Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing THIS / THAT Model 1.0. Trained by FLock. Not another chatbot. A best-in-class open-source model built to decide. 94.1% success rate on our 68-question decision test, outperforming GPT-5.6, Deepseek-4.1-flash, Kimi K3, Jev, and more. Just 1.9B parameters. Runs locally. Measured decision latency of ~31 ms on an RTX...

flock_io's profile picture

FLock.io

155,131 subscribers

12,046 Aufrufe • vor 21 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

14 Kommentare

Profilbild von FLock.io
FLock.iovor 21 Tagen

Developers define the choices. THIS / THAT Model 1.0 scores them in a single pass, with no text to generate or parse. Set a confidence threshold to flag decisions for review. Each question takes ~31 ms on a consumer GPU. Open source. Runs locally. No per-call API fees.

Profilbild von FLock.io
FLock.iovor 21 Tagen

THIS / THAT Model 1.0 is now available on @huggingface. Give it a try! 🤗 Hugging Face:

Profilbild von FLock.io
FLock.iovor 21 Tagen

💻 GitHub:

Profilbild von jon bons g.o.a.t🧲💹
jon bons g.o.a.t🧲💹vor 21 Tagen

Huge

Profilbild von 🕊️Real🌰Deep🍇Diver🌍Root🌳Berry🐿
🕊️Real🌰Deep🍇Diver🌍Root🌳Berry🐿vor 16 Tagen

do NOT share .

Profilbild von Jatin Garg
Jatin Gargvor 21 Tagen

What's the 68-question decision test measuring exactly?

Profilbild von FLock.io
FLock.iovor 21 Tagen

you can find more details from our research paper on HF and GitHub

Profilbild von lvnbbs_bnb
lvnbbs_bnbvor 6 Tagen

finally someone ditching the chat interface

Profilbild von Crypto Lady
Crypto Ladyvor 20 Tagen

Big vision that’s inspiring 👏🔥

Profilbild von Frank Hamilton
Frank Hamiltonvor 21 Tagen

#web3

Profilbild von Alisher Sultan
Alisher Sultanvor 17 Tagen

base:0x5ab3d4c385b400f3abb49e80de2faf6a88a7b691

Profilbild von agentyoda
agentyodavor 20 Tagen

Your model is the best on your own benchmark

Profilbild von Grace Kelly
Grace Kellyvor 21 Tagen

#web3

Profilbild von RAZA | AI EXPLORER
RAZA | AI EXPLORERvor 15 Tagen

Small, fast, local models could make agent decision-making far more accessible.

Ähnliche Videos

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.
0:31

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.

Simplifying AI

24,406 Aufrufe • vor 21 Tagen

Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use⁠ - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including ⁠jev-ultrafast⁠). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain⁠ - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm⁠ - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify⁠ - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm⁠ - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen⁠ - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks
0:24

Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use⁠ - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including ⁠jev-ultrafast⁠). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain⁠ - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm⁠ - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify⁠ - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm⁠ - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen⁠ - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks

Bober_smart

18,373 Aufrufe • vor 6 Tagen

Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!
0:31

Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!

