Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Wall Street's worst nightmare isn't regulation. It's a GitHub repo. Kronos. An AI trained from scratch on 12 billion candles from 45 exchanges, and it reads charts as a native language. The numbers: - 93% better at ranking price forecasts than the best time-series model that exists - Zero-shot... show more

AlphaCartel

4,958 subscribers

127,552 views • 1 month ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Sam Altman, CEO of OpenAI: "GPT 5.6 is 54% more efficient on agentic coding, and it's still the best on the market for half the cost." AI spend has never mattered as much as it does today. As a result the models keep getting better and cheaper at the same time. This is going to widen the gap between the people using AI agents and everyone else, because now it's not just powerful, it's cheap. That's exactly why i wrote a full step by step guide on agents, what they are and how to build your own from scratch. Read it below.

Sam Altman, CEO of OpenAI: "GPT 5.6 is 54% more efficient on agentic coding, and it's still the best on the market for half the cost." AI spend has never mattered as much as it does today. As a result the models keep getting better and cheaper at the same time. This is going to widen the gap between the people using AI agents and everyone else, because now it's not just powerful, it's cheap. That's exactly why i wrote a full step by step guide on agents, what they are and how to build your own from scratch. Read it below.

Anatoli Kopadze

91,518 views • 1 month ago

I told Claude to predict the next BTC candle using Kronos. didn't touch anything. +$4,200 overnight. Kronos isn't another LLM wrapper. it's a GPT-style model trained on 12 billion candles from 45 exchanges. Binance, NYSE, NASDAQ, LSE. it reads OHLC the way GPT reads English. > words = candle patterns > sentences = OHLC sequences > the corpus = every trade ever printed > the edge is simple: P(next | history) = softmax(W · h_t) same math GPT uses to predict the next word, except the "word" is the next candle. no twitter sentiment. no blog scraping. no hallucinated confidence. just statistics over 12B real price moves. I plugged Kronos into a 5-min BTC Polymarket bot. input: last 50 candles output: probability next candle closes up trades only when |p_model - p_market| > 0.04 72 hours: $300 → $4,500 ChatGPT looks at a chart and pattern-matches against an article it read. Kronos looks at the chart and remembers 12 billion of them. 87% of Polymarket is exit liquidity. one of these models is actually trading the market. 21.8k stars, free, MIT license. Tsinghua University release.

I told Claude to predict the next BTC candle using Kronos. didn't touch anything. +$4,200 overnight. Kronos isn't another LLM wrapper. it's a GPT-style model trained on 12 billion candles from 45 exchanges. Binance, NYSE, NASDAQ, LSE. it reads OHLC the way GPT reads English. > words = candle patterns > sentences = OHLC sequences > the corpus = every trade ever printed > the edge is simple: P(next | history) = softmax(W · h_t) same math GPT uses to predict the next word, except the "word" is the next candle. no twitter sentiment. no blog scraping. no hallucinated confidence. just statistics over 12B real price moves. I plugged Kronos into a 5-min BTC Polymarket bot. input: last 50 candles output: probability next candle closes up trades only when |p_model - p_market| > 0.04 72 hours: $300 → $4,500 ChatGPT looks at a chart and pattern-matches against an article it read. Kronos looks at the chart and remembers 12 billion of them. 87% of Polymarket is exit liquidity. one of these models is actually trading the market. 21.8k stars, free, MIT license. Tsinghua University release.

RetroChainer

94,059 views • 4 months ago

What the f*ck is this GitHub repo, 33k+ stars in less than a month. It's called OpenHuman, and the newest feature is why it's exploding, Super Context. > The moment you open a new chat, it runs a context pass first > Gathers what's relevant about you, your screen, your work > Then answers turn one like it's turn ten, already grounded It lives at the OS level, speaks in your voice across your whole system, connects to 118 apps you already use. Runs locally, never leaves your machine, and keeps learning you the longer you use it. It was #31 trending on GitHub for ten days straight and now it's the #1 repo on GitHub. > Repo:

What the f*ck is this GitHub repo, 33k+ stars in less than a month. It's called OpenHuman, and the newest feature is why it's exploding, Super Context. > The moment you open a new chat, it runs a context pass first > Gathers what's relevant about you, your screen, your work > Then answers turn one like it's turn ten, already grounded It lives at the OS level, speaks in your voice across your whole system, connects to 118 apps you already use. Runs locally, never leaves your machine, and keeps learning you the longer you use it. It was #31 trending on GitHub for ten days straight and now it's the #1 repo on GitHub. > Repo:

Defileo🔮

206,429 views • 2 months ago

$Big Tech's $1 trillion AI moat just got DESTROYED by a free Chinese download. Microsoft, Amazon, Google, and Meta are pouring fortunes into chips and data centers because they have been told that whoever builds the biggest model wins, and that lead becomes a fortress no one can cross. Last week a lab called Zhipu - it trades in Hong Kong as Knowledge Atlas Technology - released a model called GLM-5.2 and destroyed that idea in a single afternoon. It's open weights under an MIT license, which means anyone on earth can download it and build on it for free. On the coding and design benchmarks that actually matter, it went toe to toe with the best models America has - matching even Anthropic's Mythos-class work and beating OpenAI's flagship outright on the coding test everyone watches. And it does the work at roughly one-sixth the price. ONE-SIXTH And barely a year and a half ago a model called DeepSeek did the same thing and wiped the better part of $600 billion off Nvidia in a single session. This was only the first chapter. You cannot dig a moat around something your competitor is happy to give away. If 95% of frontier capability is free, open, and runs at a fraction of the cost, then the hundreds of billions being spent to defend the last 5% is NOT a moat. And now for the irony: The company that just proved the moat is worthless is itself the single most absurd valuation I have seen in a long career of watching absurd valuations. Zhipu did about $105 million in revenue last year and lost more than 4x what it took in. This week the market handed it a value of roughly $128 billion - at the peak, north of a 1,000x sales - on a float so thin that barely 4% of the stock actually trades. THINK about this... A company drowning in losses, doing 9 figures of revenue, priced like it does hundreds of billions, with almost nothing available to sell. So we now have a bubble in China detonating the entire justification for a bubble in America. Two manias pointed straight at each other. This is the lesson I've spent 45 years trying to beat into people. You can ignore valuation for a long time but you cannot ignore it forever. A moat story sold a trillion dollars of spending, a free download just exposed it, and the company that exposed it is priced for a fantasy of its own. When the picks-and-shovels crowd loses its monopoly on the picks, you want to be very careful what you are paying for the shovels. Numbers don't lie. Shoutout to Limitless - they were onto this story before almost anyone on Wall Street. One of the sharpest AI shows out there.$

Big Tech's $1 trillion AI moat just got DESTROYED by a free Chinese download. Microsoft, Amazon, Google, and Meta are pouring fortunes into chips and data centers because they have been told that whoever builds the biggest model wins, and that lead becomes a fortress no one can cross. Last week a lab called Zhipu - it trades in Hong Kong as Knowledge Atlas Technology - released a model called GLM-5.2 and destroyed that idea in a single afternoon. It's open weights under an MIT license, which means anyone on earth can download it and build on it for free. On the coding and design benchmarks that actually matter, it went toe to toe with the best models America has - matching even Anthropic's Mythos-class work and beating OpenAI's flagship outright on the coding test everyone watches. And it does the work at roughly one-sixth the price. ONE-SIXTH And barely a year and a half ago a model called DeepSeek did the same thing and wiped the better part of $600 billion off Nvidia in a single session. This was only the first chapter. You cannot dig a moat around something your competitor is happy to give away. If 95% of frontier capability is free, open, and runs at a fraction of the cost, then the hundreds of billions being spent to defend the last 5% is NOT a moat. And now for the irony: The company that just proved the moat is worthless is itself the single most absurd valuation I have seen in a long career of watching absurd valuations. Zhipu did about $105 million in revenue last year and lost more than 4x what it took in. This week the market handed it a value of roughly $128 billion - at the peak, north of a 1,000x sales - on a float so thin that barely 4% of the stock actually trades. THINK about this... A company drowning in losses, doing 9 figures of revenue, priced like it does hundreds of billions, with almost nothing available to sell. So we now have a bubble in China detonating the entire justification for a bubble in America. Two manias pointed straight at each other. This is the lesson I've spent 45 years trying to beat into people. You can ignore valuation for a long time but you cannot ignore it forever. A moat story sold a trillion dollars of spending, a free download just exposed it, and the company that exposed it is priced for a fantasy of its own. When the picks-and-shovels crowd loses its monopoly on the picks, you want to be very careful what you are paying for the shovels. Numbers don't lie. Shoutout to Limitless - they were onto this story before almost anyone on Wall Street. One of the sharpest AI shows out there.

