Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I tried Hedra Agent by Hedra to see if one conversation could replace the usual mess of switching models, rewriting prompts, and juggling tools. So I started with a simple idea, Hedra Agent: - Selected the right models on its own - Generated refined visuals - Suggested multiple stylistic...

azed_ai's profile picture

Amira Zairi

54,214 subscribers

31,593 Aufrufe • vor 5 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Hedra Agent 2 turns a simple concept into a full creative production workflow. Hedra I gave it a challenge: “What could New York look like in 2050?” It researched future urban trends, developed the creative direction and script, then built the visuals and final cinematic sequence. What stood out was how the entire process—from research → concept → planning → production → final videohappened in one Space. Workflow 👇
0:15

Hedra Agent 2 turns a simple concept into a full creative production workflow. Hedra I gave it a challenge: “What could New York look like in 2050?” It researched future urban trends, developed the creative direction and script, then built the visuals and final cinematic sequence. What stood out was how the entire process—from research → concept → planning → production → final videohappened in one Space. Workflow 👇

Smiling Khan

21,533 Aufrufe • vor 13 Tagen

I created this 15-second cinematic product video with GPTProto Official using Seedance 2.0, and I was really impressed by how smooth the workflow was. What stood out to me was being able to access multiple advanced AI models in one place, making it easier to test ideas, compare results, and create without constantly switching between different platforms. A more flexible way to explore AI creativity while simplifying the process of working with multiple AI tools.
0:15

I created this 15-second cinematic product video with GPTProto Official using Seedance 2.0, and I was really impressed by how smooth the workflow was. What stood out to me was being able to access multiple advanced AI models in one place, making it easier to test ideas, compare results, and create without constantly switching between different platforms. A more flexible way to explore AI creativity while simplifying the process of working with multiple AI tools.

Alamin

48,506 Aufrufe • vor 28 Tagen

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 🔽
0:11

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 Aufrufe • vor 1 Jahr

I tried MiniMax Design (H3) to see how it handles real content creation. The workflow is simple. You just write a prompt or drop in an image, and it turns that into a dynamic video with motion, framing, and scene depth. No timeline to manage. No editing setup. No back and forth. What stood out to me: • Text to video and image to video both feel smooth. • It handles motion, camera angles, and flow on its own. • Output is fast, usually within seconds. • Works well for reels, quick ads, storytelling, and idea testing. It removes the hardest part: starting from scratch and turns your ideas into content in minutes. Instead of thinking, “How do I make this video?” You start with, “What do I want to create?” That shift alone makes it worth exploring. Try it here: #Hailuo
0:10

I tried MiniMax Design (H3) to see how it handles real content creation. The workflow is simple. You just write a prompt or drop in an image, and it turns that into a dynamic video with motion, framing, and scene depth. No timeline to manage. No editing setup. No back and forth. What stood out to me: • Text to video and image to video both feel smooth. • It handles motion, camera angles, and flow on its own. • Output is fast, usually within seconds. • Works well for reels, quick ads, storytelling, and idea testing. It removes the hardest part: starting from scratch and turns your ideas into content in minutes. Instead of thinking, “How do I make this video?” You start with, “What do I want to create?” That shift alone makes it worth exploring. Try it here: #Hailuo

Manish Kumar Shah

27,680 Aufrufe • vor 4 Monaten

messy inputs 👉🏽 polished outputs built a prototype with the idea of letting users bring together images from Lummi into a canvas, quickly wireframe a concept, and then generate polished images as a photo, illustration, 3d render, whatever—with the right lighting, shadows, cohesive colors, and all that good stuff the output is still not great... but this is where I see the future of creative tools heading—kind of like how you give ChatGPT an idea for an email—all the messy bits—and it writes it for you in any tone or style you want in a clear way. now imagine that but for design or imagery
0:16

messy inputs 👉🏽 polished outputs built a prototype with the idea of letting users bring together images from Lummi into a canvas, quickly wireframe a concept, and then generate polished images as a photo, illustration, 3d render, whatever—with the right lighting, shadows, cohesive colors, and all that good stuff the output is still not great... but this is where I see the future of creative tools heading—kind of like how you give ChatGPT an idea for an email—all the messy bits—and it writes it for you in any tone or style you want in a clear way. now imagine that but for design or imagery