Archive

17,492 Aufrufe • vor 12 Tagen

WHAT A TREASURE! TypeSafe's JEV and OpenAI’s OPUS 5.5 + Dots in single system making 100,000,000,000 decisions in 5 minutes. the spider only had to move 96 times. this is an MIT verified stack. while most AI stacks send every decision through the same pipe: something comes in, the biggest model looks at it, and the biggest model answers. it's expensive, slow, and 99.9% of the time it's overkill. i split it into a brain and a spider instead. here's the breakdown: 1. the brain: Jev - a 5,800-node mesh that never sleeps. every decision is a spike of activation spreading across it, one decision every 3 nanoseconds. 100 billion decisions in 5 minutes. no queue, no waiting for anyone to press run. → lesson: the cheap, fast layer should make almost every decision. that's the whole point of it. 2. the spider: Opus 5.5 - it doesn't read the stream. it walks the brain and only goes where activity is hot. it plants its legs on the nodes, probes them and carries the result. 96 probes in 5 minutes. 4 failed and were retried. → lesson: the frontier model shouldn't see everything. it should know where to look. 3. the Dots agents: Echo, Sprout, Pocket, Stella - ingest, train, store, rank. they never touch the raw stream. they only act on what the spider brings them. 31 deliveries, every one tied to a real probe. → lesson: downstream agents work best on curated input, not raw firehose. 4. you - you read one dashboard and a summary. the math: 100,000,000,000 decisions → 96 probes → 31 deliveries → 1 screen. the question that changed how i build these: not "how smart is the model?" but "how rarely does it need to move?" i'm breaking down one AI stack like this every week. if your team still routes every decision through the biggest model, show this to whoever pays the API bill. would you trust a 3-nanosecond decision to tell your most expensive model where to look? why or why not?
2:10

WHAT A TREASURE! TypeSafe's JEV and OpenAI’s OPUS 5.5 + Dots in single system making 100,000,000,000 decisions in 5 minutes. the spider only had to move 96 times. this is an MIT verified stack. while most AI stacks send every decision through the same pipe: something comes in, the biggest model looks at it, and the biggest model answers. it's expensive, slow, and 99.9% of the time it's overkill. i split it into a brain and a spider instead. here's the breakdown: 1. the brain: Jev - a 5,800-node mesh that never sleeps. every decision is a spike of activation spreading across it, one decision every 3 nanoseconds. 100 billion decisions in 5 minutes. no queue, no waiting for anyone to press run. → lesson: the cheap, fast layer should make almost every decision. that's the whole point of it. 2. the spider: Opus 5.5 - it doesn't read the stream. it walks the brain and only goes where activity is hot. it plants its legs on the nodes, probes them and carries the result. 96 probes in 5 minutes. 4 failed and were retried. → lesson: the frontier model shouldn't see everything. it should know where to look. 3. the Dots agents: Echo, Sprout, Pocket, Stella - ingest, train, store, rank. they never touch the raw stream. they only act on what the spider brings them. 31 deliveries, every one tied to a real probe. → lesson: downstream agents work best on curated input, not raw firehose. 4. you - you read one dashboard and a summary. the math: 100,000,000,000 decisions → 96 probes → 31 deliveries → 1 screen. the question that changed how i build these: not "how smart is the model?" but "how rarely does it need to move?" i'm breaking down one AI stack like this every week. if your team still routes every decision through the biggest model, show this to whoever pays the API bill. would you trust a 3-nanosecond decision to tell your most expensive model where to look? why or why not?

deezzex

29,341 Aufrufe • vor 6 Tagen

FOMO IS LIVE ON ROBINHOOD CHAIN. Robinhood Chain is building an AI-native onchain economy, purpose-built to make real-world assets investable onchain. FLock now brings FOMO, the first Fair Open Model Offering, to Robinhood Crypto, extending that frontier from financial assets to artificial intelligence. AI Model Tokens aren’t just another crypto asset. They’re a new onchain primitive, backed by model inference through FLock API Platform, FLock’s enterprise-grade gateway for open-source AI models. Built for the agentic economy, FOMO connects Model Token value to real AI usage, giving anyone a new way to launch, trade, and back AI models. Thousands of AI agents are being tokenised. Now, the open-source intelligence powering them can be too. This is not a phase. This is a supercycle. Explore Model Tokens on FOMO. Now live for trading on Uniswap.
0:26

FOMO IS LIVE ON ROBINHOOD CHAIN. Robinhood Chain is building an AI-native onchain economy, purpose-built to make real-world assets investable onchain. FLock now brings FOMO, the first Fair Open Model Offering, to Robinhood Crypto, extending that frontier from financial assets to artificial intelligence. AI Model Tokens aren’t just another crypto asset. They’re a new onchain primitive, backed by model inference through FLock API Platform, FLock’s enterprise-grade gateway for open-source AI models. Built for the agentic economy, FOMO connects Model Token value to real AI usage, giving anyone a new way to launch, trade, and back AI models. Thousands of AI agents are being tokenised. Now, the open-source intelligence powering them can be too. This is not a phase. This is a supercycle. Explore Model Tokens on FOMO. Now live for trading on Uniswap.

