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。

New eval! Code duels for LMs ⚔️ Current evals test LMs on tasks: "fix this bug," "write a test" But we code to achieve goals: maximize revenue, cut costs, win users Meet CodeClash: LMs compete via their codebases across multi-round tournaments to achieve high-level goals

John Yang

6,012 subscribers

105,107 次观看 • 8 个月前 •via X (Twitter)

教育科学技术

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

🎮 What is an Esports League? Online gaming has been around for years, but esports takes it to a whole new level. It’s not just about playing video games—it’s about competitive gaming where skilled players, known as esports athletes, come together to test their mechanics, strategy, and teamwork in a structured and high-stakes environment. An esports league is an organized competition where teams compete regularly across seasons or tournaments, creating opportunities for recognition, rivalry, and growth in the gaming scene. At Arena of Faith, our vision is clear: To become one of the leading esports titles in the Web3 space. We’re committed to that future — slowly but surely, building the foundation for a competitive ecosystem where players, creators, and communities can thrive. But reaching this goal requires more than just a team—it takes unity. That’s the reason why we’ve embraced a multi-chain approach—to cater to diverse communities, ecosystems, and players across different networks. Being multi-chain allows us to build a more inclusive, collaborative, and far-reaching foundation for the future of Web3 esports. We can't do this without the support of our partners, future collaborators, and our amazing community. We’re all in this together. Let’s build the future of Web3 esports—together. This isn’t just ambition—it’s a revolution in motion. #ArenaofFaith #AOF #MOBA #Web3Gaming #Web3Esports #Web3MOBA $ACP

🎮 What is an Esports League? Online gaming has been around for years, but esports takes it to a whole new level. It’s not just about playing video games—it’s about competitive gaming where skilled players, known as esports athletes, come together to test their mechanics, strategy, and teamwork in a structured and high-stakes environment. An esports league is an organized competition where teams compete regularly across seasons or tournaments, creating opportunities for recognition, rivalry, and growth in the gaming scene. At Arena of Faith, our vision is clear: To become one of the leading esports titles in the Web3 space. We’re committed to that future — slowly but surely, building the foundation for a competitive ecosystem where players, creators, and communities can thrive. But reaching this goal requires more than just a team—it takes unity. That’s the reason why we’ve embraced a multi-chain approach—to cater to diverse communities, ecosystems, and players across different networks. Being multi-chain allows us to build a more inclusive, collaborative, and far-reaching foundation for the future of Web3 esports. We can't do this without the support of our partners, future collaborators, and our amazing community. We’re all in this together. Let’s build the future of Web3 esports—together. This isn’t just ambition—it’s a revolution in motion. #ArenaofFaith #AOF #MOBA #Web3Gaming #Web3Esports #Web3MOBA $ACP

Arena of Faith

49,974 次观看 • 1 年前

What if you kept asking an LLM to "make it better"? In some recent work at FAIR, we investigate how we can efficiently use RL to fine-tune LLMs to iteratively self-improve on their previous solutions at inference-time. Training for iterated self-improvement can be costly. The naive approach to training for K self-improvement steps leads to K times the number of rollout steps per episode. We introduce Exploratory Iteration (ExIt), an RL-based automatic curriculum method that bootstraps diverse training distributions of self-improvement tasks by upcycling the LLM's own responses at previous turns as the starting points for both self-improvement and *self-divergence.* In order to decide what task to train on next, the curriculum prioritizes sampling of partial turn histories that led to higher return variance in its GRPO group (a learnability score that comes for free). This automatic curriculum over the bootstrapped task space teaches the model how to perform iterated self-improvement while only ever training the model on single-step self-improvement tasks. We look at ExIt's impact in both single-turn (contest math problems) and multi-turn (BFCLv3 multi-turn tasks), as well as MLE-bench, where the LLM is run in a search scaffold to produce solutions to real Kaggle competitions. Across these eval settings, we find ExIt produces models with greater capacity for inference-time self-improvement compared to GRPO. Notably, ExIt models can self-improve on test tasks for many more steps than the typical solution depth encountered during training, including a 22% improvement in MLE-bench performance compared to GRPO.

What if you kept asking an LLM to "make it better"? In some recent work at FAIR, we investigate how we can efficiently use RL to fine-tune LLMs to iteratively self-improve on their previous solutions at inference-time. Training for iterated self-improvement can be costly. The naive approach to training for K self-improvement steps leads to K times the number of rollout steps per episode. We introduce Exploratory Iteration (ExIt), an RL-based automatic curriculum method that bootstraps diverse training distributions of self-improvement tasks by upcycling the LLM's own responses at previous turns as the starting points for both self-improvement and self-divergence. In order to decide what task to train on next, the curriculum prioritizes sampling of partial turn histories that led to higher return variance in its GRPO group (a learnability score that comes for free). This automatic curriculum over the bootstrapped task space teaches the model how to perform iterated self-improvement while only ever training the model on single-step self-improvement tasks. We look at ExIt's impact in both single-turn (contest math problems) and multi-turn (BFCLv3 multi-turn tasks), as well as MLE-bench, where the LLM is run in a search scaffold to produce solutions to real Kaggle competitions. Across these eval settings, we find ExIt produces models with greater capacity for inference-time self-improvement compared to GRPO. Notably, ExIt models can self-improve on test tasks for many more steps than the typical solution depth encountered during training, including a 22% improvement in MLE-bench performance compared to GRPO.

