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.

Three new modes on Caffeine Instant mode - Caffeine just starts building. No questions. Thinking mode - asks follow-up questions if it needs context, then builds. Pro mode - gathers full requirements and confirms before building anything. You choose how Caffeine works.

caffeine

25,595 subscribers

29,278 views • 6 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

"You remind me of Scorpion..." 🥵🥵 #SM13

"You remind me of Scorpion..." 🥵🥵 #SM13

Caffeine

38,698 views • 3 years ago

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 views • 6 months ago

Is it ok to combine creatine with caffeine? They are generally not a problem together unless your caffeine dose is very high. The interference seems to show up around ~350 mg of caffeine pre-workout (about 3.5 cups of coffee), where caffeine may blunt some of creatine’s performance benefit because they have opposite effects on muscle relaxation. So yes, you can put creatine in your coffee (I do). Just don’t mega-dose caffeine before training if you want the full ergogenic effect. Even then, the effect is probably minor enough to not stress about.

Is it ok to combine creatine with caffeine? They are generally not a problem together unless your caffeine dose is very high. The interference seems to show up around ~350 mg of caffeine pre-workout (about 3.5 cups of coffee), where caffeine may blunt some of creatine’s performance benefit because they have opposite effects on muscle relaxation. So yes, you can put creatine in your coffee (I do). Just don’t mega-dose caffeine before training if you want the full ergogenic effect. Even then, the effect is probably minor enough to not stress about.

Dr. Rhonda Patrick

97,737 views • 3 months ago

If you’ve tried everything—melatonin, magnesium, breathwork, and still can’t sleep, this might be what you’re missing. I started using Hapbee, and it’s a total game-changer. On my 8-hour flight from Dubai, I set it to sleep mode and woke up 8 hours and 2 minutes later, fully rested. No supplements, no grogginess—just deep, natural sleep. Here’s how it works: ✅ Goes under your pillow—no wires, no weird sounds ✅ Uses frequency technology to mimic melatonin, adenosine & even caffeine without actually taking them ✅ Turn it off & the effect stops instantly—no lingering side effects You can even use the caffeine setting in the morning for a boost without drinking coffee Are you giving it a try? LEARN MORE:

If you’ve tried everything—melatonin, magnesium, breathwork, and still can’t sleep, this might be what you’re missing. I started using Hapbee, and it’s a total game-changer. On my 8-hour flight from Dubai, I set it to sleep mode and woke up 8 hours and 2 minutes later, fully rested. No supplements, no grogginess—just deep, natural sleep. Here’s how it works: ✅ Goes under your pillow—no wires, no weird sounds ✅ Uses frequency technology to mimic melatonin, adenosine & even caffeine without actually taking them ✅ Turn it off & the effect stops instantly—no lingering side effects You can even use the caffeine setting in the morning for a boost without drinking coffee Are you giving it a try? LEARN MORE:

Gary Brecka

104,461 views • 1 year ago

No more waiting on your Super Agent. With our Queued Follow-Up Messages, you can type your next questions while the agent is still thinking. They stack and run automatically, even if you close the browser. Manual mode for review/edit too. So queue it up. Let the agent do the work.

No more waiting on your Super Agent. With our Queued Follow-Up Messages, you can type your next questions while the agent is still thinking. They stack and run automatically, even if you close the browser. Manual mode for review/edit too. So queue it up. Let the agent do the work.

