Loading video...

Video Failed to Load

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

Here's a supply chain attack running on an VM. It's so obvious even Claude catches it. But it doesn't matter: by the time Claude sees it, the attack is done. Except in this case, it isn't. Egress rules block it. Real attacks won't look like this. You need real containment.

Matthew Slipper

1,560 subscribers

11,575 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude 3, take this Excel Reverse Income Statement & make it a dashboard Make it nicer. Add the ability to do sensitivity analysis. All of this is real time. It diverges a bit from the spreadsheet because Claude can't read formulas, so it reconstructs the formulas itself (well)

Claude 3, take this Excel Reverse Income Statement & make it a dashboard Make it nicer. Add the ability to do sensitivity analysis. All of this is real time. It diverges a bit from the spreadsheet because Claude can't read formulas, so it reconstructs the formulas itself (well)

Ethan Mollick

255,059 views • 2 years ago

"We need this city to continue come out and support - but we don't care who we're playing, what time it is, where it is... Doesn't matter, we're gonna attack this thing with a relentless pursuit." You heard the man:

"We need this city to continue come out and support - but we don't care who we're playing, what time it is, where it is... Doesn't matter, we're gonna attack this thing with a relentless pursuit." You heard the man:

Jacksonville Jaguars

23,307 views • 2 months ago

Anthropic shows this video to every new employee. Someone re-uploaded it. I hope Anthropic doesn't see this. 14 minutes of how the Claude team actually uses Claude in real work. I watched the recording last night and kept pausing it. Each time realizing I've been using Claude like a toy. claude.md + loops is what makes Claude stop fighting you and start working for you. Most people will keep using Claude the hard way.

Anthropic shows this video to every new employee. Someone re-uploaded it. I hope Anthropic doesn't see this. 14 minutes of how the Claude team actually uses Claude in real work. I watched the recording last night and kept pausing it. Each time realizing I've been using Claude like a toy. claude.md + loops is what makes Claude stop fighting you and start working for you. Most people will keep using Claude the hard way.

Raytar

257,018 views • 1 month ago

Newsflash: If Russia is forced to attack NATO, you'll know all about it. It won't be a single drone landing on the roof of an apartment block in Romania. The idiocy of European politicians claiming it was an attack is immeasurable.

Newsflash: If Russia is forced to attack NATO, you'll know all about it. It won't be a single drone landing on the roof of an apartment block in Romania. The idiocy of European politicians claiming it was an attack is immeasurable.

Chay Bowes

36,861 views • 1 month ago

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,240 views • 4 months ago

Despite reports that Jalen Carter isn't participating in team drills, Ike isn't concerned... yet. "This is the time to air your grievances in the offseason. This is the time you do it. It doesn't have an impact on games on Sunday. It doesn't have an impact on training camp."

Despite reports that Jalen Carter isn't participating in team drills, Ike isn't concerned... yet. "This is the time to air your grievances in the offseason. This is the time you do it. It doesn't have an impact on games on Sunday. It doesn't have an impact on training camp."

SPORTSRADIO 94WIP

29,749 views • 1 month ago

This is the best new feature Claude has launched in 2026. "Teach Claude a Skill" lets AI agents watch your desktop in real time and create reusable Claude Skills. I've been using it non-stop; here's my full guide:

This is the best new feature Claude has launched in 2026. "Teach Claude a Skill" lets AI agents watch your desktop in real time and create reusable Claude Skills. I've been using it non-stop; here's my full guide:

Miles Deutscher

40,577 views • 7 days ago

THIS GUY TURNED A DESK LAMP INTO A LIVE CLAUDE CODE STATUS INDICATOR the lamp changes color based on what claude code is doing in real time when claude is thinking it's one color. when it's writing code it shifts. when it's done it changes again. when it errors out you know instantly without even looking at your screen the lamp is a moonside halo and i'm already tryna to buy one I might even buy multiple for the multiple claude sessions running in the background and turn my room into a disco if the color reflected the operational status of claude it would just be red 24/7 it could also track your usage limit. green at the start of the session, slowly fading to red as your tokens drain people are already hooking this up to their philips hue and govee setups at home

THIS GUY TURNED A DESK LAMP INTO A LIVE CLAUDE CODE STATUS INDICATOR the lamp changes color based on what claude code is doing in real time when claude is thinking it's one color. when it's writing code it shifts. when it's done it changes again. when it errors out you know instantly without even looking at your screen the lamp is a moonside halo and i'm already tryna to buy one I might even buy multiple for the multiple claude sessions running in the background and turn my room into a disco if the color reflected the operational status of claude it would just be red 24/7 it could also track your usage limit. green at the start of the session, slowly fading to red as your tokens drain people are already hooking this up to their philips hue and govee setups at home

Om Patel

108,062 views • 2 months ago

My two cents on this is that it isn't even just the upscaling, but the frame rate is especially bad here. It's not too noticeable with the cartoon segments, but it's very obvious with the intro. Here's what the intro looks like when running at a correct 60fps.

My two cents on this is that it isn't even just the upscaling, but the frame rate is especially bad here. It's not too noticeable with the cartoon segments, but it's very obvious with the intro. Here's what the intro looks like when running at a correct 60fps.

The Super Mario Bros. Super HQ!