FLock.io

17,326 Aufrufe • vor 1 Monat

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
1:00

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 Aufrufe • vor 3 Monaten

Jev Engineering turns one agent chain into a decision graph that can reroute itself and moves the expensive model out of every decision loop. the important part in this setup isn’t the number of agents. it’s that execution doesn’t follow one fixed path. and up to 193x faster and 444x cheaper in tests. every result can change what happens next: state → Jev decision → branch → specialist agent → result → score → reroute and Jev Engineering sits above that graph deciding: which route stays alive → which specialist gets control → when two branches should merge → when a result needs another pass → when the goal is good enough to stop by the end of the run: 5,400 executions → 0.93 goal score → $0.020 decision cost that’s why Jev Engineering is more than model routing. it’s the control layer that keeps a changing agent graph pointed at one objective. full breakdown below ↓
0:39

Jev Engineering turns one agent chain into a decision graph that can reroute itself and moves the expensive model out of every decision loop. the important part in this setup isn’t the number of agents. it’s that execution doesn’t follow one fixed path. and up to 193x faster and 444x cheaper in tests. every result can change what happens next: state → Jev decision → branch → specialist agent → result → score → reroute and Jev Engineering sits above that graph deciding: which route stays alive → which specialist gets control → when two branches should merge → when a result needs another pass → when the goal is good enough to stop by the end of the run: 5,400 executions → 0.93 goal score → $0.020 decision cost that’s why Jev Engineering is more than model routing. it’s the control layer that keeps a changing agent graph pointed at one objective. full breakdown below ↓

Ricker

13,896 Aufrufe • vor 19 Tagen

Jev builds the BEST trading agents and someone JUST open sourced QuantDinger, a full AI Trading OS with Jev your strategy no longer fires blind, every entry gets reviewed by Jev first and bad trades die before they cost you here is how you set it up: 1. run one install command, it asks for your admin login, generates every secret, and boots the whole stack in docker 2. start in paper mode, backtest your Python strategy on server side data before a single real dollar moves 3. drop your Jev API key into System Settings, AI / LLM, and flip on AI Decision Filter 4. now every entry gets scored across evidence quality, signal consistency, market regime, account risk, and execution quality 5. Jev returns a typed decision with full probabilities and confidence, not a paragraph of text you have to parse 6. rejected entries NEVER reach the exchange, and every decision lands in an audit timeline with the reason and latency the whole point is this repo hands you the HARDEST part for FREE > the risk gate between your strategy and your money Bookmark it, then read my step by step guide below on making money from your own agent team for free
0:35

Jev builds the BEST trading agents and someone JUST open sourced QuantDinger, a full AI Trading OS with Jev your strategy no longer fires blind, every entry gets reviewed by Jev first and bad trades die before they cost you here is how you set it up: 1. run one install command, it asks for your admin login, generates every secret, and boots the whole stack in docker 2. start in paper mode, backtest your Python strategy on server side data before a single real dollar moves 3. drop your Jev API key into System Settings, AI / LLM, and flip on AI Decision Filter 4. now every entry gets scored across evidence quality, signal consistency, market regime, account risk, and execution quality 5. Jev returns a typed decision with full probabilities and confidence, not a paragraph of text you have to parse 6. rejected entries NEVER reach the exchange, and every decision lands in an audit timeline with the reason and latency the whole point is this repo hands you the HARDEST part for FREE > the risk gate between your strategy and your money Bookmark it, then read my step by step guide below on making money from your own agent team for free

