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。

me realizing that with MiroFish from the Chinese college kid for agent simulations + OpenViking from ByteDance for infinite AI memory + this new Percepta startup that lets LLMs actually COMPUTE real math instead of guessing.. I can now build way more than just a $100k/month prediction bot, this... show more

slash1s

10,708 subscribers

90,147 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

BREAKING: LLMs just learned to COMPUTE for real, it's mean NO MORE GUESSING math. Chinese college kid Guo Hanjiang vibe-coded MiroFish in 10 days (23k+ GitHub stars, $4.1M from Shanda in 24h) - the AI swarm simulator that’s already printing. ByteDance (VolcEngine) dropped the nuclear upgrade: OpenViking - structured viking:// filesystem memory (L0 ultra-summary -> L2 full details) - agents now run 100+ steps with zero amnesia or hallucinations, 11.6k stars and climbing. Now this just dropped and the entire AI timeline is shaking. Startup Percepta embedded a full WASM virtual machine directly into Transformer weights. No more external Python sandboxes. No more hallucinations in exact tasks. The model streams raw machine code at 30,000+ tokens/sec on CPU, executes millions of steps, and solves the world’s hardest Sudoku via real backtracking + constraint propagation - 100% accurate, zero bullshit. They killed the Attention Bottleneck with Exponentially Fast Attention (HullKVCache + 2D heads + convex hull queries in log time). What used to die at 1k steps now flies. This is the bridge: System 1 intuition (normal LLMs) + System 2 deterministic logic (native code execution) in ONE brain. Agents won’t need tools anymore. Heavy simulations will run inside the weights. Check out: Now put it all together: MiroFish swarms + OpenViking infinite memory + Percepta native flawless compute = agents that can hardcore simulate millions of future scenarios, run perfect logic loops for days, and predict events/markets/reality with god-tier accuracy. No drift. No bullshit. Just pure foresight. This combo will change everything, imo. The era of predictive super-agents that actually print the future is here. We’re watching this one closely. Save this combo.

BREAKING: LLMs just learned to COMPUTE for real, it's mean NO MORE GUESSING math. Chinese college kid Guo Hanjiang vibe-coded MiroFish in 10 days (23k+ GitHub stars, $4.1M from Shanda in 24h) - the AI swarm simulator that’s already printing. ByteDance (VolcEngine) dropped the nuclear upgrade: OpenViking - structured viking:// filesystem memory (L0 ultra-summary -> L2 full details) - agents now run 100+ steps with zero amnesia or hallucinations, 11.6k stars and climbing. Now this just dropped and the entire AI timeline is shaking. Startup Percepta embedded a full WASM virtual machine directly into Transformer weights. No more external Python sandboxes. No more hallucinations in exact tasks. The model streams raw machine code at 30,000+ tokens/sec on CPU, executes millions of steps, and solves the world’s hardest Sudoku via real backtracking + constraint propagation - 100% accurate, zero bullshit. They killed the Attention Bottleneck with Exponentially Fast Attention (HullKVCache + 2D heads + convex hull queries in log time). What used to die at 1k steps now flies. This is the bridge: System 1 intuition (normal LLMs) + System 2 deterministic logic (native code execution) in ONE brain. Agents won’t need tools anymore. Heavy simulations will run inside the weights. Check out: Now put it all together: MiroFish swarms + OpenViking infinite memory + Percepta native flawless compute = agents that can hardcore simulate millions of future scenarios, run perfect logic loops for days, and predict events/markets/reality with god-tier accuracy. No drift. No bullshit. Just pure foresight. This combo will change everything, imo. The era of predictive super-agents that actually print the future is here. We’re watching this one closely. Save this combo.

