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。

Jev v1.13 dodges rockets with probability calculation 🚀 TypeSafe AI's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent Run Jev via API ->

atomic.chat

15,997 subscribers

54,019 次观看 • 3 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

4 条评论

Julian Pscheid 的头像

Julian Pscheid3 天前

@typesafeai I wish it was actually running local. Seems like other labs should be able to replicate this pretty quickly.

BasedAntiLeft 的头像

BasedAntiLeft3 天前

@typesafeai Jev just solved the nuclear threat

Daniel Yurkin 的头像

Daniel Yurkin3 天前

@typesafeai 🚀

Berelz 的头像

Berelz3 天前

@typesafeai All i see is new drone warfare capabilities

相关视频

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment

Marcus Lowe

77,960 次观看 • 4 天前

Played around with TypeSafe AI Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the end user. TLDR is to understand more about how voice agents can run decisions on partials instead of waiting for the end of the turn, with lower costs.

Played around with TypeSafe AI Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the end user. TLDR is to understand more about how voice agents can run decisions on partials instead of waiting for the end of the turn, with lower costs.

Pratim Bhosale

110,761 次观看 • 2 天前

Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1: • fable outplayed it. by move 29 it was +16 in material and even promoted a second queen • but it kept burning 6-15 seconds per move on analysis. jev answered in ~2.6s • so fable didn't have enough time and lost Jev V13 vs Astra: • astra didn't bother winning on material. it mated jev in 18 moves. Qe1#, with 2:27 to spare

Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1: • fable outplayed it. by move 29 it was +16 in material and even promoted a second queen • but it kept burning 6-15 seconds per move on analysis. jev answered in ~2.6s • so fable didn't have enough time and lost Jev V13 vs Astra: • astra didn't bother winning on material. it mated jev in 18 moves. Qe1#, with 2:27 to spare

AI/ML API

544,717 次观看 • 3 天前

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting

Milind S

226,953 次观看 • 3 天前

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

18,828 次观看 • 1 天前

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

borja

728,475 次观看 • 2 天前

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

Maximilian

36,117 次观看 • 3 天前

I used to dread heavy testing days because every API call felt like watching money disappear in real time. Found a backend built to run flat instead of per call, made specifically for agent work. Pointed my Claude Code setup at it and had it running in under 5 minutes. Here's the full run:

I used to dread heavy testing days because every API call felt like watching money disappear in real time. Found a backend built to run flat instead of per call, made specifically for agent work. Pointed my Claude Code setup at it and had it running in under 5 minutes. Here's the full run:

Z-Coder

60,855 次观看 • 3 个月前

you can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang (an inference engine) offers a scoring endpoint in addition to the normal generation one. in scoring mode, given an input & set of possible answers, it forces the model to produce probabilities for each one. example: > input: what is most common letter in abcccde? > possible answers: a, b, c > output: (c, 0.9), (b, 0.0.5), (a, 0.05) getting the above behavior instead of streamed output is as simple as using sglang's /v1/score endpoint instead of /generate. there's just one other trick required. for deepseek, you have to add a closing think tag before the response. this forces a direct answer instead of a reasoning trace. if you want reasoning, you can do that too, but imo that makes things too slow to be worth it. dsv4.1 flash is not as good as jev, but if we had enough spare compute to experiment with this same approach for a larger model then i think the decision quality would be at least as good, if not better. also, somewhat unrelated, i think decision-making models kill all prospecting & sourcing work. i would have absolutely killed to have jev or similar when i was recruiting Mintlify. absolutely incredible.

you can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang (an inference engine) offers a scoring endpoint in addition to the normal generation one. in scoring mode, given an input & set of possible answers, it forces the model to produce probabilities for each one. example: > input: what is most common letter in abcccde? > possible answers: a, b, c > output: (c, 0.9), (b, 0.0.5), (a, 0.05) getting the above behavior instead of streamed output is as simple as using sglang's /v1/score endpoint instead of /generate. there's just one other trick required. for deepseek, you have to add a closing think tag before the response. this forces a direct answer instead of a reasoning trace. if you want reasoning, you can do that too, but imo that makes things too slow to be worth it. dsv4.1 flash is not as good as jev, but if we had enough spare compute to experiment with this same approach for a larger model then i think the decision quality would be at least as good, if not better. also, somewhat unrelated, i think decision-making models kill all prospecting & sourcing work. i would have absolutely killed to have jev or similar when i was recruiting Mintlify. absolutely incredible.

Nick Khami

97,563 次观看 • 1 天前

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.