19,239 views • 4 months ago

Trump on shutdown: They’re the ones that started it. They're the ones that have it. And it's almost like a kamikaze attack by them. You want to know the truth? This is like a kamikaze attack. They lost the election in a landslide

Trump on shutdown: They’re the ones that started it. They're the ones that have it. And it's almost like a kamikaze attack by them. You want to know the truth? This is like a kamikaze attack. They lost the election in a landslide

Acyn

33,483 views • 9 months ago

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

@levelsio

143,316 views • 6 months ago

CLAUDE CAN NOW TEST ITS OWN CODE IN A REAL BROWSER AND SCREEN RECORD ITSELF DOING IT SO YOU NEVER HAVE TO VERIFY MANUALLY it opens a real browser, catches console errors, confirms network calls, and records every step, so it stops saying "this should work" and starts proving it does.

CLAUDE CAN NOW TEST ITS OWN CODE IN A REAL BROWSER AND SCREEN RECORD ITSELF DOING IT SO YOU NEVER HAVE TO VERIFY MANUALLY it opens a real browser, catches console errors, confirms network calls, and records every step, so it stops saying "this should work" and starts proving it does.

0xMarioNawfal

51,153 views • 1 month ago

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Ethan Mollick

162,293 views • 2 years ago

McKenzie tied Bitcoin to Epstein funding MIT. Lyn's answer cuts to the real point: it doesn't matter. "Even if the CIA made Bitcoin, it wouldn't change the properties. It's open source. It's auditable. You can evaluate it on what it actually is."

McKenzie tied Bitcoin to Epstein funding MIT. Lyn's answer cuts to the real point: it doesn't matter. "Even if the CIA made Bitcoin, it wouldn't change the properties. It's open source. It's auditable. You can evaluate it on what it actually is."

Swan

14,897 views • 3 months ago

Claude Code plays Runescape: The waterfall quest. Here Claude Opus 4.6 is acquiring quest items in the maze and tomb. Not a script, real play. It tried things, failed, learned, and succeeded. I sped this up a lot, it's ~20 minutes of real time.

Claude Code plays Runescape: The waterfall quest. Here Claude Opus 4.6 is acquiring quest items in the maze and tomb. Not a script, real play. It tried things, failed, learned, and succeeded. I sped this up a lot, it's ~20 minutes of real time.

Rob Haisfield

420,302 views • 5 months ago

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

69,744 views • 1 month ago

Claude Code feels completely different once you install this. Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment. It scans your project and recommends: → hooks → skills → MCP servers → subagents → automations Then sets everything up step-by-step for you. Most people are using Claude Code completely vanilla… which is why their experience feels messy. The real power comes from the ecosystem around it. Install: /plugin install claude-code-setup@claude-plugins-official Bookmark this before you forget it.

Claude Code feels completely different once you install this. Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment. It scans your project and recommends: → hooks → skills → MCP servers → subagents → automations Then sets everything up step-by-step for you. Most people are using Claude Code completely vanilla… which is why their experience feels messy. The real power comes from the ecosystem around it. Install: /plugin install claude-code-setup@claude-plugins-official Bookmark this before you forget it.

Radha Tripathi

75,447 views • 2 months ago

Could also just be watching football and fun plays like this but it doesn't have an NFL logo on the screen so it's not real 🤷‍♂️

United Football Media

75,149 views • 1 month ago

This is from today's #WCWS game. This was ruled a base hit when it happened (you can see the 'H' pop up), but was changed to a missed catch error by the first baseman at the bottom of the fourth. This is an impossible catch for the first baseman with a ball thrown from that angle, that hard. This throw has to be to the glove, and while it's not a wild throw, it's low enough that the first baseman cannot get her glove around it in time. This is where replay gets you in trouble. The slo-mo replay makes it look like it's a catchable ball, but it isn't. In real time, at live speed, this isn't an error. This isn't a missed catch or a drop. I was loving the call of a single, especially because it was the first hit, and then, when it was changed, it felt like it was to protect a no-hitter. Everything about this screams "above ordinary effort" ... I would have left this as a single.

This is from today's #WCWS game. This was ruled a base hit when it happened (you can see the 'H' pop up), but was changed to a missed catch error by the first baseman at the bottom of the fourth. This is an impossible catch for the first baseman with a ball thrown from that angle, that hard. This throw has to be to the glove, and while it's not a wild throw, it's low enough that the first baseman cannot get her glove around it in time. This is where replay gets you in trouble. The slo-mo replay makes it look like it's a catchable ball, but it isn't. In real time, at live speed, this isn't an error. This isn't a missed catch or a drop. I was loving the call of a single, especially because it was the first hit, and then, when it was changed, it felt like it was to protect a no-hitter. Everything about this screams "above ordinary effort" ... I would have left this as a single.

MLB Scoring Changes

30,825 views • 1 month ago

Flashback to when John Solomon called it like he sees it... he says Prosecutors have fallen so far behind on major arrests, time is running out on Statutes We're missing valuable time, I don't think the DOJ is getting it Pam Bondi isn't cutout for this, we need Judge Jeannine

Flashback to when John Solomon called it like he sees it... he says Prosecutors have fallen so far behind on major arrests, time is running out on Statutes We're missing valuable time, I don't think the DOJ is getting it Pam Bondi isn't cutout for this, we need Judge Jeannine

@Chicago1Ray 🇺🇸

63,252 views • 6 months ago