slash1s

156,699 次观看 • 6 个月前

While the world doomscrolls 15-second TikToks and loses its attention span.. YOU SHOULD CHECK OUT THIS NEW REPO A Chinese college kid built MiroFish in just 10 days, scored $4M funding and ByteDance just dropped the upgrade that turns it into a prediction monster. Fourth-year student Guo Hanjiang vibe coded MiroFish: thousands of autonomous AI agents simulating entire societies in real time. See the details in the post below. Feed it any news, report, or historical data - watch markets, crowds, and politics react exactly as they would. GitHub went nuclear, he scored $4M funding from Shanda Group, and Polymarket traders are already printing +$120k+ using his SPX and event simulations. But long runs had one fatal flaw: agents got amnesia, hallucinations, and context overload. Classic RAG garbage. Now the same company behind TikTok (via VolcEngine) just open-sourced the fix: OpenViking - already at 11.6k+ stars on GitHub. Repo: It turns chaotic memory into a clean, structured filesystem: -> viking://user/memories/ (your habits + past outcomes) -> viking://agent/skills/ (trading and analysis superpowers) Smart 3-layer hierarchy: .L0 - 100-token ultra-summary .L1 - quick overview .L2 - full details (opened only when needed) Agents browse folders intelligently instead of dumping everything. Result: > No more forgetting crucial facts from the start of a simulation > Way fewer hallucinations > Massive API token savings > Self-updating memory - agents get smarter after every run MiroFish + OpenViking = absolute nuclear edge for Polymarket and event prediction. I will use it for my private bot. Thousands of agents now run with perfect long-term memory, stay sharp for 100+ steps, and deliver hyper-accurate probabilities. This combo is about to change the game for anyone trading predictions. The irony is insane: the company that killed human attention with short videos just gave AI agents eternal, structured, self-evolving memory. Who’s already running this combo on Polymarket? Save this. The real alpha just dropped.

While the world doomscrolls 15-second TikToks and loses its attention span.. YOU SHOULD CHECK OUT THIS NEW REPO A Chinese college kid built MiroFish in just 10 days, scored $4M funding and ByteDance just dropped the upgrade that turns it into a prediction monster. Fourth-year student Guo Hanjiang vibe coded MiroFish: thousands of autonomous AI agents simulating entire societies in real time. See the details in the post below. Feed it any news, report, or historical data - watch markets, crowds, and politics react exactly as they would. GitHub went nuclear, he scored $4M funding from Shanda Group, and Polymarket traders are already printing +$120k+ using his SPX and event simulations. But long runs had one fatal flaw: agents got amnesia, hallucinations, and context overload. Classic RAG garbage. Now the same company behind TikTok (via VolcEngine) just open-sourced the fix: OpenViking - already at 11.6k+ stars on GitHub. Repo: It turns chaotic memory into a clean, structured filesystem: -> viking://user/memories/ (your habits + past outcomes) -> viking://agent/skills/ (trading and analysis superpowers) Smart 3-layer hierarchy: .L0 - 100-token ultra-summary .L1 - quick overview .L2 - full details (opened only when needed) Agents browse folders intelligently instead of dumping everything. Result: > No more forgetting crucial facts from the start of a simulation > Way fewer hallucinations > Massive API token savings > Self-updating memory - agents get smarter after every run MiroFish + OpenViking = absolute nuclear edge for Polymarket and event prediction. I will use it for my private bot. Thousands of agents now run with perfect long-term memory, stay sharp for 100+ steps, and deliver hyper-accurate probabilities. This combo is about to change the game for anyone trading predictions. The irony is insane: the company that killed human attention with short videos just gave AI agents eternal, structured, self-evolving memory. Who’s already running this combo on Polymarket? Save this. The real alpha just dropped.

slash1s

293,591 次观看 • 6 个月前

Everyone’s building more AI agents. Almost nobody is building a way for them to share your memory. MemU just did. Your AI now remembers you across every device and every agent, getting smarter after every conversation instead of starting from zero. This changes how personal AI actually works. 👇

Everyone’s building more AI agents. Almost nobody is building a way for them to share your memory. MemU just did. Your AI now remembers you across every device and every agent, getting smarter after every conversation instead of starting from zero. This changes how personal AI actually works. 👇

Atul Kumar

80,368 次观看 • 2 个月前

reminder that this video is 100% AI and it was way cheaper than any real UGC video out there this is an example from my V3 AI UGC system: > the visuals are now more realistic than ever (notice how the natural physics actually look right now) > it's extremely cheap. literally much cheaper than launching a real UGC program for organic > consistent high-quality voice throughout the entire video > infinite-length videos that stay cost effective no matter how long they run AI UGC can match the same exact realism as a real video if you use the right tools and systems..

reminder that this video is 100% AI and it was way cheaper than any real UGC video out there this is an example from my V3 AI UGC system: > the visuals are now more realistic than ever (notice how the natural physics actually look right now) > it's extremely cheap. literally much cheaper than launching a real UGC program for organic > consistent high-quality voice throughout the entire video > infinite-length videos that stay cost effective no matter how long they run AI UGC can match the same exact realism as a real video if you use the right tools and systems..