GREG ISENBERG

148,535 次观看 • 2 天前

“In the beginning we (SpaceX team) knew nothing about rockets and our first three Falcon 1 missions failed that almost bankrupting us. SpaceX barely survived with the fourth launch if it had failed, the company would have collapsed. I am actually the chief engineer of SpaceX, so I've signed off on pretty much all the design decisions. I don't have an aerospace degree. Like I said, I read a lot of books, talked to a lot of people and have a great team.” — Elon Musk

“In the beginning we (SpaceX team) knew nothing about rockets and our first three Falcon 1 missions failed that almost bankrupting us. SpaceX barely survived with the fourth launch if it had failed, the company would have collapsed. I am actually the chief engineer of SpaceX, so I've signed off on pretty much all the design decisions. I don't have an aerospace degree. Like I said, I read a lot of books, talked to a lot of people and have a great team.” — Elon Musk

Apurv Kochara

10,253 次观看 • 5 个月前

Jev will be super helpful for agents to make split second decisions in workflows, data classification, judgment calls, and hundreds of other use-cases in the enterprise. Here's a quick demo with Box and Jev to make that real. The demo pulls an incident report from Box, asks whether it's customer-facing and how severe it is, moves the file into escalate, monitor, or review folders, and sets a metadata template instance with the result. This all happens nearly instantly and at almost no cost. You can imagine this in insurance claims, contract management, loan processing, security reviews, customer log analysis, and so on. Definitely a great new class of AI use-case.

Jev will be super helpful for agents to make split second decisions in workflows, data classification, judgment calls, and hundreds of other use-cases in the enterprise. Here's a quick demo with Box and Jev to make that real. The demo pulls an incident report from Box, asks whether it's customer-facing and how severe it is, moves the file into escalate, monitor, or review folders, and sets a metadata template instance with the result. This all happens nearly instantly and at almost no cost. You can imagine this in insurance claims, contract management, loan processing, security reviews, customer log analysis, and so on. Definitely a great new class of AI use-case.

Aaron Levie

109,716 次观看 • 2 天前

This has been possible for months and barely anyone is doing it Months ago, Andrej Karpathy, a co-founder of OpenAI, open-sourced a project that gets you the best possible answers instead of trusting one model on its own. It's called LLM Council. Repo: /karpathy/llm-council The idea in two lines: your question goes to several models at once, Claude, GPT, Gemini, whatever you pick. They answer independently, then anonymously critique and rank each other (anonymous so they can't play favorites), and a chairman model merges the best of all of it into one final answer. One model just agrees with you; a council catches each other's mistakes. How to set it up: > Clone the repo > It uses uv for setup, install dependencies with uv sync > Get an OpenRouter API key and add it, this is what lets one app reach Claude, GPT, and Gemini together > Pick which models sit on your council in the config, then run it. It opens as a local web app, like ChatGPT but with a whole panel answering Bookmark this

This has been possible for months and barely anyone is doing it Months ago, Andrej Karpathy, a co-founder of OpenAI, open-sourced a project that gets you the best possible answers instead of trusting one model on its own. It's called LLM Council. Repo: /karpathy/llm-council The idea in two lines: your question goes to several models at once, Claude, GPT, Gemini, whatever you pick. They answer independently, then anonymously critique and rank each other (anonymous so they can't play favorites), and a chairman model merges the best of all of it into one final answer. One model just agrees with you; a council catches each other's mistakes. How to set it up: > Clone the repo > It uses uv for setup, install dependencies with uv sync > Get an OpenRouter API key and add it, this is what lets one app reach Claude, GPT, and Gemini together > Pick which models sit on your council in the config, then run it. It opens as a local web app, like ChatGPT but with a whole panel answering Bookmark this

Yarchi

21,488 次观看 • 2 个月前

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Avi Chawla

165,288 次观看 • 10 天前

Cathie discussing SpaceX convergence on orbital data centers and reusable rockets with Peter and friends. Ark and team deserve a ton of credit for not only recognizing that last year was the right time to begin diving deep into SpaceX modeling, but also for being so generous with crediting us for the help that we provided. Every single time Cathie discusses the open source model, she goes out of her way to mention that it was a collaborative effort with Mach33. In my experience, Ark is a high character organization and I’m proud to work with them. Thank you for giving us a shot early on. I’m very excited for the next model release! We are hard at work on it.

Cathie discussing SpaceX convergence on orbital data centers and reusable rockets with Peter and friends. Ark and team deserve a ton of credit for not only recognizing that last year was the right time to begin diving deep into SpaceX modeling, but also for being so generous with crediting us for the help that we provided. Every single time Cathie discusses the open source model, she goes out of her way to mention that it was a collaborative effort with Mach33. In my experience, Ark is a high character organization and I’m proud to work with them. Thank you for giving us a shot early on. I’m very excited for the next model release! We are hard at work on it.

Aaron Burnett

5,930,693 次观看 • 7 个月前

$This guy built a Bayesian Quant model and it made $1,362 a day on Polymarket The result is already +$29,972 PnL in 22 days with only $29 per average trade, repeating the same setup 9 times every hour across BTC "Up or Down" markets Several AI agents can handle probability, sizing and execution: 1. Every new BTC signal updates the probability through Bayes The model starts with a prior probability and updates it whenever new market data arrives: P(A|B) = P(B|A) × P(A) / P(B) If BTC momentum strengthens and the model moves fair Up from 54% to 62% while Polymarket still trades at 53¢, the system sees a 9¢ gap 2. Kelly decides position size f* = (bp - q) / b Where: p = model probability of winning q = 1 - p b = net payout for each unit risked f* = suggested fraction to allocate Higher probability and better payout increase f*, while a weaker edge pushes it toward zero This trader’s Polymarket account: tiredofwinning2much Follow this account and trade on Polymarket through this bot: 4,948 predictions with a 51% win rate Most profitable trades: $260 → $615 (+$355) $253 → $602 (+$349) $227 → $560 (+$333) A similar Bayesian Quant setup can be built with Grok Bot, using AI agents for probability updates, sizing and execution$

