Loading video...

Video Failed to Load

Go Home

Introducing CoreWeave ARIA, the first AI research agent that runs autoresearch in your W&B dashboard. It reads your runs, finds what's working, and launches the next experiment itself. See it on Andrej Karpathy's nanochat, proposing configs and launching real training runs. Watch👇 Chapters 0:00 The setup, nanochat runs on...

wandb's profile picture

Weights & Biases

48,643 subscribers

88,081 views • 28 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this
1:41

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this

self.dll

177,814 views • 3 months ago

Highlights brought to you by Rozzi Fireworks. Moeller started off their postseason run with a bang, as they scored a program record 25 runs in a 25-0 win over Western Hills. The offense exploded for 18 hits, including 6 extra base hits, which included 3 home runs. Matt Ponatoski led the team with 6 RBIs, one off from tying the program record in a game, going 3-3 with 2 home runs and a double. Might be the only Crusader in history to hit two home runs in a single inning (can’t verify). Jackson Porta also had 3 hits, going 3-3 himself. He also added on 3 RBIs on the day. Will Schirmer went 3-5, also registering 3 RBIs, an inside the park home run, and got a triple. Connor_Fuhrer threw a complete game 1 hitter. Connor didn’t walk a single batter for the second time this season, and he struck out 7, which ties for his career high.
2:25

Highlights brought to you by Rozzi Fireworks. Moeller started off their postseason run with a bang, as they scored a program record 25 runs in a 25-0 win over Western Hills. The offense exploded for 18 hits, including 6 extra base hits, which included 3 home runs. Matt Ponatoski led the team with 6 RBIs, one off from tying the program record in a game, going 3-3 with 2 home runs and a double. Might be the only Crusader in history to hit two home runs in a single inning (can’t verify). Jackson Porta also had 3 hits, going 3-3 himself. He also added on 3 RBIs on the day. Will Schirmer went 3-5, also registering 3 RBIs, an inside the park home run, and got a triple. Connor_Fuhrer threw a complete game 1 hitter. Connor didn’t walk a single batter for the second time this season, and he struck out 7, which ties for his career high.

BigMoeBaseballAnalytics

12,176 views • 1 year ago

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch
24:21

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

GREG ISENBERG

435,933 views • 4 months ago

I built Caduceus for Hermes Desktop Nous Research Two snakes, one staff Caduceus runs parallel AI agents in perfect sync, on any model you already have It sizes up every task and picks the path: • Easy → answered instantly • Hard → a live to-do plan + agents fanned out in parallel, verified before it calls it done Caduceus has a UI right inside Hermes so you watch every agent build your project in real time Full demo 👇
2:12

I built Caduceus for Hermes Desktop Nous Research Two snakes, one staff Caduceus runs parallel AI agents in perfect sync, on any model you already have It sizes up every task and picks the path: • Easy → answered instantly • Hard → a live to-do plan + agents fanned out in parallel, verified before it calls it done Caduceus has a UI right inside Hermes so you watch every agent build your project in real time Full demo 👇

Terp

16,919 views • 1 month ago

There's a free 120 billion parameter AI you can run on your own computer. Zero internet. Zero API costs. Zero monthly fees. It's called Nvidia Nemotron 3 Super. And it just changed what solopreneurs can do with AI agents. Here's the setup: → Download Ollama. Copy one command into your terminal. → Connect it to OpenClaw in under 10 minutes. → Your AI agent now runs 24/7 on WhatsApp, Discord, or Telegram. → It answers customers, runs tasks, and manages workflows while you sleep. → 256,000 token context window. It reads entire documents without forgetting. No subscriptions. No cloud. No one else touching your data. A full AI employee stack for $0. Save this. Set it up this weekend.
10:33

There's a free 120 billion parameter AI you can run on your own computer. Zero internet. Zero API costs. Zero monthly fees. It's called Nvidia Nemotron 3 Super. And it just changed what solopreneurs can do with AI agents. Here's the setup: → Download Ollama. Copy one command into your terminal. → Connect it to OpenClaw in under 10 minutes. → Your AI agent now runs 24/7 on WhatsApp, Discord, or Telegram. → It answers customers, runs tasks, and manages workflows while you sleep. → 256,000 token context window. It reads entire documents without forgetting. No subscriptions. No cloud. No one else touching your data. A full AI employee stack for $0. Save this. Set it up this weekend.