George Noble

69,688 views • 2 months ago

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Chaz Wargnier ♨️

565,905 views • 7 months ago

A finance professor manages $200M with AI agents, and he told everyone why: "Large language models are at the level of a fourth-year PhD student in every field" Alejandro Lopez-Lira's AI fund, Autopilot, returned 56% last year. The S&P did 16%. There are 52,000 people with money in it, and most of them just watch the machine work. What he automated is the same six-step loop every fund on earth runs: find an idea, code it, backtest it, deploy it, read the autopsy, learn from it. A quant at Two Sigma runs that loop once a month, and the salary time alone costs around $50,000 per hypothesis. All steps from this loop now fit in AI trading text box. Plain English in, executable strategy out, five-year backtest in 12 seconds, live on a broker 90 seconds after you typed the sentence. He runs $200M with AI. You can run same AI fund in two clicks, free to try: Step 6 on this loop is where everyone is stuck. Your agent has no memory. Every strategy it kills goes into a log nobody reads, and the next one starts from zero. Nobody keeps negative results. Not Citadel, not Man Group, not a single repo on GitHub. Fix that and the agent remembers every hypothesis it killed and the regime it died in. It stops burning cycles on your old mistakes. Jane Street pays 3,500 people to run this cycle and made $39.6 billion doing it. Five sixths of it is now free. Bookmark & read full map of this loop in the article below. Most people still think AI trading is out of reach for them - it isn't. Don't want to spend a dollar for testing this? Kalshi just opened a perps exchange and gives US users $25 free to start ->

A finance professor manages $200M with AI agents, and he told everyone why: "Large language models are at the level of a fourth-year PhD student in every field" Alejandro Lopez-Lira's AI fund, Autopilot, returned 56% last year. The S&P did 16%. There are 52,000 people with money in it, and most of them just watch the machine work. What he automated is the same six-step loop every fund on earth runs: find an idea, code it, backtest it, deploy it, read the autopsy, learn from it. A quant at Two Sigma runs that loop once a month, and the salary time alone costs around $50,000 per hypothesis. All steps from this loop now fit in AI trading text box. Plain English in, executable strategy out, five-year backtest in 12 seconds, live on a broker 90 seconds after you typed the sentence. He runs $200M with AI. You can run same AI fund in two clicks, free to try: Step 6 on this loop is where everyone is stuck. Your agent has no memory. Every strategy it kills goes into a log nobody reads, and the next one starts from zero. Nobody keeps negative results. Not Citadel, not Man Group, not a single repo on GitHub. Fix that and the agent remembers every hypothesis it killed and the regime it died in. It stops burning cycles on your old mistakes. Jane Street pays 3,500 people to run this cycle and made $39.6 billion doing it. Five sixths of it is now free. Bookmark & read full map of this loop in the article below. Most people still think AI trading is out of reach for them - it isn't. Don't want to spend a dollar for testing this? Kalshi just opened a perps exchange and gives US users $25 free to start ->

cvxv666

82,592 views • 26 days ago

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

ANI

163,060 views • 1 month ago

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?

Vikram M

58,688 views • 1 month ago

elon musk grabbed the source code openai open-sourced by accident, rewrote it in rust over a weekend, and shipped it as a free coding agent that does everything $200/mo chatgpt pro does. why pay $200 to openai and $200 to claude when this runs for $8 the swarm above is one weekend of exactly that: thousands of agents pouring through four endpoints, three paid seats billing $1.80 a task while the free fork bills $0. musk co-founded openai, walked out, and when they left codex on github under a permissive license, he forked it, stamped grok on it, and gave it away what the free version does that the $200 seat charges for: the agent · openai's own engine -> it reads your repo, writes patches, runs your tests, and loops until they pass, exactly like codex -> because under the hood it is codex, just faster and free. you are paying $200 for the paid skin of a tool now sitting on github the license · apache-2.0, un-revocable -> free to use, free to fork, free to ship inside your own product with zero strings -> openai cannot pull it back. musk made sure the license is the kind that never expires the switch · one line, no new tools -> point it at any openai-compatible or claude-compatible endpoint, including an $8 kimi backend -> same terminal, same workflow, gpt-5.6 and opus 5 just quietly lose the seat the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the free agent plus an $8 kimi key does the same daily work -> that is a 98% cut, built out of openai's own source code, handed to you by the guy suing them here is the part they will fight me on: openai did not lose this to a better model, they lost it to their own license and an enemy with a weekend free. the $200 was never the tool, it was the toll, and musk just put openai's own logo on the road around it drop your $400/mo ai stack to $8. the run above is openai's own agent, rewritten free, doing the job it bills $200 a month for. the full breakdown is in the article below

