨️

176,267 görüntüleme • 1 yıl önce

Pink police booths are being established across West Bengal, marking a strong step forward in ensuring women’s safety under the BJP government. With dedicated women police officers deployed for round the clock duty, these booths will provide immediate assistance, build trust at the grassroots level, and create a visible sense of security in every locality. This is governance with intent and sensitivity. Safer streets, stronger communities, and a clear message that every woman in Bengal matters, every hour of the day and night.

Pink police booths are being established across West Bengal, marking a strong step forward in ensuring women’s safety under the BJP government. With dedicated women police officers deployed for round the clock duty, these booths will provide immediate assistance, build trust at the grassroots level, and create a visible sense of security in every locality. This is governance with intent and sensitivity. Safer streets, stronger communities, and a clear message that every woman in Bengal matters, every hour of the day and night.

BJP West Bengal

34,945 görüntüleme • 2 ay önce