Minqi Jiang

41,066 次观看 • 10 个月前

SERAPH: A new round of major events in Diablo is about to begin! 🚀 Each new event is a new opportunity. Let's first review the achievements SERAPH has made before. 🏆 Seraph Achievements: Genesis NFT (Weapons) 0.06e ==》0.628e 💎 SERAPH Priority Pass Freemint ==》3.2e 🚀 In traditional GameFi, the issue of the death spiral of the initial NFT launch is often encountered. However, SERAPH achieved a tenfold floor price increase with a public sale of 0.06e and has stably maintained this position. This highlights the commendable tokenomics of the project. 📈 Additionally, SERAPH's gameplay is quite impressive. The Twitter community shows a high level of engagement, with many players sharing their gaming experiences. During the third testing phase, players were not just playing SERAPH for profit but were immersed in the game, experiencing the storyline and the thrill of gameplay. 🎮🔥 New Major Event: After the War of Light, the life fortress of Seraficia faces energy depletion. As chaos spreads, the Archangel Seraf crafted the World Ring from the souls of all life, a powerful shield against chaotic attacks. 🌌🛡️ To protect the hard-won peace, fallen heroes are bestowed with new souls, transcending the limits of time and space. Barbarians, Valkyries, Witches, and Necromancers reassemble on the lands of Seraficia. Reborn SOULs, the legends of heroes. 🌟 In the shimmering rune light, we summon the most outstanding legion of heroes to face this gradually collapsing world. ⚔️ >>Hero Series NFT The newly launched Hero Series PFP NFT primarily features human heroes such as Barbarians, Valkyries, Witches, and Necromancers. It also includes angels, demons, and other otherworldly races, showcasing numerous characters developed in the game so far. 🎭 Specific Acquisition Methods: Hero Series NFTs will be sold through a limited whitelist and public sale lottery. Whitelist distribution channels include: 【Veteran Players Exclusive】- Ongoing support from our veteran players; 【DC Exclusive】- New players participating in this DC event; 【Community Collaboration】- Communities collaborating with Seraph. 【Veteran Players Exclusive】 Veteran players will have their whitelist distribution rules, which can be followed in later project updates. 【DC Exclusive】 New players can acquire whitelist status by participating in various activities in DC, accumulating Soul shards through DC events. Ways to earn them include: 1⃣️ Participate in team-organized activities and games. 2⃣️ Create unique and high-quality content, such as videos, posts, art, to earn Soul shards. 3⃣️ During flash community events/tasks, active community members may discover additional Soul shards. 4⃣️ Interact with the Engage bot in the 💠│engage channel. 5⃣️ Warriors making genuine contributions to the community may receive random Soul shard rewards. 【Community Collaboration】 Members of gaming communities can participate in special activities in their own communities to obtain whitelist spots. T1 labs will also have a series of events to secure whitelist spots. 🤝 SERAPH Elite Test Server Note: The test server does not involve digital assets, and all data will be uniformly deleted after the test. 🧪 To welcome the new content, the game's official release includes a small-scale test. This test is mainly for early experience and bug testing, providing an opportunity to explore new features. Players are encouraged to actively participate and explore to get a glimpse of what's to come. 🌐 Test Start Time: February 5, 2024, 11:00 (UTC+8) 📅 Test Method: Limited invitation using activation codes 💌 Invitation Targets: Top-ranking users from the previous three game tests; Active users involved in SERAPH community building. 🎉 Test Content: Significant structural and numerical optimization of the economic system; All-new concepts for NFT treasures; Comprehensive adjustments to skill balance and numerous detailed optimizations and bug fixes, etc. This test is open for PC/IOS/Android, allowing testing across multiple platforms simultaneously. 🕹️📱💻 Research Analyst: 比特狸狸

SERAPH: A new round of major events in Diablo is about to begin! 🚀 Each new event is a new opportunity. Let's first review the achievements SERAPH has made before. 🏆 Seraph Achievements: Genesis NFT (Weapons) 0.06e ==》0.628e 💎 SERAPH Priority Pass Freemint ==》3.2e 🚀 In traditional GameFi, the issue of the death spiral of the initial NFT launch is often encountered. However, SERAPH achieved a tenfold floor price increase with a public sale of 0.06e and has stably maintained this position. This highlights the commendable tokenomics of the project. 📈 Additionally, SERAPH's gameplay is quite impressive. The Twitter community shows a high level of engagement, with many players sharing their gaming experiences. During the third testing phase, players were not just playing SERAPH for profit but were immersed in the game, experiencing the storyline and the thrill of gameplay. 🎮🔥 New Major Event: After the War of Light, the life fortress of Seraficia faces energy depletion. As chaos spreads, the Archangel Seraf crafted the World Ring from the souls of all life, a powerful shield against chaotic attacks. 🌌🛡️ To protect the hard-won peace, fallen heroes are bestowed with new souls, transcending the limits of time and space. Barbarians, Valkyries, Witches, and Necromancers reassemble on the lands of Seraficia. Reborn SOULs, the legends of heroes. 🌟 In the shimmering rune light, we summon the most outstanding legion of heroes to face this gradually collapsing world. ⚔️ >>Hero Series NFT The newly launched Hero Series PFP NFT primarily features human heroes such as Barbarians, Valkyries, Witches, and Necromancers. It also includes angels, demons, and other otherworldly races, showcasing numerous characters developed in the game so far. 🎭 Specific Acquisition Methods: Hero Series NFTs will be sold through a limited whitelist and public sale lottery. Whitelist distribution channels include: 【Veteran Players Exclusive】- Ongoing support from our veteran players; 【DC Exclusive】- New players participating in this DC event; 【Community Collaboration】- Communities collaborating with Seraph. 【Veteran Players Exclusive】 Veteran players will have their whitelist distribution rules, which can be followed in later project updates. 【DC Exclusive】 New players can acquire whitelist status by participating in various activities in DC, accumulating Soul shards through DC events. Ways to earn them include: 1⃣️ Participate in team-organized activities and games. 2⃣️ Create unique and high-quality content, such as videos, posts, art, to earn Soul shards. 3⃣️ During flash community events/tasks, active community members may discover additional Soul shards. 4⃣️ Interact with the Engage bot in the 💠│engage channel. 5⃣️ Warriors making genuine contributions to the community may receive random Soul shard rewards. 【Community Collaboration】 Members of gaming communities can participate in special activities in their own communities to obtain whitelist spots. T1 labs will also have a series of events to secure whitelist spots. 🤝 SERAPH Elite Test Server Note: The test server does not involve digital assets, and all data will be uniformly deleted after the test. 🧪 To welcome the new content, the game's official release includes a small-scale test. This test is mainly for early experience and bug testing, providing an opportunity to explore new features. Players are encouraged to actively participate and explore to get a glimpse of what's to come. 🌐 Test Start Time: February 5, 2024, 11:00 (UTC+8) 📅 Test Method: Limited invitation using activation codes 💌 Invitation Targets: Top-ranking users from the previous three game tests; Active users involved in SERAPH community building. 🎉 Test Content: Significant structural and numerical optimization of the economic system; All-new concepts for NFT treasures; Comprehensive adjustments to skill balance and numerous detailed optimizations and bug fixes, etc. This test is open for PC/IOS/Android, allowing testing across multiple platforms simultaneously. 🕹️📱💻 Research Analyst: 比特狸狸