Julian Goldie SEO

29,325 views • 4 months ago

Today we are re-introducing Warp, the AI-native employee management platform for payroll, compliance, benefits, HR, and IT that runs itself. We’ve raised $85M to rebuild the last great enterprise software category. We shipped more in the last 3 months than our first two years combined, so we made a video to tell our story and showcase the platform. Warp brings payroll, HR, compliance, IT, and benefits into one platform, from your first hire to your ten-thousandth. Payroll runs on its own, accurate and on time across all 50 states, and in 150-plus countries in local currency. Hire in a new state and Warp registers you with every agency automatically. When a tax notice shows up, Warp reads it, drafts the response, and files it across more than 10,000 jurisdictions. 80% resolve without anyone on your team touching them. The rest go to our in-house tax experts, not back to you. Onboarding runs itself. The moment an offer is signed, agreements, direct deposit, tax forms, benefits, and every account, app, and device get provisioned automatically. The day someone leaves, all of it deactivates in one action. Benefits work the same way. Warp is your licensed broker across every carrier for health, dental, vision, and 401k. You pick the plan. Enrollment, renewals, and every deduction into payroll happen on their own. Revenue has grown 100x in 2 years. 1,200+ companies run payroll, HR, and compliance on Warp. We're on track to process $1.7B in payroll this year. This is just the beginning of what AI-native employee management looks like. We can't wait to build the rest of it with you. Run your company at warp speed:
2:14

Today we are re-introducing Warp, the AI-native employee management platform for payroll, compliance, benefits, HR, and IT that runs itself. We’ve raised $85M to rebuild the last great enterprise software category. We shipped more in the last 3 months than our first two years combined, so we made a video to tell our story and showcase the platform. Warp brings payroll, HR, compliance, IT, and benefits into one platform, from your first hire to your ten-thousandth. Payroll runs on its own, accurate and on time across all 50 states, and in 150-plus countries in local currency. Hire in a new state and Warp registers you with every agency automatically. When a tax notice shows up, Warp reads it, drafts the response, and files it across more than 10,000 jurisdictions. 80% resolve without anyone on your team touching them. The rest go to our in-house tax experts, not back to you. Onboarding runs itself. The moment an offer is signed, agreements, direct deposit, tax forms, benefits, and every account, app, and device get provisioned automatically. The day someone leaves, all of it deactivates in one action. Benefits work the same way. Warp is your licensed broker across every carrier for health, dental, vision, and 401k. You pick the plan. Enrollment, renewals, and every deduction into payroll happen on their own. Revenue has grown 100x in 2 years. 1,200+ companies run payroll, HR, and compliance on Warp. We're on track to process $1.7B in payroll this year. This is just the beginning of what AI-native employee management looks like. We can't wait to build the rest of it with you. Run your company at warp speed:

Ayush S

30,433 views • 19 days ago

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7
13:29

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7

Noisy

524,181 views • 1 month ago

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own
0:20

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

NO1ennn

40,079 views • 1 month ago

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch
39:43

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

80,088 views • 14 days ago

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!
20:04

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!

Theo

33,099 views • 4 months ago

What if instead of autoresearch reflecting incremental progress from a single person, it reflected *hundreds* of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.
1:43

What if instead of autoresearch reflecting incremental progress from a single person, it reflected *hundreds* of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.