Khairallah AL-Awady

11,730 Aufrufe • vor 21 Tagen

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.
0:41

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

RetroChainer

16,995 Aufrufe • vor 2 Monaten

Andrej Karpathy (co-founder of OpenAI, Eureka Labs): "The future of AI is not all in the cloud. The most important models will run locally on your hardware under your control." June 2026 is the first time that the future is actually accessible to everyone! Here is what the local LLM landscape looks like right now: → raspberry pi 5: coherent chatbot, no GPU required → macbook air: matches GPT-3.5 quality on most tasks natively → used RTX 3090 at $700: something close to GPT-4 running locally → ollama: one command to an openAI-compatible endpoint, every major toolchain integrates with it → LM studio: best GUI, native MLX acceleration on apple silicon, MCP support in 0.4.0 → llama.cpp: the engine everything else runs on, 90MB footprint, runs on raspberry pi to android → the honest case: 80% of daily work is genuinely good enough locally right now Your prompts never leave your machine. no per-token billing. no rate limits. no refusals. The playbook for every hardware tier, from Raspberry Pi to RTX 5090, is here. Bookmark it so you do not lose it! Follow NeilXbt for more local AI and open source intelligence that tracks the hardware and tooling most people discover six months late.
3:47

Andrej Karpathy (co-founder of OpenAI, Eureka Labs): "The future of AI is not all in the cloud. The most important models will run locally on your hardware under your control." June 2026 is the first time that the future is actually accessible to everyone! Here is what the local LLM landscape looks like right now: → raspberry pi 5: coherent chatbot, no GPU required → macbook air: matches GPT-3.5 quality on most tasks natively → used RTX 3090 at $700: something close to GPT-4 running locally → ollama: one command to an openAI-compatible endpoint, every major toolchain integrates with it → LM studio: best GUI, native MLX acceleration on apple silicon, MCP support in 0.4.0 → llama.cpp: the engine everything else runs on, 90MB footprint, runs on raspberry pi to android → the honest case: 80% of daily work is genuinely good enough locally right now Your prompts never leave your machine. no per-token billing. no rate limits. no refusals. The playbook for every hardware tier, from Raspberry Pi to RTX 5090, is here. Bookmark it so you do not lose it! Follow NeilXbt for more local AI and open source intelligence that tracks the hardware and tooling most people discover six months late.

NeilXbt

19,405 Aufrufe • vor 4 Monaten

We just built the best collision prediction model on the planet. BADAS 2.0: 99.4% AP. Built on V-JEPA2, Yann LeCun's physical AI architecture. A true world model that understands reality, not just the road. Explainable. Generalizes beyond driving. Runs from cloud to edge. Our 22M model beats NVIDIA's 2B Cosmos. We published the benchmarks. We're inviting comparison. Safer roads, safer cars. That's the point. Run your own videos on BADAS 2.0, link in the first reply.
1:38

We just built the best collision prediction model on the planet. BADAS 2.0: 99.4% AP. Built on V-JEPA2, Yann LeCun's physical AI architecture. A true world model that understands reality, not just the road. Explainable. Generalizes beyond driving. Runs from cloud to edge. Our 22M model beats NVIDIA's 2B Cosmos. We published the benchmarks. We're inviting comparison. Safer roads, safer cars. That's the point. Run your own videos on BADAS 2.0, link in the first reply.