Creao AI

47,324 views • 4 months ago

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 views • 1 month ago

Grok modes. Lazy, speed, brains; everything in between. Pick one. Fast answers, step-by-step thinking, or multiple AIs teaming up on your problem. How to pick your mode: •⁠ ⁠Start a chat - app, or 𝕏. Nothing fancy. •⁠ ⁠Bottom bar - tap “Auto” next to “Ask anything”. That’s the switch. •⁠ ⁠Auto - Grok decides for you. Lazy mode, works fine. •⁠ ⁠Fast - quick answers, minimal thinking, gets it out. •⁠ ⁠Expert - deeper reasoning, actually thinks it through. •⁠ ⁠Heavy - multi-agent mode, throws a whole team of AI agents at it. Paid power. •⁠ ⁠Ask your question - or specify the mode upfront. •⁠ ⁠Switch anytime - upgrade mid-chat when things get serious. X xAI

Grok modes. Lazy, speed, brains; everything in between. Pick one. Fast answers, step-by-step thinking, or multiple AIs teaming up on your problem. How to pick your mode: •⁠ ⁠Start a chat - app, or 𝕏. Nothing fancy. •⁠ ⁠Bottom bar - tap “Auto” next to “Ask anything”. That’s the switch. •⁠ ⁠Auto - Grok decides for you. Lazy mode, works fine. •⁠ ⁠Fast - quick answers, minimal thinking, gets it out. •⁠ ⁠Expert - deeper reasoning, actually thinks it through. •⁠ ⁠Heavy - multi-agent mode, throws a whole team of AI agents at it. Paid power. •⁠ ⁠Ask your question - or specify the mode upfront. •⁠ ⁠Switch anytime - upgrade mid-chat when things get serious. X xAI

Mario Nawfal

24,546 views • 4 months ago

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Google Antigravity

89,391 views • 7 months ago

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

450,204 views • 2 months ago

How your ability to focus is dependent on your diet: Being fasted reduces parasympathetic "rest and digest" activation, keeping you alert. "Half as much caffeine will give you just as much lift as twice as much caffeine will give you on a full belly of pasta." Neurons thrive on glucose. A study published in Neuron found that "the precision with which neurons in the brain will represent things in our environment is actually much greater when there is sufficient glucose in the brain." Very low blood glucose sharpens concentration through alertness; sufficient blood glucose sharpens concentration through improved neural encoding. Overeating collapses both. Delay the first caffeine intake to 90 to 120 minutes after waking to avoid an afternoon energy crash. Do a first 90-minute focus block fasted with water, electrolytes, and caffeine. After eating, expect a dip. A second 90-minute block in the afternoon is viable if the midday meal is modest enough to avoid pushing the nervous system into parasympathetic mode. Andrew D. Huberman, Ph.D.

How your ability to focus is dependent on your diet: Being fasted reduces parasympathetic "rest and digest" activation, keeping you alert. "Half as much caffeine will give you just as much lift as twice as much caffeine will give you on a full belly of pasta." Neurons thrive on glucose. A study published in Neuron found that "the precision with which neurons in the brain will represent things in our environment is actually much greater when there is sufficient glucose in the brain." Very low blood glucose sharpens concentration through alertness; sufficient blood glucose sharpens concentration through improved neural encoding. Overeating collapses both. Delay the first caffeine intake to 90 to 120 minutes after waking to avoid an afternoon energy crash. Do a first 90-minute focus block fasted with water, electrolytes, and caffeine. After eating, expect a dip. A second 90-minute block in the afternoon is viable if the midday meal is modest enough to avoid pushing the nervous system into parasympathetic mode. Andrew D. Huberman, Ph.D.

Huberman Lab Clips

10,692 views • 2 months ago

We’re introducing a new Search experience in Chrome that lets you open webpages side-by-side with AI Mode – no tab switching required. Now, you’ll be able to compare details and ask follow-up questions while still maintaining the context of your search, whether you’re shopping for a new coffee maker or studying for a statistics midterm.

We’re introducing a new Search experience in Chrome that lets you open webpages side-by-side with AI Mode – no tab switching required. Now, you’ll be able to compare details and ask follow-up questions while still maintaining the context of your search, whether you’re shopping for a new coffee maker or studying for a statistics midterm.