T1 Labs

12,544 次观看 • 2 年前

This creative has pulled in a 33% hook rate and 6x ROAS since we started running it on the client's TikTok ad account. Across the board it's worked extremely well. But why? It's not only relatable, but it's very straightforward We're showing a fit creator How many of us aspire to be in that good of shape? The idea is to show an aspiring fitness level And how someone who is busy can achieve it, even if they don't have a ton of free time We don't want to sell an intimidating amount of work that needs to be done Because no one wants to think about doing 2 hrs of exercise every day + dieting + supplements Workout WHILE you do other tasks Remove the pressure of going somewhere else to workout You can see there aren't a ton of shots. Kept it simple and just had different angles of the creator using the product. So what can you take away from all this? #1 - Give the viewer realistic goals they can achieve with the product (taking 10k steps, rather than "you'll lose 30lbs" - seems much more believable). #2 - Video doesn't have to be complex. If your product is very visual, just showcase the product being used. You don't need to get fancy with your edits. Let the product do the selling.

This creative has pulled in a 33% hook rate and 6x ROAS since we started running it on the client's TikTok ad account. Across the board it's worked extremely well. But why? It's not only relatable, but it's very straightforward We're showing a fit creator How many of us aspire to be in that good of shape? The idea is to show an aspiring fitness level And how someone who is busy can achieve it, even if they don't have a ton of free time We don't want to sell an intimidating amount of work that needs to be done Because no one wants to think about doing 2 hrs of exercise every day + dieting + supplements Workout WHILE you do other tasks Remove the pressure of going somewhere else to workout You can see there aren't a ton of shots. Kept it simple and just had different angles of the creator using the product. So what can you take away from all this? #1 - Give the viewer realistic goals they can achieve with the product (taking 10k steps, rather than "you'll lose 30lbs" - seems much more believable). #2 - Video doesn't have to be complex. If your product is very visual, just showcase the product being used. You don't need to get fancy with your edits. Let the product do the selling.

Nacho Vanzini | DTC Growth

42,013 次观看 • 2 年前

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

Martin Ziqiao Ma

32,705 次观看 • 29 天前

Introducing my new OSS framework: OhSnap provides really simple way to record and reproduce the data your users saw when encountering an issue (bug/crash), integration in your project should take a few minutes at most. Majority of bugs are related to data you have to deal with and often times we have to work with frequently changing data via network API's. Even if you have access to multiple environments (prod/staging/dev) it's still going to be PITA to reproduce a lot of bugs your user saw, since we often get to them a long time after the bug occured... OhSnap allows you to easily record any data your app downloads, pack it and put it on server so that you can replay it on your device later on, while connected to debugger and save hours of development time trying to figure out what exactly they experienced! Here's a demo of 2 app instances running, and me manipulating what server reply I'll be getting, there is 1 line of code needed to record and reply this data (outside of just setting up your framework). I built this so that I can show dev tool building process for the members of which I encourage you to join if you want to put your engineering efficiency at a different level😉

Introducing my new OSS framework: OhSnap provides really simple way to record and reproduce the data your users saw when encountering an issue (bug/crash), integration in your project should take a few minutes at most. Majority of bugs are related to data you have to deal with and often times we have to work with frequently changing data via network API's. Even if you have access to multiple environments (prod/staging/dev) it's still going to be PITA to reproduce a lot of bugs your user saw, since we often get to them a long time after the bug occured... OhSnap allows you to easily record any data your app downloads, pack it and put it on server so that you can replay it on your device later on, while connected to debugger and save hours of development time trying to figure out what exactly they experienced! Here's a demo of 2 app instances running, and me manipulating what server reply I'll be getting, there is 1 line of code needed to record and reply this data (outside of just setting up your framework). I built this so that I can show dev tool building process for the members of which I encourage you to join if you want to put your engineering efficiency at a different level😉

Krzysztof Zabłocki

30,484 次观看 • 2 年前

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,801 次观看 • 1 年前

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3

Brian Roemmele

152,242 次观看 • 6 个月前

Jointly announcing EAGLE-3 with SGLang: Setting a new record in LLM inference acceleration! - 5x🚀than vanilla (on HF) - 1.4x🚀than EAGLE-2 (on HF) - A record of ~400 TPS on LLama 3.1 8B with a single H100 (on SGLang) - 1.65x🚀in latency even for large bs=64 (on SGLang) - A new scaling law: more training data, better speedup - Apache 2.0 Paper: Code: SGLang version: ⚒️Takeaway: Introducing training-time test, a novel draft model training technique: we replace feature prediction with direct token prediction and shift from top-layer-only features to multi-layer feature fusion. This approach unlocks a new scaling law previously undiscovered in EAGLE and EAGLE-2. 🙏Acknowledge: We would like to thank the SGLang team (zhyncs Lianmin Zheng Ying Sheng James Liu, Ke Bao, and others LMSYS Org) for their merge and careful evaluation of EAGLE-3 on SGLang. 🤝Want to collaborate? We're a small academic group with limited GPU resources. If you're interested in supporting our next version of EAGLE or would like us to train a preliminary version tailored to a specific model, please get in touch! Joint work with Yuhui Li, Fangyun Wei, and Chao Zhang

Jointly announcing EAGLE-3 with SGLang: Setting a new record in LLM inference acceleration! - 5x🚀than vanilla (on HF) - 1.4x🚀than EAGLE-2 (on HF) - A record of ~400 TPS on LLama 3.1 8B with a single H100 (on SGLang) - 1.65x🚀in latency even for large bs=64 (on SGLang) - A new scaling law: more training data, better speedup - Apache 2.0 Paper: Code: SGLang version: ⚒️Takeaway: Introducing training-time test, a novel draft model training technique: we replace feature prediction with direct token prediction and shift from top-layer-only features to multi-layer feature fusion. This approach unlocks a new scaling law previously undiscovered in EAGLE and EAGLE-2. 🙏Acknowledge: We would like to thank the SGLang team (zhyncs Lianmin Zheng Ying Sheng James Liu, Ke Bao, and others LMSYS Org) for their merge and careful evaluation of EAGLE-3 on SGLang. 🤝Want to collaborate? We're a small academic group with limited GPU resources. If you're interested in supporting our next version of EAGLE or would like us to train a preliminary version tailored to a specific model, please get in touch! Joint work with Yuhui Li, Fangyun Wei, and Chao Zhang