starmex

110,709 views • 7 days ago

EVERYONE'S BUYING THE M4 MAC MINI AS A CHEAP DESKTOP. HERE'S WHY IT ENDS UP UNUSED. the pitch is irresistible: a tiny mac that runs cool, quiet, and cheap. then the receipt shows up. the mac mini ships with no screen, no keyboard, no mouse. add a monitor, a decent keyboard and mouse, and more storage, and the "$799 mac" is past $1,000 fast. and macos isn't windows. if your world is gaming, specific windows apps, or the setup you already know, the mini fights you the whole way. that's how so many end up back on a pc, the mini in a drawer. so what is the mac mini actually great at? not being your main desktop. it's the box you never look at. headless in a corner, it's a near-silent always-on server: run local ai models on it, host your automations, keep your files, and reach it from the laptop you already use. it earns its keep by disappearing. the honest turn: the mac mini isn't a cheap desktop. it's a cheap server pretending to be one. buy it for the job it's quietly brilliant at, not the one the ads imply. want a main computer? price the whole setup first. want a silent little box that runs ai and never bothers you? this is the one. no monitor in the box, no keyboard, no "just $599". save this before you buy the sticker price instead of the real one.

EVERYONE'S BUYING THE M4 MAC MINI AS A CHEAP DESKTOP. HERE'S WHY IT ENDS UP UNUSED. the pitch is irresistible: a tiny mac that runs cool, quiet, and cheap. then the receipt shows up. the mac mini ships with no screen, no keyboard, no mouse. add a monitor, a decent keyboard and mouse, and more storage, and the "$799 mac" is past $1,000 fast. and macos isn't windows. if your world is gaming, specific windows apps, or the setup you already know, the mini fights you the whole way. that's how so many end up back on a pc, the mini in a drawer. so what is the mac mini actually great at? not being your main desktop. it's the box you never look at. headless in a corner, it's a near-silent always-on server: run local ai models on it, host your automations, keep your files, and reach it from the laptop you already use. it earns its keep by disappearing. the honest turn: the mac mini isn't a cheap desktop. it's a cheap server pretending to be one. buy it for the job it's quietly brilliant at, not the one the ads imply. want a main computer? price the whole setup first. want a silent little box that runs ai and never bothers you? this is the one. no monitor in the box, no keyboard, no "just $599". save this before you buy the sticker price instead of the real one.

RetroChainer

12,520 views • 1 month ago

Nvidia has just announced Alpamayo 2 Super, an open 34 billion parameter reasoning vision-language-action model designed to accelerate the development of autonomous vehicles. This new model combines the NVIDIA Cosmos 3 Super reasoning model with a 2 billion parameter diffusion-based action expert model, and is post trained with reinforcement learning. The model can return multiple outputs: future trajectory plans, reasoning traces, grounded answers to questions about the scenes, and auto label generation. The model weights are now available for anyone to download on Hugging Face, and the inference code has been posted to GitHub. Distilled models can be deployed commercially without any further permission from Nvidia, and model outputs carry no license conditions. Automakers can distill down a compact version of this model that can run on the Nvidia computer in the car. Major kudos to Nvidia and Jensen Huang for advancing the state of the industry by releasing this as an open model with permissive licensing. Jensen isn't just paying lip service to the idea of open models, Nvidia is actually contributing to the ecosystem — and it's great for their business, because it helps sell more Thor computers that go in the car. Anyone can go download the model and play with it. If you do, let me know what you think. Personally I think it's so cool that we have open weights models that are this advanced, for anyone to download.

Nvidia has just announced Alpamayo 2 Super, an open 34 billion parameter reasoning vision-language-action model designed to accelerate the development of autonomous vehicles. This new model combines the NVIDIA Cosmos 3 Super reasoning model with a 2 billion parameter diffusion-based action expert model, and is post trained with reinforcement learning. The model can return multiple outputs: future trajectory plans, reasoning traces, grounded answers to questions about the scenes, and auto label generation. The model weights are now available for anyone to download on Hugging Face, and the inference code has been posted to GitHub. Distilled models can be deployed commercially without any further permission from Nvidia, and model outputs carry no license conditions. Automakers can distill down a compact version of this model that can run on the Nvidia computer in the car. Major kudos to Nvidia and Jensen Huang for advancing the state of the industry by releasing this as an open model with permissive licensing. Jensen isn't just paying lip service to the idea of open models, Nvidia is actually contributing to the ecosystem — and it's great for their business, because it helps sell more Thor computers that go in the car. Anyone can go download the model and play with it. If you do, let me know what you think. Personally I think it's so cool that we have open weights models that are this advanced, for anyone to download.