Miko

36,141 次观看 • 2 个月前

Just ran a real campaign with Hellyeah X-Ray. The tracking was so clean and accurate that I finally saw exactly which ads were driving real conversions instead of just clicks. Connected GitHub → AI agent wired the conversion tracking → launched ads → and finally got clean, accurate results instead of guessing. This is what proper tracking actually looks like

Just ran a real campaign with Hellyeah X-Ray. The tracking was so clean and accurate that I finally saw exactly which ads were driving real conversions instead of just clicks. Connected GitHub → AI agent wired the conversion tracking → launched ads → and finally got clean, accurate results instead of guessing. This is what proper tracking actually looks like

Shah💤aman

26,413 次观看 • 1 个月前

Just built a bot that first runs hyper-realistic MiroFish swarm simulations on every upcoming Bitcoin and crypto event. And then agent instantly trades the real live markets on Polymarket, already printing $12,000+ per day in testing. Couldn't hold back after diving into MiroFish. Took the new god-tier agent behavior simulator from that Chinese college quant who coded it in 10 days, exploded GitHub to 23k+ stars and bagged $4.1M from Shanda overnight.. Paired it with OpenClaw (24/7 autonomous execution) + Claude Opus 4.6. And in one day built my first version of private Polymarket bot. Now it: -> spawns thousands of agents with real memory and personalities -> runs full GraphRAG swarm simulations modeling exactly how news, ETF flows, macro data, whale activity and sentiment will move Bitcoin price -> simulates thousands of possible futures specifically for Polymarket Bitcoin contracts -> detects where the crowd probability is mispriced on every crypto market and extracts the real edge -> auto-trades the edges instantly through OpenClaw the moment the opportunity appears Testing the bot + MiroFish based simulator live right now. First runs already printing hard. Meanwhile there's a real trader crushing with a similar stack imo, $321k all-time profit and 12k/day, 100% won on Bitcoin markets. Wallet: My own Polymarket profile + full trade logs drop later once I scale it hard. New meta just dropped, don't miss out! Check the guide and all info below.

slash1s

114,880 次观看 • 6 个月前

Sam Altman: "I can kind of automate an entire startup of agents and four of us. Four people and all this compute." This might be the biggest startup opportunity of 2026. He says the startups being created today could be far more valuable than the startups of the past. Why? What took his first YC startup 3 months to build can now be done by a coding agent in minutes. And his advice is simple: "You can now do three months of work in 17 minutes, but you better just go do three months of work." Most founders are still using agents to write code. The next ones will build entire companies around them. But that starts with knowing how to build agents that actually work. Here's your chance to learn and build one today ↓

Sam Altman: "I can kind of automate an entire startup of agents and four of us. Four people and all this compute." This might be the biggest startup opportunity of 2026. He says the startups being created today could be far more valuable than the startups of the past. Why? What took his first YC startup 3 months to build can now be done by a coding agent in minutes. And his advice is simple: "You can now do three months of work in 17 minutes, but you better just go do three months of work." Most founders are still using agents to write code. The next ones will build entire companies around them. But that starts with knowing how to build agents that actually work. Here's your chance to learn and build one today ↓

Rahul

22,194 次观看 • 1 个月前

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

DeepLearning.AI

12,785 次观看 • 7 天前

Hermes AI trading agent + math from this article = $440,000 profit on Polymarket in just 20 days. Zero profile views. This guy made almost $500k and everyone is acting like it’s completely normal. 85% win rate = he’s not guessing the future, he’s farming pure mathematical edge. Wallet of the agent: 850 green trades out of every 1,000. At his size and ROI he makes 11x more on winners than he loses. This is the real secret of any top PnL trader on Polymarket: stop guessing and and just exploit the math. Save this post so you don’t forget to read the article. Or take action right now and copy every trade this agent makes using this TG bot:

cvxv666

59,902 次观看 • 5 个月前

Launching now: a new way to follow the AI industry. Beta starts now for the next month. A joint project between Unaligned (my company) and Levangie Labs (Brayden Levangie company). It reads 50,000 of you, and follows 8,300 AI companies here on X. And pulls out the best and most interesting. All built with the X API. Check it out: And please sign up for its daily newsletter. Yeah, $25 a month is a lot for many of you, but that will defray the costs and let me expand it to do a lot more than just AI. Also, the same AI agent that built the site, and did EVERYTHING you see can build custom reports for you on literally any tech community here on X. It supports OpenClaw, RSS, and Notebook LM too. And I'll add more from your requests. More:

Launching now: a new way to follow the AI industry. Beta starts now for the next month. A joint project between Unaligned (my company) and Levangie Labs (Brayden Levangie company). It reads 50,000 of you, and follows 8,300 AI companies here on X. And pulls out the best and most interesting. All built with the X API. Check it out: And please sign up for its daily newsletter. Yeah, $25 a month is a lot for many of you, but that will defray the costs and let me expand it to do a lot more than just AI. Also, the same AI agent that built the site, and did EVERYTHING you see can build custom reports for you on literally any tech community here on X. It supports OpenClaw, RSS, and Notebook LM too. And I'll add more from your requests. More:

Robert Scoble

148,581 次观看 • 6 个月前

This is one of the most personal things I’ve ever shared. A painful memory from my past… and a moment with God that healed it. If you’ve ever felt rejected, this is for you. Follow me for more inspirational stories like this

This is one of the most personal things I’ve ever shared. A painful memory from my past… and a moment with God that healed it. If you’ve ever felt rejected, this is for you. Follow me for more inspirational stories like this

Steve Shultz

8,112,946 次观看 • 5 个月前

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Kawsar

31,812 次观看 • 7 个月前

Shadow Love🎬 I actually like how this scene treats the divine artifact. It isn’t just some convenient power-up he can use whenever he wants, the power is literally more than his body can handle. To me, that makes the artifact way more interesting, because every time he uses it there’s a genuine chance the power could consume him instead.

Shadow Love🎬 I actually like how this scene treats the divine artifact. It isn’t just some convenient power-up he can use whenever he wants, the power is literally more than his body can handle. To me, that makes the artifact way more interesting, because every time he uses it there’s a genuine chance the power could consume him instead.

11

58,520 次观看 • 17 天前

I think I like this Thresh combo? #2XKO_thresh Good damage and carry while setting up lantern in a way that lets a team mate like Ahri or Senna get a mixup off lantern tag Lots of layers you can go for so this is just an example. Can shorten the combo to build less break

I think I like this Thresh combo? #2XKO_thresh Good damage and carry while setting up lantern in a way that lets a team mate like Ahri or Senna get a mixup off lantern tag Lots of layers you can go for so this is just an example. Can shorten the combo to build less break

SQ

14,903 次观看 • 3 个月前

Anthropic's Claude team just showed how to give your AI agents real memory in under 18 minutes. Free. From the people who built it. You've been building agents that forget everything between sessions. This fixes that tonight. One person + 10 agents with memory + dreaming = a team that runs 24/7, learns from every task, and improves itself overnight. Worth more than any $500 AI agent course. Bookmark it. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Anthropic's Claude team just showed how to give your AI agents real memory in under 18 minutes. Free. From the people who built it. You've been building agents that forget everything between sessions. This fixes that tonight. One person + 10 agents with memory + dreaming = a team that runs 24/7, learns from every task, and improves itself overnight. Worth more than any $500 AI agent course. Bookmark it. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

11,230 次观看 • 4 个月前

Blown away by the outputs from Genie 3. This is a huge moment for world models - we now have real-time, playable simulations that you can generate from a text prompt. I pulled together some of my favorite outputs that showcase how you can interact with the scenes👇

Blown away by the outputs from Genie 3. This is a huge moment for world models - we now have real-time, playable simulations that you can generate from a text prompt. I pulled together some of my favorite outputs that showcase how you can interact with the scenes👇

Justine Moore

75,149 次观看 • 1 年前

$INFERRA Just came across Inferra and this one actually feels really interesting. 9ufM9TJd1UEmi9awnGfxCkCHAgQ3JZ5Sw6YxeSeEASY They're building a decentralized marketplace where AI compute becomes a tradable commodity. Instead of letting GPU power sit idle, providers can list verified compute capacity while users can buy, sell, trade, or redeem it for actual compute access. What caught my attention is that they're approaching compute like a real market, with spot trading, futures, and eventually inference markets. As AI demand keeps exploding, compute is becoming one of the most valuable resources in the industry. Projects focused on making that resource more liquid and accessible make a lot of sense to me. High risk as marketcap is tiny. But definitely an interesting compute bet I aped small. DYOR. RR