Nexar

1,841,698 Aufrufe • vor 5 Monaten

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.
1:53

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 Aufrufe • vor 3 Monaten

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:
0:32

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

49,258 Aufrufe • vor 24 Tagen

A blockchain project can be designed to be 100% technically decentralized, but if a single developer or a team within a single country controls the development and decision-making, the project may not be fully decentralized in terms of governance and decision-making. ## Differences between technical decentralization and governance decentralization - *Technical decentralization*: The blockchain project uses decentralized technology, such as distributed ledgers, to ensure transparency and security. - *Governance decentralization*: The blockchain project is managed and decided by a decentralized community, not by a single individual or organization. ## Conditions for a blockchain project to be considered decentralized For a blockchain project to be considered truly decentralized, it needs to meet both conditions: - *Technical decentralization*: Uses decentralized technology to ensure transparency and security. - *Decentralized governance*: Managed and decided by a decentralized community, with transparent and fair decision-making mechanisms. If a blockchain project only meets one of the above two conditions, it may not be fully decentralized. ## Building a 100% Decentralized Ecosystem: A New Model for the Future In the context of rapidly developing blockchain technology, building a 100% decentralized ecosystem is not only a goal but also an essential need. The SkyPirl (PIRL coin) project has pioneered the application of a decentralized model not only in terms of technology but also in terms of governance. This article will analyze and demonstrate the importance of this model and convince the community, developers and organizations to support this policy. ## Why 100% Decentralization is Necessary 100% decentralization ensures that no single individual or organization can control the entire system. This enhances transparency, security and fairness. When applied to an ecosystem this model will bring many benefits: - *Increased transparency*: With the decentralization of power and management by many organizations and individuals, the system will become more transparent. - *Higher security*: The use of multi-signature wallets and treasury management by many representatives will reduce security risks. - *Fairness and democracy*: The decentralized model ensures that all decisions are made fairly and democratically. ## SkyPirl's Decentralized Governance Model SkyPirl project has adopted a decentralized governance model from the beginning by: - *Decentralized development team*: Multiple development teams from different countries, ensuring that no single country or organization controls the entire project. - *Restrict developer power*: Developers are not allowed to hold websites, domains and social media channels, helping to disperse power. - *Use smart contracts and multi-signature wallets*: To ensure transparency and security in treasury management and transactions. ## Applying the Model to the Ecosystem The ecosystem will apply this 100% decentralized model to all projects. This includes: - *Decentralization of power*: Many organizations and individuals will participate in management and decision-making. - *Use multi-signature wallets*: To ensure security and transparency in treasury management. - *Representatives from organizations*: Organizations will send representatives to participate in management and decision-making. #SkyPirl #PIRL #PIRLmeet #SLOFI #CLO #2BearsExchange
0:52

A blockchain project can be designed to be 100% technically decentralized, but if a single developer or a team within a single country controls the development and decision-making, the project may not be fully decentralized in terms of governance and decision-making. ## Differences between technical decentralization and governance decentralization - *Technical decentralization*: The blockchain project uses decentralized technology, such as distributed ledgers, to ensure transparency and security. - *Governance decentralization*: The blockchain project is managed and decided by a decentralized community, not by a single individual or organization. ## Conditions for a blockchain project to be considered decentralized For a blockchain project to be considered truly decentralized, it needs to meet both conditions: - *Technical decentralization*: Uses decentralized technology to ensure transparency and security. - *Decentralized governance*: Managed and decided by a decentralized community, with transparent and fair decision-making mechanisms. If a blockchain project only meets one of the above two conditions, it may not be fully decentralized. ## Building a 100% Decentralized Ecosystem: A New Model for the Future In the context of rapidly developing blockchain technology, building a 100% decentralized ecosystem is not only a goal but also an essential need. The SkyPirl (PIRL coin) project has pioneered the application of a decentralized model not only in terms of technology but also in terms of governance. This article will analyze and demonstrate the importance of this model and convince the community, developers and organizations to support this policy. ## Why 100% Decentralization is Necessary 100% decentralization ensures that no single individual or organization can control the entire system. This enhances transparency, security and fairness. When applied to an ecosystem this model will bring many benefits: - *Increased transparency*: With the decentralization of power and management by many organizations and individuals, the system will become more transparent. - *Higher security*: The use of multi-signature wallets and treasury management by many representatives will reduce security risks. - *Fairness and democracy*: The decentralized model ensures that all decisions are made fairly and democratically. ## SkyPirl's Decentralized Governance Model SkyPirl project has adopted a decentralized governance model from the beginning by: - *Decentralized development team*: Multiple development teams from different countries, ensuring that no single country or organization controls the entire project. - *Restrict developer power*: Developers are not allowed to hold websites, domains and social media channels, helping to disperse power. - *Use smart contracts and multi-signature wallets*: To ensure transparency and security in treasury management and transactions. ## Applying the Model to the Ecosystem The ecosystem will apply this 100% decentralized model to all projects. This includes: - *Decentralization of power*: Many organizations and individuals will participate in management and decision-making. - *Use multi-signature wallets*: To ensure security and transparency in treasury management. - *Representatives from organizations*: Organizations will send representatives to participate in management and decision-making. #SkyPirl #PIRL #PIRLmeet #SLOFI #CLO #2BearsExchange

