Loading video...

Video Failed to Load

Go Home

. M2 uses "interleaved thinking" - instead of one thinking block at the start, you get multiple thinking blocks throughout a single request. The model re-evaluates its approach as it goes, adapting based on tool outputs and new information. You'll see these thinking blocks appear in the UI showing...

cline's profile picture

Cline

72,528 subscribers

53,426 views • 9 months 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

The fastest provider for kimi-k2-thinking <now in Cline>
0:34

The fastest provider for kimi-k2-thinking <now in Cline>

Cline

41,284 views • 9 months ago

the "thinking" text Claude shows you is not its thinking it's the part it chose to write down the real reasoning runs in a layer you never see Anthropic just proved it we learned to read the output and never noticed we were reading the summary
1:05

the "thinking" text Claude shows you is not its thinking it's the part it chose to write down the real reasoning runs in a layer you never see Anthropic just proved it we learned to read the output and never noticed we were reading the summary

Lagosaur

31,172 views • 1 month ago

Grok 3 introduced a very compelling Thinking UX. Super elegant approach for showing reasoning in real-time, and gives the user a ton of confidence in what's happening. Give the designer a raise.
0:25

Grok 3 introduced a very compelling Thinking UX. Super elegant approach for showing reasoning in real-time, and gives the user a ton of confidence in what's happening. Give the designer a raise.

Aaron Levie

1,423,751 views • 1 year ago

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:
0:30

Google drops Gemini 2.0 Flash Thinking a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more now available in anychat, try it out:

AK

141,723 views • 1 year ago

You know that "But, wait..." moment in every LLM thinking trace? I made it visible. I asked 8 models the same tricky probability question and rendered their reasoning as trees. Every time a model rejects its own idea and pivots, every "But...", every "Wait, actually...", a new branch grows. Same question. Completely different minds.
0:20

You know that "But, wait..." moment in every LLM thinking trace? I made it visible. I asked 8 models the same tricky probability question and rendered their reasoning as trees. Every time a model rejects its own idea and pivots, every "But...", every "Wait, actually...", a new branch grows. Same question. Completely different minds.

stevibe

86,683 views • 1 month ago

"It's normally a player speeding up and thinking about the transfer, thinking about a throw before the catch and not staying fully through the process one thing at a time." It's a simple concept, but one that can eliminate countless errors on routine plays. When runners get on base, players often want to speed everything up. The best defenders do the opposite. They stay present, complete the catch, and trust the process one step at a time. Watch the full presentation at or in the My ABCA app!
1:24

"It's normally a player speeding up and thinking about the transfer, thinking about a throw before the catch and not staying fully through the process one thing at a time." It's a simple concept, but one that can eliminate countless errors on routine plays. When runners get on base, players often want to speed everything up. The best defenders do the opposite. They stay present, complete the catch, and trust the process one step at a time. Watch the full presentation at or in the My ABCA app!

ABCA

15,552 views • 2 months ago

The rain in Spain falls mainly….as a deluge. Murcia earlier today. And on it goes, floods in one country, blistering heatwaves in the next. That’s what the #ClimateEmergency looks like, and no amount of political wishful thinking will make it go away.
1:34

The rain in Spain falls mainly….as a deluge. Murcia earlier today. And on it goes, floods in one country, blistering heatwaves in the next. That’s what the #ClimateEmergency looks like, and no amount of political wishful thinking will make it go away.

John Gibbons 🇵🇸

73,395 views • 2 years ago

WORK IN PROGRESS #99 - OUR LAUNCHPAD UI 🔳 This weeks WIP looks at some of the design thinking behind our launchpad UI with some behind the scenes looks at our character creator and process. Episode #100 next week...big one 👀 Let us know if you like what you see ⬇️
0:52

WORK IN PROGRESS #99 - OUR LAUNCHPAD UI 🔳 This weeks WIP looks at some of the design thinking behind our launchpad UI with some behind the scenes looks at our character creator and process. Episode #100 next week...big one 👀 Let us know if you like what you see ⬇️

Youmio

16,885 views • 1 year ago

GLM 4.6 fans! just soared to the top as the fastest provider in Artificial Analysis for the model. > a 114 TPS and <0.18s TTFT. > That's 2x faster than the next best option on both metrics. Available now in Cline.
0:21

GLM 4.6 fans! just soared to the top as the fastest provider in Artificial Analysis for the model. > a 114 TPS and <0.18s TTFT. > That's 2x faster than the next best option on both metrics. Available now in Cline.