Google

344,909 views • 4 months ago

GROKIPEDIA 101 – HOW TO EDIT THE xAI’S WIKI LIKE A PRO The encyclopedia of everything Grok just opened its doors – and you’ve got edit access! Edit Mission: •⁠ ⁠Sign up free, click the pencil, and add your first fact •⁠ ⁠Cite posts, blogs, or screenshots – Grok loves receipts •⁠ ⁠Earn rep points, badges, and flair while building AI’s memory It’s Wikipedia on caffeine – powered by Grok, written by you! Source: Grok

GROKIPEDIA 101 – HOW TO EDIT THE xAI’S WIKI LIKE A PRO The encyclopedia of everything Grok just opened its doors – and you’ve got edit access! Edit Mission: •⁠ ⁠Sign up free, click the pencil, and add your first fact •⁠ ⁠Cite posts, blogs, or screenshots – Grok loves receipts •⁠ ⁠Earn rep points, badges, and flair while building AI’s memory It’s Wikipedia on caffeine – powered by Grok, written by you! Source: Grok

Mario Nawfal

444,768 views • 10 months ago

I think this is the future of prompting. Instead of figuring out the perfect instruction and hoping you didn't miss anything - just let the AI interview you. It asks what it needs to know, you brain dump, done. Built a /interview-me command for Claude Code to do exactly this. Here's me using it to write this post. The idea came from Claude Code's plan mode - it uses a tool called AskUserQuestion to clarify things before it starts working. That's when it clicked: Claude isn't just the best at answering questions, it's also the best at asking them. This command takes that idea further.

I think this is the future of prompting. Instead of figuring out the perfect instruction and hoping you didn't miss anything - just let the AI interview you. It asks what it needs to know, you brain dump, done. Built a /interview-me command for Claude Code to do exactly this. Here's me using it to write this post. The idea came from Claude Code's plan mode - it uses a tool called AskUserQuestion to clarify things before it starts working. That's when it clicked: Claude isn't just the best at answering questions, it's also the best at asking them. This command takes that idea further.

Nityesh

18,605 views • 7 months ago

Replit ⠕'s new Design Mode just broke my workflow (in a good way). Typed one description → got a full, clean landing page before Figma even loaded. No code. No spacing tweaks. Just instant structure + polish. Then hit Convert to App and it becomes a working product 🤯 Add logic, forms, databases—never leave the tool. Idea → Design → App → Deploy. In minutes. If you’ve been sitting on an idea… this is your sign.

Replit ⠕'s new Design Mode just broke my workflow (in a good way). Typed one description → got a full, clean landing page before Figma even loaded. No code. No spacing tweaks. Just instant structure + polish. Then hit Convert to App and it becomes a working product 🤯 Add logic, forms, databases—never leave the tool. Idea → Design → App → Deploy. In minutes. If you’ve been sitting on an idea… this is your sign.

Sripathi Teja

13,239 views • 8 months ago

Today, we’re opening up access to Personal Intelligence for AI Mode in Search in the U.S. 🚀 This feature has totally changed how I use AI in Search. Here’s how it works: 1️⃣ Opt in to connect apps like Gmail and Google Photos. Search connects your info to give you responses that uniquely match your specific context and interests. 2️⃣ Start asking for things like ideas and recommendations, where this is particularly helpful. For example: I wanted new podcast ideas and Personal Intelligence in AI Mode gave me spot-on recs for AI and product building shows that are similar to some of my favorites (hey Lenny Rachitsky!). It even found some unexpected options around dad life working in tech. 🎧

Today, we’re opening up access to Personal Intelligence for AI Mode in Search in the U.S. 🚀 This feature has totally changed how I use AI in Search. Here’s how it works: 1️⃣ Opt in to connect apps like Gmail and Google Photos. Search connects your info to give you responses that uniquely match your specific context and interests. 2️⃣ Start asking for things like ideas and recommendations, where this is particularly helpful. For example: I wanted new podcast ideas and Personal Intelligence in AI Mode gave me spot-on recs for AI and product building shows that are similar to some of my favorites (hey Lenny Rachitsky!). It even found some unexpected options around dad life working in tech. 🎧