Paul Scotti @ ICML

22,181 views • 28 days ago

KING MALIK Achievements as a Cricketer: ● International Cricket: Runs: 11,867 Hundreds: 12 Fifties: 61 Double Hundred: 1 Catches: 166 Sixes: 199 Wickets: 218 BBI: 4/19 POTMs: 25 POTSs: 8 ●T20 Format: Runs: 13,571 Wickets: 187 Fifties: 83 Catches: 238 Sixes: 422 POTMs: 43 POTSs: 3 BBI: 5/13 5fers: 2 ■ MAJOR TOURNAMENT WINS: • 2009 T20WC • 2017 Champions Trophy • 2000 Asia Cup • 16 T20 titles ■ PAKISTAN-SPECIFIC RECORDS: • 9th highest international run-scorer for Pakistan: (11,867 runs) • 5th most ODI runs for Pakistan: (7,534 runs) • 4th most T20I runs for Pakistan: (2,423 runs) • 5th most ODI wickets for Pakistan among spinners: (158 Wickets) • 7th most Player of the Match awards for Pakistan: (25 POTMs) • 3rd most Player of the Series awards for Pakistan: (8 POTS) • Most runs for Pakistan in multi-nation events: (2,033 runs) • 2nd most centuries for Pakistan in tournaments: (4 Hundreds) • 2nd Most Player of the Match awards for Pakistan in tournaments: (7 POTMs) • Most Runs for Pakistan in T20 World Cups: (646 runs at an average of 34) • Most Runs for Pakistan in Asia Cups: (907 runs at an average of 65 along with 14 wickets at an economy of 4.3) • 2nd most Player of the Match awards in Asia Cup history: (5 POTMs) • Highest run-scorer in Asia Cup 2004: 316 runs at an average of 64 (along with 9 wickets at an economy of 3.2) • Highest score in Champions Trophy for Pakistan: 128 vs India (2009) ■ ICONIC MOMENTS vs INDIA & In BIG GAMES: • Four ODI centuries and 11 fifties against India in 42 Matches. • 1,782 ODI runs vs India @ 47 average. • Only Pakistani batter to score an ODI century against India in ICC events & Asia Cups. • Most ODI hundreds in multinational tournaments vs India — (3 Hundreds) • Century + four-wicket haul in the same ODI. • Only player in T20 World Cup history to score two consecutive Match winning fifties on consecutive days: • 57 (31) vs Sri Lanka 17 SEP 2007 • 52* (38) vs Australia 18 SEP 2007 • Match-winning partnerships with Shahid Afridi in 2009 T20WC semi-final & final ■ LEADERSHIP & CLUTCH RECORDS: • 3rd most T20 Trophies (16 Titles) • 6th Most runs in T20s.(13571 runs) • 6th most POTMs in T20s. (43 POTMs) • Highest winning percentage as Pakistan ODI captain — 61.0% • Highest Batting Average against SENA in T20WC history: (49.80) • First captain to win 10 T20I matches. •2nd most Player of the Match awards as captain in T20s. (18 POTMs) • 700+ T20I runs @ 47 avg & 150+ SR under Sarfraz Ahmed during Pakistan’s 3-year No.1 ranking period. • Most runs in middle order in T20I wins (1662) • 4th Most T20I wins as a Player (86 wins). • Most not-outs in successful T20I run-chases in history — (18 times). • 3rd most not-outs in successful run-chases (ODI + T20I) — (40 Times). • 4th Most runs in Psl history (2350 runs) • Highest 4th innings batting average in the 21st century — (58.71 Avg) • Led Pakistan to the 2007 T20 World Cup final ■ T20 KNOCKOUTS & FINAL MASTER: • Most Player of the Match awards in T20 knockouts — 9 • Most Player of the Match awards in T20 finals — (5 POTMs) • Most runs in T20 finals — 589 @ 42 avg + 12 wickets • Most runs in T20 knockouts — 1,675 @ 36 avg + 24 wickets • Most runs in winning T20 finals — 470 @ 58 avg + 7 wickets • Most runs in winning T20 knockouts — 1,001 @ 50 avg + 16 wickets. • Player of the Match award in CPL Final 2015. • Player of the Match award in LPL Final 2020. ■ HISTORIC MILESTONES: • 30,000+ runs and 750+ wickets in professional cricket. • Only player in history with 25,000+ runs & 300+ wickets — 25,018 runs & 496 wickets. •Only Asian player with 2,000+ runs & 50+ wickets as captain in T20 cricket — 4,115 runs & 78 wickets Happy birthday to one of the Greatest and most underrated cricket ever. Shoaib Malik 🇵🇰 #PakvsAus #PakVsInd
0:36