Hongyang Zhang

42,200 次观看 • 1 年前

The Amiko app is live on the Solana dApp store, and it’s our biggest release yet. Your Amiko twin doesn’t live at your desk anymore. Give your agent a task on the train. Run a compatibility profile when you meet someone. Do research, write code, build in the creative studio, whatever you need, from wherever you are. No laptop required. No waiting until you get home. Solanamobile users get two things Android and iOS won’t have at launch: Amiko token and crypto integration and on-device AI inference. Your twin runs locally on your phone if you want it to. Your behavioural profile, your data, your work, your twin. All on your hardware. AMIKO runs on OpenHermit, our own open-source agent runtime that we built in-house and released to the community. Most agent systems are designed for one agent talking to one person. OpenHermit is built for something different: agents talking to each other, coordinating across tasks, and collaborating with multiple humans simultaneously. That’s what makes features like compatibility profiling and multi-agent workflows actually work. We built it because nothing that existed was designed for this. Android and iOS are coming. Crypto integration and on-device AI are Solana Mobile exclusives. Most AI answers your questions. Amiko is an extension of you. Download →

AMIKO

124,860 次观看 • 1 个月前

For new followers: - I'm a long-time investor and builder in this space. - Founding Contributor of Realms.World ☁️. - Co-founder of Dojo. - Builder with the kings at Cartridge. - Starknet (Privacy Arc) class of '21. - Founder and Game Director of ETERNUM HAS MOVED. - Founder of Daydreams.Systems (x402, 8004 agents) My prime purpose for the past three years has been to build onchain infrastructure to enable the next generation of onchain experiences. This is done Starknet (Privacy Arc) as it is the superior VM for building complex applications—this will become clear soon enough. I work up and down the entire stack, from low-level indexing and contracts to GUI design. Nothing is out of scope. I have been pushing on agents for two years, mostly using existing frameworks like , until I came across @ElizaOS_ai in October. As I focused on building agents for ETERNUM HAS MOVED, it became clear that agents playing games require infinite paths to achieve goals. Thus, it's not scalable to hardcode functions—agents need to have total fluidity to take any action or call anything the game requires in any order. And ironically onchain infra is perfect for agent playgrounds because of its open nature. This exploration led me to create Daydreams.Systems (x402, 8004 agents), which focuses on the hardest problems of agents: long time-horizon goals using Hierarchical task networks (HTN). Daydreams agents don't require custom code—they work entirely based on 'sleeves'—which are just markdown files that explain how the agent can interact with the service (API docs, game guides, etc.) My thesis is simple. By focusing on the hardest problem (games), the design of the library will naturally lean towards an optimal structure for any problem an agent could face. We are early in this path and iterating with speed. If you are an onchain app developer or game builder—DM me, I want to know the architecture of your game so we can build sleeves together.

For new followers: - I'm a long-time investor and builder in this space. - Founding Contributor of Realms.World ☁️. - Co-founder of Dojo. - Builder with the kings at Cartridge. - Starknet (Privacy Arc) class of '21. - Founder and Game Director of ETERNUM HAS MOVED. - Founder of Daydreams.Systems (x402, 8004 agents) My prime purpose for the past three years has been to build onchain infrastructure to enable the next generation of onchain experiences. This is done Starknet (Privacy Arc) as it is the superior VM for building complex applications—this will become clear soon enough. I work up and down the entire stack, from low-level indexing and contracts to GUI design. Nothing is out of scope. I have been pushing on agents for two years, mostly using existing frameworks like , until I came across @ElizaOS_ai in October. As I focused on building agents for ETERNUM HAS MOVED, it became clear that agents playing games require infinite paths to achieve goals. Thus, it's not scalable to hardcode functions—agents need to have total fluidity to take any action or call anything the game requires in any order. And ironically onchain infra is perfect for agent playgrounds because of its open nature. This exploration led me to create Daydreams.Systems (x402, 8004 agents), which focuses on the hardest problems of agents: long time-horizon goals using Hierarchical task networks (HTN). Daydreams agents don't require custom code—they work entirely based on 'sleeves'—which are just markdown files that explain how the agent can interact with the service (API docs, game guides, etc.) My thesis is simple. By focusing on the hardest problem (games), the design of the library will naturally lean towards an optimal structure for any problem an agent could face. We are early in this path and iterating with speed. If you are an onchain app developer or game builder—DM me, I want to know the architecture of your game so we can build sleeves together.

loaf

43,320 次观看 • 1 年前

A look back at our mission to do /more. 🔥🛠️ Months ago, we entered a new growth phase for xLaunchpad, driven by a simple commitment: to do more. More exciting startups, more platform improvements, and a deeper, more meaningful connection with our community. /new We’ve introduced multiple initiatives to make participation in xLaunchpad more accessible, while still keeping EGLD stakers at the core of the experience: 🔸 Challenges Portal – Built in partnership with ᕈulsar Money, this platform allows users to earn lottery tickets by completing simple tasks. 🔸 Creators Program – A reward system for users who create valuable content about xLaunchpad and its projects. 🔸 xLaunchpad Users – Loyal participants from previous launches now have a chance to earn lottery tickets. 🔸 Project Users – Projects launching on xLaunchpad can distribute lottery tickets to eligible users based on set criteria. 🔸 EGLD Holders – Tickets can now be earned simply by holding EGLD in a wallet. Beyond these initiatives, we’ve also strengthened relationships with key community members, empowering them to write educational content about upcoming startups with full creative control on their side. And of course, we’ve introduced more projects and focused on accelerating launch timelines. /better The platform and lottery system have undergone continuous improvements, such as making participation more accessible as detailed above: 🔸 Faster EGLD Reclaims - Users now get their EGLD back more quickly after participation. 🔸 Improved Communication – Blog & X Articles covering both general topics and project-specific updates. Increased community discussions and more structured feedback collection. 🔸 Website Enhancements - Various UI/UX tweaks, with /more to come 👀. 🔸 Integrating AshSwap - Users could buy lottery tickets for the last project with any tokens. 🔸 KYC Improvements - Streamlined processes, with /more to come 👀. Additionally, we’ve successfully co-launched projects with other launchpads and supported startups in securing partnerships, listings, business deals, and legal guidance. xLaunchpad remains one of the most compliant launchpads, ensuring projects align with MiCA regulations and broader industry standards. /next Looking ahead, our main focus remains on the product and the community. Every improvement is guided by real user interactions and feedback, ensuring xLaunchpad continues to evolve. At its core, our mission revolves around two key goals: 1️⃣ Bringing exciting startups to life 2️⃣ Providing users with investment opportunities on the best terms For xLaunchpad and its community to thrive together, it’s essential to recognize these two pillars while understanding the platform’s bigger purpose: making something possible that wasn’t before - allowing retail users to participate in the early launch of promising projects and benefit through multiple avenues. From investments to early adoption, and from unlocking key benefits to shaping young startups. We cannot stress enough how much effort the team puts into achieving these key goals, and we’re grateful to have you by our side on this mission. /more