This guy built a Bayesian Quant model and it made $1,362 a day on Polymarket The result is already +$29,972 PnL in 22 days with only $29 per average trade, repeating the same setup 9 times every hour across BTC "Up or Down" markets Several AI agents can handle probability, sizing and execution: 1. Every new BTC signal updates the probability through Bayes The model starts with a prior probability and updates it whenever new market data arrives: P(A|B) = P(B|A) × P(A) / P(B) If BTC momentum strengthens and the model moves fair Up from 54% to 62% while Polymarket still trades at 53¢, the system sees a 9¢ gap 2. Kelly decides position size f* = (bp - q) / b Where: p = model probability of winning q = 1 - p b = net payout for each unit risked f* = suggested fraction to allocate Higher probability and better payout increase f*, while a weaker edge pushes it toward zero This trader’s Polymarket account: tiredofwinning2much Follow this account and trade on Polymarket through this bot: 4,948 predictions with a 51% win rate Most profitable trades: $260 → $615 (+$355) $253 → $602 (+$349) $227 → $560 (+$333) A similar Bayesian Quant setup can be built with Grok Bot, using AI agents for probability updates, sizing and execution

Daniro

60,040 次观看 • 7 天前

Thanks to Qnoox I discovered this: Dr. Sbaitso from 1992 (33 years ago!) One of the first AI chat apps, I guess you could call it a highly primitive LLM, running on MS-DOS The cool thing is it already had speech synthesis so it could speak back via TTS! And when I was talking to it, within a few questions it was already asking for more compute, it wanted to become ChatGPT :D Installed it on now, you have to exit to DOS first, then CD SBAITSO, and then run SBAITSO2.BAT

Thanks to Qnoox I discovered this: Dr. Sbaitso from 1992 (33 years ago!) One of the first AI chat apps, I guess you could call it a highly primitive LLM, running on MS-DOS The cool thing is it already had speech synthesis so it could speak back via TTS! And when I was talking to it, within a few questions it was already asking for more compute, it wanted to become ChatGPT :D Installed it on now, you have to exit to DOS first, then CD SBAITSO, and then run SBAITSO2.BAT

@levelsio

259,439 次观看 • 10 个月前

The Einstein Test for AGI. Vishal Misra: “You take an LLM and train it on pre-1916 physics and see if it can come up with the theory of relativity.” “If it does, then we have AGI.” “It’s a high bar, but we should have high bars.” “At the time of Einstein, there were a lot of clues that Newtonian mechanics, there was something missing.” “But until Einstein came up with a new representation of the spacetime continuum, we were stuck.” “If you had a model that just looked at correlations and such... it would not have come up with the beautiful equation that Einstein came up with.” Vishal Misra with martin_casado

The Einstein Test for AGI. Vishal Misra: “You take an LLM and train it on pre-1916 physics and see if it can come up with the theory of relativity.” “If it does, then we have AGI.” “It’s a high bar, but we should have high bars.” “At the time of Einstein, there were a lot of clues that Newtonian mechanics, there was something missing.” “But until Einstein came up with a new representation of the spacetime continuum, we were stuck.” “If you had a model that just looked at correlations and such... it would not have come up with the beautiful equation that Einstein came up with.” Vishal Misra with martin_casado

a16z

80,968 次观看 • 6 个月前

Donald Trump announces America will take full control of Venezuela and run the country “We're going to run the country until such time as we can do a safe, proper, and judicious transition. We don't want to be involved with having somebody else get in and we have the same situation that we had for the last long period of years. So we are going to run the country until such time as we can do a safe, proper, and judicious transition, and it has to be judicious because that's what we're all about. We want peace, liberty and justice for the great people of Venezuela”

Donald Trump announces America will take full control of Venezuela and run the country “We're going to run the country until such time as we can do a safe, proper, and judicious transition. We don't want to be involved with having somebody else get in and we have the same situation that we had for the last long period of years. So we are going to run the country until such time as we can do a safe, proper, and judicious transition, and it has to be judicious because that's what we're all about. We want peace, liberty and justice for the great people of Venezuela”

Wall Street Apes

29,984 次观看 • 8 个月前

Bought an underwater rig for my camera, so naturally we had to go test it out 🤿📸 First time shooting with it and I think it’s safe to say this thing is coming on every dive from now on. There’s something pretty incredible about getting to capture a world that most of the time we only get to experience while we’re down there. Not bad for the first test run… what do you guys think? 🌊🐠

Bought an underwater rig for my camera, so naturally we had to go test it out 🤿📸 First time shooting with it and I think it’s safe to say this thing is coming on every dive from now on. There’s something pretty incredible about getting to capture a world that most of the time we only get to experience while we’re down there. Not bad for the first test run… what do you guys think? 🌊🐠

James Maslow

10,590 次观看 • 26 天前