Whole Mars Catalog

45,595 views • 29 days ago

Kronos is a foundation model trained on 12B+ candlestick records from 45+ exchanges It takes OHLCV candles in, outputs predicted candles out Temperature sampling lets you generate 50-100 different forecast trajectories per run / Polymarket has 3,455 active crypto markets. $83M+ volume Most resolve on Binance BTC/USDT 1-min candle data, the exact same format Kronos was trained on // The method: > Pull 480 candles from Binance (free via ccxt) > Run Kronos 100 times with temperature sampling > Count how many trajectories cross the strike price > 68 out of 100 cross $75K = your estimate is 68% > Polymarket prices it at 75% > Delta = 7pp → potential edge on No /// Best targets: monthly "hit price" markets "What price will BTC hit in April?" has $13.5M volume Current odds: ↑$75K at 75%, ↑$80K at 18%, ↑$100K at 35% (annual) Runs on a $0.03/hr VPS Kronos-small is 24.7M params, works on CPU. ~15-30 sec per trajectory. 50 trajectories = ~15 min. Free model, free data, no API keys. //// Where to hunt for edge: > Alt-coins (ETH, SOL, XRP) — less efficient pricing > Mid-probability strikes (30-70% range) > Shorter timeframes (5min, 15min, 1h markets) > Less liquid strikes away from round numbers Kronos sees price only. No Fed meetings, no ETF flows, no macro. Use it as one signal, not the only one Also 100 samples ≈ ±9pp confidence interval you just need real edge to overcome noise.

Kronos is a foundation model trained on 12B+ candlestick records from 45+ exchanges It takes OHLCV candles in, outputs predicted candles out Temperature sampling lets you generate 50-100 different forecast trajectories per run / Polymarket has 3,455 active crypto markets. $83M+ volume Most resolve on Binance BTC/USDT 1-min candle data, the exact same format Kronos was trained on // The method: > Pull 480 candles from Binance (free via ccxt) > Run Kronos 100 times with temperature sampling > Count how many trajectories cross the strike price > 68 out of 100 cross $75K = your estimate is 68% > Polymarket prices it at 75% > Delta = 7pp → potential edge on No /// Best targets: monthly "hit price" markets "What price will BTC hit in April?" has $13.5M volume Current odds: ↑$75K at 75%, ↑$80K at 18%, ↑$100K at 35% (annual) Runs on a $0.03/hr VPS Kronos-small is 24.7M params, works on CPU. ~15-30 sec per trajectory. 50 trajectories = ~15 min. Free model, free data, no API keys. //// Where to hunt for edge: > Alt-coins (ETH, SOL, XRP) — less efficient pricing > Mid-probability strikes (30-70% range) > Shorter timeframes (5min, 15min, 1h markets) > Less liquid strikes away from round numbers Kronos sees price only. No Fed meetings, no ETF flows, no macro. Use it as one signal, not the only one Also 100 samples ≈ ±9pp confidence interval you just need real edge to overcome noise.

wincy.eth

25,391 views • 4 months ago

Researchers found a way to make LLMs 8.5x faster! (without compromising accuracy) Speculative decoding is quite an effective way to address the single-token bottleneck in traditional LLM inference. A small "draft" model first generates the next several tokens, then the large model verifies all of them at once in a single forward pass. If a token at any position is wrong, you keep everything before it and restart from there. This never does worse than normal decoding. But current drafters in Speculative decoding still guess one token at a time. That makes the drafting step itself a bottleneck, capping real-world speedups at 2-3x. DFlash is a new technique that swaps the autoregressive drafter with a lightweight block diffusion model that guesses all tokens in one parallel shot. Drafting cost stays flat no matter how many tokens you speculate. On top of that, the drafter is conditioned on hidden features pulled from multiple layers of the target model and injected into every draft layer, so it makes significantly better guesses than a drafter working from scratch. In the side-by-side demo below, vanilla decoding runs at 48.5 tokens/sec. DFlash hits 415 tokens/sec on the same model, with zero quality loss. It's already integrated with vLLM, SGLang, and Transformers, with draft models on HuggingFace for several models like Qwen3, Qwen3.5, Llama 3.1, Kimi-K2.5, gpt-oss, and many more. I have shared the GitHub repo in the replies! KV caching is another must-know technique to boost LLM inference. I recently wrote an article about it. Read it below. 👉 Over to you: What use case are you working on that can benefit from this new technique?