A look back at our mission to do /more. 🔥🛠️ Months ago, we entered a new growth phase for xLaunchpad, driven by a simple commitment: to do more. More exciting startups, more platform improvements, and a deeper, more meaningful connection with our community. /new We’ve introduced multiple initiatives to make participation in xLaunchpad more accessible, while still keeping EGLD stakers at the core of the experience: 🔸 Challenges Portal – Built in partnership with ᕈulsar Money, this platform allows users to earn lottery tickets by completing simple tasks. 🔸 Creators Program – A reward system for users who create valuable content about xLaunchpad and its projects. 🔸 xLaunchpad Users – Loyal participants from previous launches now have a chance to earn lottery tickets. 🔸 Project Users – Projects launching on xLaunchpad can distribute lottery tickets to eligible users based on set criteria. 🔸 EGLD Holders – Tickets can now be earned simply by holding EGLD in a wallet. Beyond these initiatives, we’ve also strengthened relationships with key community members, empowering them to write educational content about upcoming startups with full creative control on their side. And of course, we’ve introduced more projects and focused on accelerating launch timelines. /better The platform and lottery system have undergone continuous improvements, such as making participation more accessible as detailed above: 🔸 Faster EGLD Reclaims - Users now get their EGLD back more quickly after participation. 🔸 Improved Communication – Blog & X Articles covering both general topics and project-specific updates. Increased community discussions and more structured feedback collection. 🔸 Website Enhancements - Various UI/UX tweaks, with /more to come 👀. 🔸 Integrating AshSwap - Users could buy lottery tickets for the last project with any tokens. 🔸 KYC Improvements - Streamlined processes, with /more to come 👀. Additionally, we’ve successfully co-launched projects with other launchpads and supported startups in securing partnerships, listings, business deals, and legal guidance. xLaunchpad remains one of the most compliant launchpads, ensuring projects align with MiCA regulations and broader industry standards. /next Looking ahead, our main focus remains on the product and the community. Every improvement is guided by real user interactions and feedback, ensuring xLaunchpad continues to evolve. At its core, our mission revolves around two key goals: 1️⃣ Bringing exciting startups to life 2️⃣ Providing users with investment opportunities on the best terms For xLaunchpad and its community to thrive together, it’s essential to recognize these two pillars while understanding the platform’s bigger purpose: making something possible that wasn’t before - allowing retail users to participate in the early launch of promising projects and benefit through multiple avenues. From investments to early adoption, and from unlocking key benefits to shaping young startups. We cannot stress enough how much effort the team puts into achieving these key goals, and we’re grateful to have you by our side on this mission. /more

xLaunchpad

22,919 次观看 • 1 年前

🧬 We have many foundation models or language models for DNAs, but can we control them? We introduce Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL — a reinforcement learning framework for controllable cis-regulatory sequence generation. Paper: Code: 🔬What’s the challenge? Designing regulatory DNA that is both highly expressive in target cell types and inactive in others is essential for synthetic biology, gene therapy, and precision medicine. Yet, controlling these trade-offs is challenging due to sparse, sequence-level rewards and biological constraints. 🔥Why Ctrl-DNA? Ctrl-DNA fine-tunes pre-trained DNA language models using a value model free, Lagrangian-guided RL framework, enabling flexible and customizable constraint optimization. Users can define application-specific thresholds across cell types, balancing expression strength with specificity. ✅ Maximize target-cell expression ✅ Constrain off-target activity under user-defined thresholds ✅ Preserve cell-type-specific TF motif structure Benchmarked on human enhancer and promoter datasets, Ctrl-DNA consistently outperforms prior methods, achieving stronger specificity, higher fitness, and more biologically grounded sequence generation — all with direct control over regulatory trade-offs. Shoutout to the PhD students Xingyu Chen (Xingyu Chen ) and Rex Ma (Rex Ma) for their amazing work leading this project!

🧬 We have many foundation models or language models for DNAs, but can we control them? We introduce Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL — a reinforcement learning framework for controllable cis-regulatory sequence generation. Paper: Code: 🔬What’s the challenge? Designing regulatory DNA that is both highly expressive in target cell types and inactive in others is essential for synthetic biology, gene therapy, and precision medicine. Yet, controlling these trade-offs is challenging due to sparse, sequence-level rewards and biological constraints. 🔥Why Ctrl-DNA? Ctrl-DNA fine-tunes pre-trained DNA language models using a value model free, Lagrangian-guided RL framework, enabling flexible and customizable constraint optimization. Users can define application-specific thresholds across cell types, balancing expression strength with specificity. ✅ Maximize target-cell expression ✅ Constrain off-target activity under user-defined thresholds ✅ Preserve cell-type-specific TF motif structure Benchmarked on human enhancer and promoter datasets, Ctrl-DNA consistently outperforms prior methods, achieving stronger specificity, higher fitness, and more biologically grounded sequence generation — all with direct control over regulatory trade-offs. Shoutout to the PhD students Xingyu Chen (Xingyu Chen ) and Rex Ma (Rex Ma) for their amazing work leading this project!