Pablo Stanley

12,109 Aufrufe • vor 1 Jahr

Burned 200k tokens just for "animations" and still AI couldn't do it well. I tried one of the expert animation design engineer's, Emil Kowalski's Agent Skill on my website to improve animation using Grok 4.5 It analyzed the UI, found issues, came up with a good plan, and iterated multiple times. The end result actually made parts of the UX worse. Also, it never suggested the animation experience I had in mind. So I explained exactly how I wanted it to feel. It got much closer, but still missed details like applying the same animation during keyboard navigation between cards. That silly. The lesson isn't about the model or the Agent Skill. But it's about, "Even the strongest models can't infer your taste yet." They can't and won't suggest it. AI only executes. You have to define the experience with enough details for it to execute. Otherwise, you'll end up with something that's almost okay, but still not what you wanted
0:13

Burned 200k tokens just for "animations" and still AI couldn't do it well. I tried one of the expert animation design engineer's, Emil Kowalski's Agent Skill on my website to improve animation using Grok 4.5 It analyzed the UI, found issues, came up with a good plan, and iterated multiple times. The end result actually made parts of the UX worse. Also, it never suggested the animation experience I had in mind. So I explained exactly how I wanted it to feel. It got much closer, but still missed details like applying the same animation during keyboard navigation between cards. That silly. The lesson isn't about the model or the Agent Skill. But it's about, "Even the strongest models can't infer your taste yet." They can't and won't suggest it. AI only executes. You have to define the experience with enough details for it to execute. Otherwise, you'll end up with something that's almost okay, but still not what you wanted

The Bugged Dev

26,416 Aufrufe • vor 1 Monat

Hot take: most “AI creator” tools are just fancy prompt boxes. This one actually behaves like an agent. I gave it a messy idea and instead of breaking, it: - built visuals (images) - turned them into video - kept iterating without me stepping in every 2 seconds (you can see it in the screen recording 👇) Halfway through using Yapper , it clicked — this thing doesn’t just generate… it works through ideas. That’s the difference: it thinks in workflows, not single outputs. You spend less time prompting…and more time actually creating. Not perfect yet — but it’s one of the first tools that feels like it scales with you. If you’re deep into AI, you’ll see the shift instantly.
0:16

Hot take: most “AI creator” tools are just fancy prompt boxes. This one actually behaves like an agent. I gave it a messy idea and instead of breaking, it: - built visuals (images) - turned them into video - kept iterating without me stepping in every 2 seconds (you can see it in the screen recording 👇) Halfway through using Yapper , it clicked — this thing doesn’t just generate… it works through ideas. That’s the difference: it thinks in workflows, not single outputs. You spend less time prompting…and more time actually creating. Not perfect yet — but it’s one of the first tools that feels like it scales with you. If you’re deep into AI, you’ll see the shift instantly.

The AI Guru 💡

50,197 Aufrufe • vor 3 Monaten

My favorite cmux feature is Cmd+Shift+U. I have 17 workspaces open right now, each running an agent. I used to click through tabs and macOS system-wide notifications to figure out what completed. But with cmux, I can just "Cmd+Shift+U" Cmd+Shift+U jumps to the newest unread notification. In practice that means the last agent that finished. It switches to the right workspace, focuses the exact pane, flashes it so you see where to look, and marks it read. If the notification came from another window, that window comes forward.
0:16

My favorite cmux feature is Cmd+Shift+U. I have 17 workspaces open right now, each running an agent. I used to click through tabs and macOS system-wide notifications to figure out what completed. But with cmux, I can just "Cmd+Shift+U" Cmd+Shift+U jumps to the newest unread notification. In practice that means the last agent that finished. It switches to the right workspace, focuses the exact pane, flashes it so you see where to look, and marks it read. If the notification came from another window, that window comes forward.

Lawrence Chen

28,517 Aufrufe • vor 5 Monaten

Every creator has been here: an idea in your head, no time to build it, no clean way to visualize it. So I tried something different… I opened Freepik and built the entire concept as a short video, start to finish, in one place. I wrote a simple scene, dropped in my product, and let Freepik generate a cinematic first draft. Then I refined it: better framing, smoother motion, cleaner lighting. The kind of polish you’d normally need a full editing stack for, all handled inside the same workflow. One idea. One tool. A finished video in minutes. Try it now:
0:17

Every creator has been here: an idea in your head, no time to build it, no clean way to visualize it. So I tried something different… I opened Freepik and built the entire concept as a short video, start to finish, in one place. I wrote a simple scene, dropped in my product, and let Freepik generate a cinematic first draft. Then I refined it: better framing, smoother motion, cleaner lighting. The kind of polish you’d normally need a full editing stack for, all handled inside the same workflow. One idea. One tool. A finished video in minutes. Try it now:

Chidanand Tripathi

93,250 Aufrufe • vor 9 Monaten

For 6 months I woke up at 5 AM to catch Asian markets on Polymarket. During that time I lost my girlfriend, gained 8 kg, and got used to drinking coffee instead of breakfast Then I wrote an agent that monitors everything for me while I sleep. In the 1st month income went up 15% and I finally deleted the 5 AM alarm Turns out a half-asleep human trades worse than a 200-line script I thought discipline meant waking up early. In reality it was just stubbornness that cost me money and health. When I finally sat down to build the agent it became clear why Here is what is under the hood: 1. Sentiment analysis powered by Claude. Every 15 minutes the agent runs a feed from 40+ Asian sources: Reuters Asia, Nikkei, South China Morning Post, Yonhap 2. NLP tone classification. It compares sentiment shifts to open markets on Polymarket through the API, and if the news has already dropped but the odds have not reacted yet that is the entry window 3. Kelly criterion. A mathematical formula for position sizing instead of my usual "I will bet more, feeling lucky" 4. A hard stop at 5% of the deposit per trade so that 1 mistake cannot kill the entire account 5. A cooldown between entries so the agent does not stack up a cluster of correlated positions These are exactly the rules I was missing at 5 AM. I knew them perfectly well but consistently ignored them because on adrenaline and caffeine every bet felt like an "obvious opportunity" When I ran a backtest on my old trades it was genuinely painful: 60% of the bets I placed by hand in a half-asleep state would have been rejected by the agent for failing the expected value filter Those were the exact ones dragging the whole result down When I was building my agent I needed a benchmark. A wallet that already trades on similar logic so I could compare my results to someone else's Found 1 that works almost like a mirror of what I described: same Asian markets, same cold calculation without emotion. I still keep it bookmarked and periodically check how it handles the same situations: That is actually the wallet I started with when testing auto-copying through a bot before I launched my own agent. A useful thing if you want to see how a strategy works on someone else's example first and only then build your own:
0:14

For 6 months I woke up at 5 AM to catch Asian markets on Polymarket. During that time I lost my girlfriend, gained 8 kg, and got used to drinking coffee instead of breakfast Then I wrote an agent that monitors everything for me while I sleep. In the 1st month income went up 15% and I finally deleted the 5 AM alarm Turns out a half-asleep human trades worse than a 200-line script I thought discipline meant waking up early. In reality it was just stubbornness that cost me money and health. When I finally sat down to build the agent it became clear why Here is what is under the hood: 1. Sentiment analysis powered by Claude. Every 15 minutes the agent runs a feed from 40+ Asian sources: Reuters Asia, Nikkei, South China Morning Post, Yonhap 2. NLP tone classification. It compares sentiment shifts to open markets on Polymarket through the API, and if the news has already dropped but the odds have not reacted yet that is the entry window 3. Kelly criterion. A mathematical formula for position sizing instead of my usual "I will bet more, feeling lucky" 4. A hard stop at 5% of the deposit per trade so that 1 mistake cannot kill the entire account 5. A cooldown between entries so the agent does not stack up a cluster of correlated positions These are exactly the rules I was missing at 5 AM. I knew them perfectly well but consistently ignored them because on adrenaline and caffeine every bet felt like an "obvious opportunity" When I ran a backtest on my old trades it was genuinely painful: 60% of the bets I placed by hand in a half-asleep state would have been rejected by the agent for failing the expected value filter Those were the exact ones dragging the whole result down When I was building my agent I needed a benchmark. A wallet that already trades on similar logic so I could compare my results to someone else's Found 1 that works almost like a mirror of what I described: same Asian markets, same cold calculation without emotion. I still keep it bookmarked and periodically check how it handles the same situations: That is actually the wallet I started with when testing auto-copying through a bot before I launched my own agent. A useful thing if you want to see how a strategy works on someone else's example first and only then build your own:

Blaze

126,874 Aufrufe • vor 4 Monaten

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 Aufrufe • vor 2 Tagen

I built "Avalanche Map" as a desktop app with to plan ski touring adventures! The Glaze agent just figured out how to pull the latest avalanche report from the official Swedish avalanche website - including detailed topo shading and slope angles. It supports 3d maps and can filter map output by the aspects affected by today's danger. Building niche software like this with just a few prompts is great
0:13

I built "Avalanche Map" as a desktop app with to plan ski touring adventures! The Glaze agent just figured out how to pull the latest avalanche report from the official Swedish avalanche website - including detailed topo shading and slope angles. It supports 3d maps and can filter map output by the aspects affected by today's danger. Building niche software like this with just a few prompts is great

Samuel

11,883 Aufrufe • vor 5 Monaten

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.
0:15

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.

elvis

37,647 Aufrufe • vor 22 Tagen

Very pleasantly surprised to discover Cursor cloud agents can playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!
0:17

Very pleasantly surprised to discover Cursor cloud agents can playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!