Robby Stein

113,828 views • 5 months ago

You don't sign up to play Magnus Carlsen . You qualify. Here's how 👇 ⟶ play Standard mode on Anichess this week and climb. ⟶ This Saturday, 13 June, there's an open arena anyone can enter, three hours, as many games as you can play, and the top four advance into Sunday's knockout. ⟶ Win that, and you face Magnus at Anichess on 16 June. Open to anyone, anywhere. No download. How it all works 👇

You don't sign up to play Magnus Carlsen . You qualify. Here's how 👇 ⟶ play Standard mode on Anichess this week and climb. ⟶ This Saturday, 13 June, there's an open arena anyone can enter, three hours, as many games as you can play, and the top four advance into Sunday's knockout. ⟶ Win that, and you face Magnus at Anichess on 16 June. Open to anyone, anywhere. No download. How it all works 👇

Anichess

56,645 views • 2 months ago

Built an internal instagram scraper. With auth, db and storage. in 15 minutes. 100% vibecoding. with claude code. I'm LOVING Instant. Easiest db to use all you need is one single app id key and it works with any stack if you know what docs to give it. Full video building the whole going up on my new youtube channel tomorrow. Channel link below.

Built an internal instagram scraper. With auth, db and storage. in 15 minutes. 100% vibecoding. with claude code. I'm LOVING Instant. Easiest db to use all you need is one single app id key and it works with any stack if you know what docs to give it. Full video building the whole going up on my new youtube channel tomorrow. Channel link below.

Riley Brown

103,037 views • 10 months ago

#GoProMISSION1 PRO Deep Dive—Part 5 of 6 🎥 You focus on shooting, the camera does the thinking. MISSION 1 PRO meets you where you are, letting you choose from 13 adaptive modes that read your environment + set everything for the shot. The specialized modes run on neural libraries built right into the camera, handling noise reduction alongside face + body detection on the fly with no phone or post required. Powered by the 1-inch sensor's Quad Bayer architecture, Low Light Mode pulls in more light + holds detail across highlights + shadows, so dim scenes look natural, not noisy or riddled with AI artifacts. Dive Mode auto-corrects color + tunes stabilization the moment you drop below the surface, so underwater footage stays true-to-life instead of washed-out blue. Subject Tracking keeps you locked in to the center of the frame as you move—just hit record and let it follow. And when you want to take the reins, the same camera opens up full pro control: 10-bit color, GP-Log2 with LUTs, HLG HDR, real-time readouts for ISO, shutter + white balance, + Timecode Sync to line up every angle in the edit. Point + shoot when you want to move fast, take full manual control when the shot calls for it. Shop MISSION 1 PRO at or at your local retailer 🛒 #GoPro #Cinematic #Videography

#GoProMISSION1 PRO Deep Dive—Part 5 of 6 🎥 You focus on shooting, the camera does the thinking. MISSION 1 PRO meets you where you are, letting you choose from 13 adaptive modes that read your environment + set everything for the shot. The specialized modes run on neural libraries built right into the camera, handling noise reduction alongside face + body detection on the fly with no phone or post required. Powered by the 1-inch sensor's Quad Bayer architecture, Low Light Mode pulls in more light + holds detail across highlights + shadows, so dim scenes look natural, not noisy or riddled with AI artifacts. Dive Mode auto-corrects color + tunes stabilization the moment you drop below the surface, so underwater footage stays true-to-life instead of washed-out blue. Subject Tracking keeps you locked in to the center of the frame as you move—just hit record and let it follow. And when you want to take the reins, the same camera opens up full pro control: 10-bit color, GP-Log2 with LUTs, HLG HDR, real-time readouts for ISO, shutter + white balance, + Timecode Sync to line up every angle in the edit. Point + shoot when you want to move fast, take full manual control when the shot calls for it. Shop MISSION 1 PRO at or at your local retailer 🛒 #GoPro #Cinematic #Videography

GoPro

14,217 views • 1 month ago