KING MALIK Achievements as a Cricketer: ● International Cricket: Runs: 11,867 Hundreds: 12 Fifties: 61 Double Hundred: 1 Catches: 166 Sixes: 199 Wickets: 218 BBI: 4/19 POTMs: 25 POTSs: 8 ●T20 Format: Runs: 13,571 Wickets: 187 Fifties: 83 Catches: 238 Sixes: 422 POTMs: 43 POTSs: 3 BBI: 5/13 5fers: 2 ■ MAJOR TOURNAMENT WINS: • 2009 T20WC • 2017 Champions Trophy • 2000 Asia Cup • 16 T20 titles ■ PAKISTAN-SPECIFIC RECORDS: • 9th highest international run-scorer for Pakistan: (11,867 runs) • 5th most ODI runs for Pakistan: (7,534 runs) • 4th most T20I runs for Pakistan: (2,423 runs) • 5th most ODI wickets for Pakistan among spinners: (158 Wickets) • 7th most Player of the Match awards for Pakistan: (25 POTMs) • 3rd most Player of the Series awards for Pakistan: (8 POTS) • Most runs for Pakistan in multi-nation events: (2,033 runs) • 2nd most centuries for Pakistan in tournaments: (4 Hundreds) • 2nd Most Player of the Match awards for Pakistan in tournaments: (7 POTMs) • Most Runs for Pakistan in T20 World Cups: (646 runs at an average of 34) • Most Runs for Pakistan in Asia Cups: (907 runs at an average of 65 along with 14 wickets at an economy of 4.3) • 2nd most Player of the Match awards in Asia Cup history: (5 POTMs) • Highest run-scorer in Asia Cup 2004: 316 runs at an average of 64 (along with 9 wickets at an economy of 3.2) • Highest score in Champions Trophy for Pakistan: 128 vs India (2009) ■ ICONIC MOMENTS vs INDIA & In BIG GAMES: • Four ODI centuries and 11 fifties against India in 42 Matches. • 1,782 ODI runs vs India @ 47 average. • Only Pakistani batter to score an ODI century against India in ICC events & Asia Cups. • Most ODI hundreds in multinational tournaments vs India — (3 Hundreds) • Century + four-wicket haul in the same ODI. • Only player in T20 World Cup history to score two consecutive Match winning fifties on consecutive days: • 57 (31) vs Sri Lanka 17 SEP 2007 • 52* (38) vs Australia 18 SEP 2007 • Match-winning partnerships with Shahid Afridi in 2009 T20WC semi-final & final ■ LEADERSHIP & CLUTCH RECORDS: • 3rd most T20 Trophies (16 Titles) • 6th Most runs in T20s.(13571 runs) • 6th most POTMs in T20s. (43 POTMs) • Highest winning percentage as Pakistan ODI captain — 61.0% • Highest Batting Average against SENA in T20WC history: (49.80) • First captain to win 10 T20I matches. •2nd most Player of the Match awards as captain in T20s. (18 POTMs) • 700+ T20I runs @ 47 avg & 150+ SR under Sarfraz Ahmed during Pakistan’s 3-year No.1 ranking period. • Most runs in middle order in T20I wins (1662) • 4th Most T20I wins as a Player (86 wins). • Most not-outs in successful T20I run-chases in history — (18 times). • 3rd most not-outs in successful run-chases (ODI + T20I) — (40 Times). • 4th Most runs in Psl history (2350 runs) • Highest 4th innings batting average in the 21st century — (58.71 Avg) • Led Pakistan to the 2007 T20 World Cup final ■ T20 KNOCKOUTS & FINAL MASTER: • Most Player of the Match awards in T20 knockouts — 9 • Most Player of the Match awards in T20 finals — (5 POTMs) • Most runs in T20 finals — 589 @ 42 avg + 12 wickets • Most runs in T20 knockouts — 1,675 @ 36 avg + 24 wickets • Most runs in winning T20 finals — 470 @ 58 avg + 7 wickets • Most runs in winning T20 knockouts — 1,001 @ 50 avg + 16 wickets. • Player of the Match award in CPL Final 2015. • Player of the Match award in LPL Final 2020. ■ HISTORIC MILESTONES: • 30,000+ runs and 750+ wickets in professional cricket. • Only player in history with 25,000+ runs & 300+ wickets — 25,018 runs & 496 wickets. •Only Asian player with 2,000+ runs & 50+ wickets as captain in T20 cricket — 4,115 runs & 78 wickets Happy birthday to one of the Greatest and most underrated cricket ever. Shoaib Malik 🇵🇰 #PakvsAus #PakVsInd

Daniyal

23,126 views • 5 months ago

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2
11:32

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 views • 1 month ago

this Adaptive AI agent tells brands exactly what tiktok content is going viral in their niche before they brief a single creator here's how brands are running campaigns that actually convert on Content Rewards: -> drop your niche hashtag in and it scans TikTok for the highest performing content right now -> filters by view velocity, engagement rate, and watch time -> identifies the exact hooks, formats, and topics driving views in your market -> maps out the patterns every viral video in your niche shares -> generates a full content brief your creators can execute immediately -> launch it as a clipping campaign on content rewards and scale with hundreds of creators -> tracks what's working and updates the brief as trends shift -> every step from trend research to live campaign is automated what used to cost a full agency retainer now runs on autopilot. reply "AGENT" + RT and i'll send you the full breakdown so you can launch your first data-driven creator campaign this week (must be following)
0:45