Researchers found a way to make LLMs 8.5x faster! (without compromising accuracy) Speculative decoding is quite an effective way to address the single-token bottleneck in traditional LLM inference. A small "draft" model first generates the next several tokens, then the large model verifies all of them at once in a single forward pass. If a token at any position is wrong, you keep everything before it and restart from there. This never does worse than normal decoding. But current drafters in Speculative decoding still guess one token at a time. That makes the drafting step itself a bottleneck, capping real-world speedups at 2-3x. DFlash is a new technique that swaps the autoregressive drafter with a lightweight block diffusion model that guesses all tokens in one parallel shot. Drafting cost stays flat no matter how many tokens you speculate. On top of that, the drafter is conditioned on hidden features pulled from multiple layers of the target model and injected into every draft layer, so it makes significantly better guesses than a drafter working from scratch. In the side-by-side demo below, vanilla decoding runs at 48.5 tokens/sec. DFlash hits 415 tokens/sec on the same model, with zero quality loss. It's already integrated with vLLM, SGLang, and Transformers, with draft models on HuggingFace for several models like Qwen3, Qwen3.5, Llama 3.1, Kimi-K2.5, gpt-oss, and many more. I have shared the GitHub repo in the replies! KV caching is another must-know technique to boost LLM inference. I recently wrote an article about it. Read it below. 👉 Over to you: What use case are you working on that can benefit from this new technique?

Avi Chawla

157,390 views • 3 months ago

Andrej Karpathy, founding member of OpenAI and ex-Director of AI at Tesla: "creators are paying $5,000 a month to agencies to build the exact AI 'content factory' this free talk hands you in 39 minutes." this free 2025 talk holds the entire "$1M YouTube on autopilot" the 2026 threads sell you for $500. karpathy explains the whole thing on stage: the model is the new computer, your only job is to feed it memory and verify what it gives back. that's the "second brain." that's it. the gurus wrap it in obsidian folders, a /wiki command and a "secret stack." karpathy handed you the actual idea for zero dollars -> dump raw sources in one place, let the model synthesize and maintain an interlinked wiki it can actually use. raw → synthesis → reuse. the architecture's been public the whole time. and here's the part the thread skips. he calls these models "people spirits" -> fallible, confidently wrong, output you check, not trust. the moat was never the obsidian setup. the moat is what you feed it and the judgment to catch where it's lying. the folder structure is free. the taste isn't. bookmark & watch today ↓

Andrej Karpathy, founding member of OpenAI and ex-Director of AI at Tesla: "creators are paying $5,000 a month to agencies to build the exact AI 'content factory' this free talk hands you in 39 minutes." this free 2025 talk holds the entire "$1M YouTube on autopilot" the 2026 threads sell you for $500. karpathy explains the whole thing on stage: the model is the new computer, your only job is to feed it memory and verify what it gives back. that's the "second brain." that's it. the gurus wrap it in obsidian folders, a /wiki command and a "secret stack." karpathy handed you the actual idea for zero dollars -> dump raw sources in one place, let the model synthesize and maintain an interlinked wiki it can actually use. raw → synthesis → reuse. the architecture's been public the whole time. and here's the part the thread skips. he calls these models "people spirits" -> fallible, confidently wrong, output you check, not trust. the moat was never the obsidian setup. the moat is what you feed it and the judgment to catch where it's lying. the folder structure is free. the taste isn't. bookmark & watch today ↓

Ridark

48,183 views • 2 months ago

Former BlackRock fund manager Ed Dowd on the SpaceX IPO "It's overvalued and there's no growth there" "They've changed the rules to get it listed. A lot of people are saying it's unethical" "If you look at the numbers, it's a 15% growth company pricing at 100 times revenues" "It's going to come out at [a] $2 trillion [market cap]... [but it could] easily... [be] a 50% loss [inside of 12 months]" This clip of Dowd (Edward Dowd), a former BlackRock fund manager and co-founder of Phinance Technologies, is taken from an interview with Daniela Cambone-Taub (Daniela Cambone-Taub) posted to the ITM TRADING, INC. YouTube channel on June 5, 2026.