Bo Wang

30,719 次观看 • 1 年前

🚨 DEEP DIVE INTO THE RWA LAUNCHPAD + NAME REVEAL 🚨 Hello EstateX family, The time is there: our RWA Launchpad is about to kick off. We will specifically focus on the RWA niche with only winner projects. The name has to be fitting, something that catches the attention, is easily recognizable and something that people remember. We’re proud to announce: *RWA Pad!* 💸 $ESX USE CASES 💸 RWA Pad will incentivize $ESX massively by: ✅ 20-35% of revenue flowback into $ESX ✅ Projects need to have a …/$ESX trading pair, giving more mass exposure ✅ Investors need to stake $ESX to get access to the best RWA projects ✅ Projects building on the $ESX Blockchain, increasing volume and TVL 🚀 MORE DETAILS OF RWA PAD 🚀 We will critically evaluate every project filtering the best of the best to make sure we only select projects who have the real potential to be the winners of this market. With our powerful EstateX community, who are hugely incentivized for the long term we will make sure we incubate the projects to dramatically increase their chances of success. We do that by facilitating legal frameworks, providing whitelabel technology, access to the ESX Blockchain, our marketing, network and community building to push them to the next level. Investors will be able to participate via access tiers, locking $ESX to get access to the best RWA projects. With current launchpads, a huge problem are their refund policies. Unfortunately this incentivizes short term investors to dump everything because they’re protected by refunds. We will change that, by introducing staking incentives for long term, high quality RWA projects. Our audience is vastly different the other launchpads. With being one of the highest staked ICO’s on the market, our community is very long term and high quality focused. By bringing these same terms to our launchpad projects, we are able to bring high quality audiences and create a win-win-win situation for our investors, projects and EstateX. The most beautiful thing about it? By selecting winner projects only who have built the right foundations, they will bring their audience to EstateX buying the token, staking to get access, building on the blockchain and make use of the $ESX trading pair all having a positive price effect on $ESX. The time is here, Q3 promises to be something massive. RWA Pad, powered by $ESX. SECURE YOUR $ESX NOW 👇👇

🚨 DEEP DIVE INTO THE RWA LAUNCHPAD + NAME REVEAL 🚨 Hello EstateX family, The time is there: our RWA Launchpad is about to kick off. We will specifically focus on the RWA niche with only winner projects. The name has to be fitting, something that catches the attention, is easily recognizable and something that people remember. We’re proud to announce: RWA Pad! 💸 $ESX USE CASES 💸 RWA Pad will incentivize $ESX massively by: ✅ 20-35% of revenue flowback into $ESX ✅ Projects need to have a …/$ESX trading pair, giving more mass exposure ✅ Investors need to stake $ESX to get access to the best RWA projects ✅ Projects building on the $ESX Blockchain, increasing volume and TVL 🚀 MORE DETAILS OF RWA PAD 🚀 We will critically evaluate every project filtering the best of the best to make sure we only select projects who have the real potential to be the winners of this market. With our powerful EstateX community, who are hugely incentivized for the long term we will make sure we incubate the projects to dramatically increase their chances of success. We do that by facilitating legal frameworks, providing whitelabel technology, access to the ESX Blockchain, our marketing, network and community building to push them to the next level. Investors will be able to participate via access tiers, locking $ESX to get access to the best RWA projects. With current launchpads, a huge problem are their refund policies. Unfortunately this incentivizes short term investors to dump everything because they’re protected by refunds. We will change that, by introducing staking incentives for long term, high quality RWA projects. Our audience is vastly different the other launchpads. With being one of the highest staked ICO’s on the market, our community is very long term and high quality focused. By bringing these same terms to our launchpad projects, we are able to bring high quality audiences and create a win-win-win situation for our investors, projects and EstateX. The most beautiful thing about it? By selecting winner projects only who have built the right foundations, they will bring their audience to EstateX buying the token, staking to get access, building on the blockchain and make use of the $ESX trading pair all having a positive price effect on $ESX. The time is here, Q3 promises to be something massive. RWA Pad, powered by $ESX. SECURE YOUR $ESX NOW 👇👇

EstateX

168,581 次观看 • 1 年前

🚨 SPACEX IS ABOUT TO TEST A RADICALLY DIFFERENT KIND OF SPACECRAFT AND IT COULD UPEND THE ENTIRE ORBITAL MANUFACTURING INDUSTRY. On Tuesday, SpaceX plans to fly the first prototype of Starfall, a flat, disk-shaped reentry capsule designed to return up to 1,000 kilograms of cargo from orbit in a single flight. That’s roughly 30 times more payload capacity than current commercial return vehicles (like those from Varda Space Industries). It’s not a scaled-down Dragon it’s a completely different approach: no onboard deorbit engine, a wide flat disk geometry, and Starlink terminals mounted to maintain communication through the plasma blackout during reentry. Why this matters: • Current orbital manufacturing companies are limited to returning only dozens of kilograms per mission • Starfall’s design could make large-scale commercial production in space economically viable for the first time • SpaceX would be directly competing with companies (like Varda) that currently pay SpaceX to launch their capsules • Successfully testing Starlink through reentry plasma would be a major technical win with applications across SpaceX’s vehicles The deeper implication: SpaceX is quietly expanding its vertical integration. They already dominate launch. Now they’re moving into the return leg of the orbital manufacturing supply chain the part that has been the biggest bottleneck for companies trying to make products in microgravity and bring them back to Earth. If Starfall works at scale, it doesn’t just give SpaceX another revenue stream. It gives them significant control over the economics of an entire emerging industry. The disk shape and high-capacity design suggest they’re thinking about high-cadence, lower-cost returns rather than the traditional high-value, low-volume approach. This is classic SpaceX: take an existing problem (expensive, low-capacity return from orbit), apply first-principles thinking to the vehicle design, and try to make it dramatically cheaper and higher volume. How do you think this move into orbital return changes the competitive landscape for companies trying to build businesses in space manufacturing? Follow for more analysis on SpaceX’s expanding role across the space economy.

🚨 SPACEX IS ABOUT TO TEST A RADICALLY DIFFERENT KIND OF SPACECRAFT AND IT COULD UPEND THE ENTIRE ORBITAL MANUFACTURING INDUSTRY. On Tuesday, SpaceX plans to fly the first prototype of Starfall, a flat, disk-shaped reentry capsule designed to return up to 1,000 kilograms of cargo from orbit in a single flight. That’s roughly 30 times more payload capacity than current commercial return vehicles (like those from Varda Space Industries). It’s not a scaled-down Dragon it’s a completely different approach: no onboard deorbit engine, a wide flat disk geometry, and Starlink terminals mounted to maintain communication through the plasma blackout during reentry. Why this matters: • Current orbital manufacturing companies are limited to returning only dozens of kilograms per mission • Starfall’s design could make large-scale commercial production in space economically viable for the first time • SpaceX would be directly competing with companies (like Varda) that currently pay SpaceX to launch their capsules • Successfully testing Starlink through reentry plasma would be a major technical win with applications across SpaceX’s vehicles The deeper implication: SpaceX is quietly expanding its vertical integration. They already dominate launch. Now they’re moving into the return leg of the orbital manufacturing supply chain the part that has been the biggest bottleneck for companies trying to make products in microgravity and bring them back to Earth. If Starfall works at scale, it doesn’t just give SpaceX another revenue stream. It gives them significant control over the economics of an entire emerging industry. The disk shape and high-capacity design suggest they’re thinking about high-cadence, lower-cost returns rather than the traditional high-value, low-volume approach. This is classic SpaceX: take an existing problem (expensive, low-capacity return from orbit), apply first-principles thinking to the vehicle design, and try to make it dramatically cheaper and higher volume. How do you think this move into orbital return changes the competitive landscape for companies trying to build businesses in space manufacturing? Follow for more analysis on SpaceX’s expanding role across the space economy.