$INFERRA Just came across Inferra and this one actually feels really interesting. 9ufM9TJd1UEmi9awnGfxCkCHAgQ3JZ5Sw6YxeSeEASY They're building a decentralized marketplace where AI compute becomes a tradable commodity. Instead of letting GPU power sit idle, providers can list verified compute capacity while users can buy, sell, trade, or redeem it for actual compute access. What caught my attention is that they're approaching compute like a real market, with spot trading, futures, and eventually inference markets. As AI demand keeps exploding, compute is becoming one of the most valuable resources in the industry. Projects focused on making that resource more liquid and accessible make a lot of sense to me. High risk as marketcap is tiny. But definitely an interesting compute bet I aped small. DYOR. RR

Crypto Ideology ✍🏻

14,105 次观看 • 3 个月前

holy sh*t, this is f**king insane. someone finally mapped what actually sits between an llm and a production-grade agent, and it is way more than just a better prompt. [6 layers, 1 complete agent stack] 1. models for reasoning 2. tools + mcp for action 3. memory for continuity 4. orchestration for coordination 5. evals for verification 6. guardrails for control the model is only the starting point. the real system is everything that lets it remember, act, recover, verify and keep working without a human fixing every step. save this before building your next agent.

holy sh*t, this is f**king insane. someone finally mapped what actually sits between an llm and a production-grade agent, and it is way more than just a better prompt. [6 layers, 1 complete agent stack] 1. models for reasoning 2. tools + mcp for action 3. memory for continuity 4. orchestration for coordination 5. evals for verification 6. guardrails for control the model is only the starting point. the real system is everything that lets it remember, act, recover, verify and keep working without a human fixing every step. save this before building your next agent.

Gipp 🦅

18,451 次观看 • 1 个月前

"When social media first started rising, we didn't necessarily realize how much of that was actually just foundational infrastructure for the future of humanity.” Ben Fielding of gensyn on why AI is about to repeat the mistake social media made, and how we can still fix it: "This isn't just a product that you chat with. It's actually new fundamental infrastructure for humanity, and we should build that learning from the lessons from before. If we let a single company build AI, they hold an enormous amount of power in the world." "If you actually distribute that out and provide it in a kind of sovereign way — it's on all of our own devices and we own it — then actually you steer the world in a very different social direction."

"When social media first started rising, we didn't necessarily realize how much of that was actually just foundational infrastructure for the future of humanity.” Ben Fielding of gensyn on why AI is about to repeat the mistake social media made, and how we can still fix it: "This isn't just a product that you chat with. It's actually new fundamental infrastructure for humanity, and we should build that learning from the lessons from before. If we let a single company build AI, they hold an enormous amount of power in the world." "If you actually distribute that out and provide it in a kind of sovereign way — it's on all of our own devices and we own it — then actually you steer the world in a very different social direction."

a16z crypto

79,296 次观看 • 5 个月前

Sam Altman says the AI infrastructure race is not about bigger chatbots. It is about shifting the planet's intellectual output from human brains to AI brains. "If people knew what we could do with compute, they would want way, way more." "The thing I am personally most excited about is to use AI and lots of compute to discover new science." "A recent cool example here is we built the Sora Android app using Codex... in less than a month." "You can imagine that way much further, where entire companies can build their products using lots of compute." Then he gives the scale: "Let's say that an AI company today might be generating something on the order of 10 trillion tokens a day out of frontier models." "We're going to have these models at a company be outputting more tokens per day than all of humanity put together, and then 10 times that, and then 100 times that." The bottleneck is moving from software talent to compute supply, inference speed, product integration, and where all that machine intelligence gets pointed.

Sam Altman says the AI infrastructure race is not about bigger chatbots. It is about shifting the planet's intellectual output from human brains to AI brains. "If people knew what we could do with compute, they would want way, way more." "The thing I am personally most excited about is to use AI and lots of compute to discover new science." "A recent cool example here is we built the Sora Android app using Codex... in less than a month." "You can imagine that way much further, where entire companies can build their products using lots of compute." Then he gives the scale: "Let's say that an AI company today might be generating something on the order of 10 trillion tokens a day out of frontier models." "We're going to have these models at a company be outputting more tokens per day than all of humanity put together, and then 10 times that, and then 100 times that." The bottleneck is moving from software talent to compute supply, inference speed, product integration, and where all that machine intelligence gets pointed.

Karl Mehta

16,619 次观看 • 3 个月前