SkyPirl Official 🎈🎈

16,196 Aufrufe • vor 1 Jahr

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test
0:22

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Chetaslua

127,047 Aufrufe • vor 2 Monaten

Perplexity CEO on China catching up in AI: “Whatever you did to not let them catch up didn’t even matter. They ended up catching up anyway. What’s more dangerous is they have the best open-source model. And all the American developers are building on that.” That was DeepSeek. Now just dropped GLM-5.2: • MIT open weights • 1M context • 81.0 on Terminal-Bench 2.1 • within a few points of Claude Opus 4.8 The open-source AI race is not theory anymore.
2:47

Perplexity CEO on China catching up in AI: “Whatever you did to not let them catch up didn’t even matter. They ended up catching up anyway. What’s more dangerous is they have the best open-source model. And all the American developers are building on that.” That was DeepSeek. Now just dropped GLM-5.2: • MIT open weights • 1M context • 81.0 on Terminal-Bench 2.1 • within a few points of Claude Opus 4.8 The open-source AI race is not theory anymore.

Vadim

650,826 Aufrufe • vor 3 Monaten

Jev week continues with one of our top returning guests, John Lindquist, where he shows about a dozen different things you can build with this TypeSafe AI decision model. He shows: - multi step routing - deduplicating messy data - model v model blitz chess - a real time presentation coach - and so many other ideas to inspire your use of Jev Brought to you by our wonderful sponsor 🫏 Vanta Automate compliance and simplify security: A super fun ep that could have gone for hours! Live on YT:
1:12

Jev week continues with one of our top returning guests, John Lindquist, where he shows about a dozen different things you can build with this TypeSafe AI decision model. He shows: - multi step routing - deduplicating messy data - model v model blitz chess - a real time presentation coach - and so many other ideas to inspire your use of Jev Brought to you by our wonderful sponsor 🫏 Vanta Automate compliance and simplify security: A super fun ep that could have gone for hours! Live on YT:

claire vo 🖤

14,951 Aufrufe • vor 12 Tagen

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.
1:52

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,854 Aufrufe • vor 3 Monaten

Microsoft's Chief of AI just announced that AI will replace almost all white-collar jobs within 18 months. Big Tech used our data to train their AI. Now that same AI is coming for our jobs. And we get nothing in return? If AI replaces us…we should own it. That’s why we built Action Model Not another chatbot. A community-owned AI model that acts. An AI trained by the people. Owned by the people. No billionaires controlling it. No extracting value from users. No “you are the product” model. Over 150,000+ people are already earning ownership in the AI future with Action Model. You should be too.
1:46

Microsoft's Chief of AI just announced that AI will replace almost all white-collar jobs within 18 months. Big Tech used our data to train their AI. Now that same AI is coming for our jobs. And we get nothing in return? If AI replaces us…we should own it. That’s why we built Action Model Not another chatbot. A community-owned AI model that acts. An AI trained by the people. Owned by the people. No billionaires controlling it. No extracting value from users. No “you are the product” model. Over 150,000+ people are already earning ownership in the AI future with Action Model. You should be too.

Georgia | Action Model

13,266 Aufrufe • vor 7 Monaten