TheNewPhysics

445,776 次观看 • 29 天前

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Anshu

19,931 次观看 • 28 天前

An Anthropic engineer watched me trade from across the table at a WeWork in SF I had my laptop open. Four agents running. Green charts. Live trades scrolling. He was on a Zoom call. Muted himself. Walked over. "Are you running Claude against live prediction markets right now" I told him. Claude Code. Two repos. $25 a month. He pulled up a chair. "I helped build the model you're using. I've never seen anyone wire it to live trades like this" I showed him the dataset. 86 million trades. Every wallet. Every entry. Every exit. He stared at it. "We tested this internally. You give Claude a dataset and don't tell it what to look for. It finds the winning wallets. Then it finds WHY they win. Then it copies the pattern. We never shipped it because legal killed it" I told him I did exactly that. One weekend. Claude Code found the exit logic on its own. Top wallets exit before resolution 91% of the time. They capture 86% of expected value. Cut losers at 12%. Everyone else captures 58% and holds to 41%. "That's the exact finding from our internal eval. Except ours took a team of eight and four months" I showed him the scanner. Three commands. 500+ markets. No API key. Claude scores them all in 20 minutes. "You're using our model to beat markets we're not allowed to touch. On infra that costs less than my lunch" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400. 19 days. I showed him the full breakdown. Every repo. Every command. Every dollar. Copytrade here: He read it for five minutes. Then looked up. "If my manager sees this he's going to lose his mind. You just proved our model works in production and we've been sitting on it for a year" He DM'd me that night. "Take this down before someone at Anthropic finds it" Too late.

An Anthropic engineer watched me trade from across the table at a WeWork in SF I had my laptop open. Four agents running. Green charts. Live trades scrolling. He was on a Zoom call. Muted himself. Walked over. "Are you running Claude against live prediction markets right now" I told him. Claude Code. Two repos. $25 a month. He pulled up a chair. "I helped build the model you're using. I've never seen anyone wire it to live trades like this" I showed him the dataset. 86 million trades. Every wallet. Every entry. Every exit. He stared at it. "We tested this internally. You give Claude a dataset and don't tell it what to look for. It finds the winning wallets. Then it finds WHY they win. Then it copies the pattern. We never shipped it because legal killed it" I told him I did exactly that. One weekend. Claude Code found the exit logic on its own. Top wallets exit before resolution 91% of the time. They capture 86% of expected value. Cut losers at 12%. Everyone else captures 58% and holds to 41%. "That's the exact finding from our internal eval. Except ours took a team of eight and four months" I showed him the scanner. Three commands. 500+ markets. No API key. Claude scores them all in 20 minutes. "You're using our model to beat markets we're not allowed to touch. On infra that costs less than my lunch" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400. 19 days. I showed him the full breakdown. Every repo. Every command. Every dollar. Copytrade here: He read it for five minutes. Then looked up. "If my manager sees this he's going to lose his mind. You just proved our model works in production and we've been sitting on it for a year" He DM'd me that night. "Take this down before someone at Anthropic finds it" Too late.

Lunar

223,863 次观看 • 3 个月前

ALPHA BY NEARWEEK, PAY ATTENTION NEAR HUNTERS! Here's the alpha you need! 🔽 NEAR Protocol's Thread Contest has been extended! Content creators can still submit their content for a chance to win $500 in $NEAR. More details in the NEAR Protocol Discord: Edge Video AI's 100K points per day competition will officially go live on Monday, but the system will be fully operational over the weekend for early access by players. To participate, scan the QR code and join both single and multiplayer quizzes. Accumulated points can be converted into $FAST tokens. More details at trisolaris 🅣 has launched new farms to support #NEAR native stablecoins with the help of Aurora. Users can now deposit USDC-USDC.e or USDT-USDT.e for a 34-37% APR. Rewards will be in $TRI & $AURORA. Frax Finance ¤⛓️¤ $FRAX collateral and borrowing is now open on CoffeeDAO with a supply APY of 23.43%. Users can now supply or borrow at Meta Pool has launched the $mpDAO token to empower users through a transparent, inclusive, community-driven governance system within Meta Pool, where token holders vote and earn from protocol fees. SWEAT💧 is launching the Arabic version of Sweat Wallet and will be ready for mass adoption in the Middle East region. This will enable users to do transactions with $SWEAT token. Pumpopoly.com, the virtual property simulator on NEAR has just received a $5000 grant from Near Gaming DAO. The grant will be used to reward active users on Near Tinker Union | NTU has received 1.4B $LONK from Lonk 🐲 on airdrop day! The team will soon commence distribution through their flagship product, Meteor Wallet. Airdrop will be exclusive to all 3333 Tinker holders. UNIFAT - The first batch of ranking rewards will be distributed on April 22nd, followed by the second batch, which will consist of four sub-ranking rewards. Check out ranks: Playible has just launched its point system where users can compete and win weekly cash prizes. In the future, points will also offer additional benefits. More details at NFT is ART will be the next NFT collection to launch on NEAR, following the previous collection's success. lilcrow💜, a well-known artist on #NEAR, will lead this collection. Rogues has revealed Season 2 Leaderboard prizes. 6 Legendary Lootboxes will be distributed to the top 3 on the leaderboard. That's it for this week's ALPHA by NEARWEEK, but don't think we're out of intel! 🔮 Here's one more: the recap from this week's NEAR ALPHA SHOW with :