this Adaptive AI agent tells brands exactly what tiktok content is going viral in their niche before they brief a single creator here's how brands are running campaigns that actually convert on Content Rewards: -> drop your niche hashtag in and it scans TikTok for the highest performing content right now -> filters by view velocity, engagement rate, and watch time -> identifies the exact hooks, formats, and topics driving views in your market -> maps out the patterns every viral video in your niche shares -> generates a full content brief your creators can execute immediately -> launch it as a clipping campaign on content rewards and scale with hundreds of creators -> tracks what's working and updates the brief as trends shift -> every step from trend research to live campaign is automated what used to cost a full agency retainer now runs on autopilot. reply "AGENT" + RT and i'll send you the full breakdown so you can launch your first data-driven creator campaign this week (must be following)

adam

331,919 views • 3 months ago

The top ranked team in the state, Defiance Baseball used a 6 run 5th inning to defeat #4 (D6) Fairview High School Baseball 9-4 in a tune up game for both teams before the tourney starts later this week. 8 of 9 hitters for the Bulldogs collected hits, and 7 of 9 hitters scored runs as Defiance used a balanced attack 1-9 in the lineup. Logan Hutcheson had three hits out of the leadoff spot while the 2-3 hole of Cohen Stockman-Brady Borton drove in 5 runs. Garyson Smiddy went the distance on the bump, striking out 9. Fairview (20-3) had a 3-1 lead through 4 but couldn’t hold on. The Apaches swing it well 1-9 and have multiple arms they can throw at you. Follow the thread for videos, reports and more 📹📝👇
3:50

The top ranked team in the state, Defiance Baseball used a 6 run 5th inning to defeat #4 (D6) Fairview High School Baseball 9-4 in a tune up game for both teams before the tourney starts later this week. 8 of 9 hitters for the Bulldogs collected hits, and 7 of 9 hitters scored runs as Defiance used a balanced attack 1-9 in the lineup. Logan Hutcheson had three hits out of the leadoff spot while the 2-3 hole of Cohen Stockman-Brady Borton drove in 5 runs. Garyson Smiddy went the distance on the bump, striking out 9. Fairview (20-3) had a 3-1 lead through 4 but couldn’t hold on. The Apaches swing it well 1-9 and have multiple arms they can throw at you. Follow the thread for videos, reports and more 📹📝👇

Prep Baseball Ohio Scouting Coverage

10,422 views • 1 year ago

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.
0:41

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.

cvxv666

103,359 views • 21 days ago

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change
18:41

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change

Mr. Buzzoni

153,432 views • 1 month ago

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.
0:34

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.

Hassan

27,086 views • 10 months ago

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock
0:31

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock

Gipp 🦅

18,927 views • 25 days ago

I've decided that what is going on right now with the Mississippi State Baseball program is The Curse of Yoknapatawpha. You William Faulkner fans won't have to run to Google, and you old timers will remember the Curse of the Lava Rocks one season in a year when the Bulldogs played in Hawaii. How else to positively explain the five-game SEC losing streak after sweeping the rival Ole Miss Rebels at home? Tonight, it was a 6-2 loss to Tennessee and not getting a hit, much less a run, while the Volunteers put up a 4-0 lead. Not getting a single walk didn't help when home runs and extra base hits did score runs, and the Bulldogs settled down after Duke Stone was roughed up early but then put up zeroes. Here are post-game comments from Coach Oak. The third game is Sunday at 1 pm.
6:30

I've decided that what is going on right now with the Mississippi State Baseball program is The Curse of Yoknapatawpha. You William Faulkner fans won't have to run to Google, and you old timers will remember the Curse of the Lava Rocks one season in a year when the Bulldogs played in Hawaii. How else to positively explain the five-game SEC losing streak after sweeping the rival Ole Miss Rebels at home? Tonight, it was a 6-2 loss to Tennessee and not getting a hit, much less a run, while the Volunteers put up a 4-0 lead. Not getting a single walk didn't help when home runs and extra base hits did score runs, and the Bulldogs settled down after Duke Stone was roughed up early but then put up zeroes. Here are post-game comments from Coach Oak. The third game is Sunday at 1 pm.

Doug Kyle

26,898 views • 3 months ago