Former BlackRock fund manager Ed Dowd on the SpaceX IPO "It's overvalued and there's no growth there" "They've changed the rules to get it listed. A lot of people are saying it's unethical" "If you look at the numbers, it's a 15% growth company pricing at 100 times revenues" "It's going to come out at [a] $2 trillion [market cap]... [but it could] easily... [be] a 50% loss [inside of 12 months]" This clip of Dowd (Edward Dowd), a former BlackRock fund manager and co-founder of Phinance Technologies, is taken from an interview with Daniela Cambone-Taub (Daniela Cambone-Taub) posted to the ITM TRADING, INC. YouTube channel on June 5, 2026.

Sense Receptor

80,466 views • 2 months ago

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does

plutos

152,392 views • 2 months ago

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Harman

41,278 views • 1 month ago

Watch what Nadella did on the Microsoft earnings call tonight. An analyst asked how Microsoft benefits from enterprises adopting open models when it carries all that frontier lab exposure. Instead of defending the lab relationship, Nadella laid out an architecture: "You've got to keep your harness separate from the model. The harness will ensure that your memory, your context, all of that is external. That means any given model at any given time is swappable." And then the part that should worry anyone underwriting model moats: use frontier models where they earn it, low-cost models where they don't, "and in fact, train your own model when you don't want to use any external model itself because after all, you have all the outputs, you have all the traces, you have all the context." The firm keeps the harness. The models compete for slots inside it. Jensen Huang said most companies will be built on harnesses at the LangChain fireside on July 8. I published the full framework on July 12, five launches in three days, all converging on the same architecture. Tonight the largest enterprise software company on earth made it the official pitch on an earnings call. The moat question in enterprise AI just moved from who has the best weights to who owns the loop around them. And if the completed task is the unit everyone now competes on, someone has to price it for the buyer. That is the next thing we are building at BEP Research: a cost per task tool for enterprises. More on that soon. I also took the paywall off the full framework piece tonight, so the whole thing is free to read:

Watch what Nadella did on the Microsoft earnings call tonight. An analyst asked how Microsoft benefits from enterprises adopting open models when it carries all that frontier lab exposure. Instead of defending the lab relationship, Nadella laid out an architecture: "You've got to keep your harness separate from the model. The harness will ensure that your memory, your context, all of that is external. That means any given model at any given time is swappable." And then the part that should worry anyone underwriting model moats: use frontier models where they earn it, low-cost models where they don't, "and in fact, train your own model when you don't want to use any external model itself because after all, you have all the outputs, you have all the traces, you have all the context." The firm keeps the harness. The models compete for slots inside it. Jensen Huang said most companies will be built on harnesses at the LangChain fireside on July 8. I published the full framework on July 12, five launches in three days, all converging on the same architecture. Tonight the largest enterprise software company on earth made it the official pitch on an earnings call. The moat question in enterprise AI just moved from who has the best weights to who owns the loop around them. And if the completed task is the unit everyone now competes on, someone has to price it for the buyer. That is the next thing we are building at BEP Research: a cost per task tool for enterprises. More on that soon. I also took the paywall off the full framework piece tonight, so the whole thing is free to read:

Ben Pouladian

53,335 views • 1 month ago

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Yarchi

42,733 views • 17 days ago

When I came on board at Hanna Barbera, the priority was THE REAL ADVENTURES JONNY QUEST (1996). The series is credited as one of the first animated television series to use motion capture technology for the CGI sequences in "QuestWorld," the virtual reality environment featured in the show. It was a novel approach at the time for an animated series. Because it was so ambitious, we had two separate teams working to keep up with the schedule. As crude as this might look, it was groundbreaking given the fact that it was done on a TV schedule and budget.

When I came on board at Hanna Barbera, the priority was THE REAL ADVENTURES JONNY QUEST (1996). The series is credited as one of the first animated television series to use motion capture technology for the CGI sequences in "QuestWorld," the virtual reality environment featured in the show. It was a novel approach at the time for an animated series. Because it was so ambitious, we had two separate teams working to keep up with the schedule. As crude as this might look, it was groundbreaking given the fact that it was done on a TV schedule and budget.

Brian A. Miller

16,168 views • 1 year ago