Danny Limanseta

52,121 Aufrufe • vor 5 Monaten

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.
0:16

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.

stevibe

44,151 Aufrufe • vor 2 Monaten

🚨 one person can now do the work of an entire creative team. i just tested it on a real one. a friend needed an ad for his brand, so I opened the new Runway Agent 2.0 to try it out. here's how it went: → it generated the music and the key image first, so I could approve the direction → once I gave the ok, it built the full video around it → and when something was off, i changed just that one piece, without redoing the rest one prompt, and I had the ad we needed, work that used to take weeks. this is what it made 👇 if you want to try it → · 30% off 3 months with code RUNWAYAGENT — made with Runway · #MadeWithRunway · #ad
0:18

🚨 one person can now do the work of an entire creative team. i just tested it on a real one. a friend needed an ad for his brand, so I opened the new Runway Agent 2.0 to try it out. here's how it went: → it generated the music and the key image first, so I could approve the direction → once I gave the ok, it built the full video around it → and when something was off, i changed just that one piece, without redoing the rest one prompt, and I had the ad we needed, work that used to take weeks. this is what it made 👇 if you want to try it → · 30% off 3 months with code RUNWAYAGENT — made with Runway · #MadeWithRunway · #ad

brenz.

28,698 Aufrufe • vor 1 Monat

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓
0:15

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

Argona

887,792 Aufrufe • vor 7 Tagen

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."
0:15

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."

Kōda

48,253 Aufrufe • vor 6 Tagen

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.
0:17

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.

Anam Hira

42,149 Aufrufe • vor 1 Monat

WTF, GROK BOT JUST MADE AI AGENTS AVAILABLE TO LITERALLY ANYONE – CREATING CONTENT HAS NEVER BEEN THIS EASY, EVEN IF YOU'VE NEVER MADE ANYTHING BEFORE Content was never a talent problem. It's a headcount problem. One person doing research, design, copy, analytics, timing and publishing – that's six jobs. The switching between them is what kills consistency, not a lack of ideas. Here's what one of these setups actually looks like. A Chief of Staff sits in the middle and routes every task. Nothing lands on the human. → Researcher tracks what's actually moving and pulls real sources instead of guesswork → Writer turns that research into finished copy, ready to review → Visualiser gets fed a few reference visuals once, then ships everything in that style → Analyst reads the numbers and tells the rest of the team what worked → Scheduler owns timing and holds the queue → Publisher ships it The part that makes it work: every agent on Grok Bot gets its own persistent computer, browser and file system – and they all share memory. So the research is already sitting inside the draft before the draft starts. No copy-pasting between tools. No approving every step. No human in the middle. You can even teach an agent a repetitive task by recording yourself doing it once. Start recording, do the thing, stop. It learns the pattern. And that's the real shift. Nobody needs AI to tell them what to post. They need it to delete the 40 steps between the idea and the post. Everyone has a backlog of things they've meant to make for months. This is what starts clearing it. Full breakdown of the setup in the article below ↓
0:20

WTF, GROK BOT JUST MADE AI AGENTS AVAILABLE TO LITERALLY ANYONE – CREATING CONTENT HAS NEVER BEEN THIS EASY, EVEN IF YOU'VE NEVER MADE ANYTHING BEFORE Content was never a talent problem. It's a headcount problem. One person doing research, design, copy, analytics, timing and publishing – that's six jobs. The switching between them is what kills consistency, not a lack of ideas. Here's what one of these setups actually looks like. A Chief of Staff sits in the middle and routes every task. Nothing lands on the human. → Researcher tracks what's actually moving and pulls real sources instead of guesswork → Writer turns that research into finished copy, ready to review → Visualiser gets fed a few reference visuals once, then ships everything in that style → Analyst reads the numbers and tells the rest of the team what worked → Scheduler owns timing and holds the queue → Publisher ships it The part that makes it work: every agent on Grok Bot gets its own persistent computer, browser and file system – and they all share memory. So the research is already sitting inside the draft before the draft starts. No copy-pasting between tools. No approving every step. No human in the middle. You can even teach an agent a repetitive task by recording yourself doing it once. Start recording, do the thing, stop. It learns the pattern. And that's the real shift. Nobody needs AI to tell them what to post. They need it to delete the 40 steps between the idea and the post. Everyone has a backlog of things they've meant to make for months. This is what starts clearing it. Full breakdown of the setup in the article below ↓

SCOTTY BEAM

4,610,705 Aufrufe • vor 1 Tag