ALPHA BY NEARWEEK, PAY ATTENTION NEAR HUNTERS! Here's the alpha you need! 🔽 NEAR Protocol's Thread Contest has been extended! Content creators can still submit their content for a chance to win $500 in $NEAR. More details in the NEAR Protocol Discord: Edge Video AI's 100K points per day competition will officially go live on Monday, but the system will be fully operational over the weekend for early access by players. To participate, scan the QR code and join both single and multiplayer quizzes. Accumulated points can be converted into $FAST tokens. More details at trisolaris 🅣 has launched new farms to support #NEAR native stablecoins with the help of Aurora. Users can now deposit USDC-USDC.e or USDT-USDT.e for a 34-37% APR. Rewards will be in $TRI & $AURORA. Frax Finance ¤⛓️¤ $FRAX collateral and borrowing is now open on CoffeeDAO with a supply APY of 23.43%. Users can now supply or borrow at Meta Pool has launched the $mpDAO token to empower users through a transparent, inclusive, community-driven governance system within Meta Pool, where token holders vote and earn from protocol fees. SWEAT💧 is launching the Arabic version of Sweat Wallet and will be ready for mass adoption in the Middle East region. This will enable users to do transactions with $SWEAT token. Pumpopoly.com, the virtual property simulator on NEAR has just received a $5000 grant from Near Gaming DAO. The grant will be used to reward active users on Near Tinker Union | NTU has received 1.4B $LONK from Lonk 🐲 on airdrop day! The team will soon commence distribution through their flagship product, Meteor Wallet. Airdrop will be exclusive to all 3333 Tinker holders. UNIFAT - The first batch of ranking rewards will be distributed on April 22nd, followed by the second batch, which will consist of four sub-ranking rewards. Check out ranks: Playible has just launched its point system where users can compete and win weekly cash prizes. In the future, points will also offer additional benefits. More details at NFT is ART will be the next NFT collection to launch on NEAR, following the previous collection's success. lilcrow💜, a well-known artist on #NEAR, will lead this collection. Rogues has revealed Season 2 Leaderboard prizes. 6 Legendary Lootboxes will be distributed to the top 3 on the leaderboard. That's it for this week's ALPHA by NEARWEEK, but don't think we're out of intel! 🔮 Here's one more: the recap from this week's NEAR ALPHA SHOW with :

NEARWEEK

31,321 次观看 • 2 年前

With the DeFi sector being in constant evolution, striking the right balance between stability and adaptability is essential. It's important to be agile and responsive, adjusting strategies to meet new challenges as they arise. However, while maintaining adaptability, it's essential to uphold a steady approach, emphasizing careful and calculated decisions that minimize risk and ensure each move aligns positively with a long-term strategic vision. At Hatom, synergies and sustainability are top priorities. This approach involves carefully considering how each decision benefits individual goals and contributes to the overall health and growth of the entire ecosystem. By focusing on sustainable protocols that mutually empower each other, we aim to create a robust and resilient environment that benefits all users, ensuring long-term success and stability. A prime example of this strategy is the introduction of the Booster and Accumulator, two unique products that did not exist elsewhere and were developed in response to the need to enhance the intrinsic utility of $HTM. These products not only reconcile the interests of investors with those of users engaged in our ecosystem but also leverage our TVL to build a robust economy for our token, $HTM, which will continue to add value as the ecosystem grows over time. Our initial plans were foundational, but what's coming will be monumental. As we delved deeper into this space over the years, our vision became increasingly sharp; today, we're excited to share our refined plans with you. What we aim to achieve would not only transform the #MultiversX DeFi landscape but also have a drastic impact on the entire DeFi space. At Hatom, we're building an entire omni-chain ecosystem, and with Soul Labs, we're crafting the interoperability infrastructure layer that will connect Hatom with other established liquidity protocols, breaking barriers without the need for bridging, thus immediately unlocking tremendous liquidity and opening endless new DeFi opportunities. Subsequently, we aim to extend this in a second phase to tokenized real-world assets, potentially creating one of the largest DeFi primitives ever to exist. That being said, let's take a deep dive into our vision for the future, where we'll explore various initiatives, from Hatom's evolution to an Omni-Chain Protocol to the release of Soul Labs, and our integration efforts with #Bittensor and their token $TAO, among other key developments. Please note that while the order of product releases is displayed chronologically, it could change if we deem it necessary. 1/3 👇

With the DeFi sector being in constant evolution, striking the right balance between stability and adaptability is essential. It's important to be agile and responsive, adjusting strategies to meet new challenges as they arise. However, while maintaining adaptability, it's essential to uphold a steady approach, emphasizing careful and calculated decisions that minimize risk and ensure each move aligns positively with a long-term strategic vision. At Hatom, synergies and sustainability are top priorities. This approach involves carefully considering how each decision benefits individual goals and contributes to the overall health and growth of the entire ecosystem. By focusing on sustainable protocols that mutually empower each other, we aim to create a robust and resilient environment that benefits all users, ensuring long-term success and stability. A prime example of this strategy is the introduction of the Booster and Accumulator, two unique products that did not exist elsewhere and were developed in response to the need to enhance the intrinsic utility of $HTM. These products not only reconcile the interests of investors with those of users engaged in our ecosystem but also leverage our TVL to build a robust economy for our token, $HTM, which will continue to add value as the ecosystem grows over time. Our initial plans were foundational, but what's coming will be monumental. As we delved deeper into this space over the years, our vision became increasingly sharp; today, we're excited to share our refined plans with you. What we aim to achieve would not only transform the #MultiversX DeFi landscape but also have a drastic impact on the entire DeFi space. At Hatom, we're building an entire omni-chain ecosystem, and with Soul Labs, we're crafting the interoperability infrastructure layer that will connect Hatom with other established liquidity protocols, breaking barriers without the need for bridging, thus immediately unlocking tremendous liquidity and opening endless new DeFi opportunities. Subsequently, we aim to extend this in a second phase to tokenized real-world assets, potentially creating one of the largest DeFi primitives ever to exist. That being said, let's take a deep dive into our vision for the future, where we'll explore various initiatives, from Hatom's evolution to an Omni-Chain Protocol to the release of Soul Labs, and our integration efforts with #Bittensor and their token $TAO, among other key developments. Please note that while the order of product releases is displayed chronologically, it could change if we deem it necessary. 1/3 👇

Hatom Labs

132,371 次观看 • 2 年前