Cline

31,584 views • 10 months ago

.Yutori's Co-CEO Devi Parikh on why she left Meta to start her company with Abhishek Das. “We are rethinking what the interface with the web looks like, and that requires a certain sort of… thinking from first principles, thinking from scratch, thinking from a clean slate…” “That's just much harder to do in a larger company that has all of the baggage associated with it from its prior success.” Watch the full episode on
0:40

.Yutori's Co-CEO Devi Parikh on why she left Meta to start her company with Abhishek Das. “We are rethinking what the interface with the web looks like, and that requires a certain sort of… thinking from first principles, thinking from scratch, thinking from a clean slate…” “That's just much harder to do in a larger company that has all of the baggage associated with it from its prior success.” Watch the full episode on

The Information

11,043 views • 11 months ago

Releasing Cline CLI 2.0! Part of the Cline open-source project trusted by 5M+ developers. Redesigned terminal UI, parallel agents, ACP integration (use Cline in Zed, Neovim, e/plugins , and emacs), and free Kimi.ai Kimi K2.5! Read what’s new 👇
0:48

Releasing Cline CLI 2.0! Part of the Cline open-source project trusted by 5M+ developers. Redesigned terminal UI, parallel agents, ACP integration (use Cline in Zed, Neovim, e/plugins , and emacs), and free Kimi.ai Kimi K2.5! Read what’s new 👇

Cline

30,314 views • 6 months ago

Jensen Huang doesn’t use AI to think less. He uses it to think past his own limits. Huang: “90% of my instructions are actually conflated with questions.” The man running a five trillion dollar company doesn’t give AI commands. He interrogates it. Huang: “I take the answer from one AI, give it to the other AI, ask them to critique itself.” Same question. Multiple models. Pit them against each other. Keep only what survives. Not because the machine can’t be trusted. Because challenging it is where the sharpest thinking happens. Huang: “The process of critiquing, criticizing the answers, applying your critical thinking, enhances cognitive skills.” AI doesn’t replace your thinking. It demands more of it than you’ve ever given. Every question takes reasoning. Every answer takes scrutiny. The machine isn’t thinking for you. It’s pulling thinking out of you that didn’t exist before you sat down. Huang: “In order to formulate good questions, you have to be thinking, you have to be analytical, you have to be reasoning yourself.” AI is not the shortcut everyone thinks it is. It is the most powerful cognitive amplifier ever built. It sharpens the engaged. It leaves the passive exactly where they started. Same tool. Same access. The only variable is what you bring to it. The world is debating whether AI will replace human thinking. Wrong conversation. The real question is what happens when a tool built to think for you becomes the thing that forces you to think beyond yourself. That’s not a threat to humanity. That’s the entire point.
1:30

Jensen Huang doesn’t use AI to think less. He uses it to think past his own limits. Huang: “90% of my instructions are actually conflated with questions.” The man running a five trillion dollar company doesn’t give AI commands. He interrogates it. Huang: “I take the answer from one AI, give it to the other AI, ask them to critique itself.” Same question. Multiple models. Pit them against each other. Keep only what survives. Not because the machine can’t be trusted. Because challenging it is where the sharpest thinking happens. Huang: “The process of critiquing, criticizing the answers, applying your critical thinking, enhances cognitive skills.” AI doesn’t replace your thinking. It demands more of it than you’ve ever given. Every question takes reasoning. Every answer takes scrutiny. The machine isn’t thinking for you. It’s pulling thinking out of you that didn’t exist before you sat down. Huang: “In order to formulate good questions, you have to be thinking, you have to be analytical, you have to be reasoning yourself.” AI is not the shortcut everyone thinks it is. It is the most powerful cognitive amplifier ever built. It sharpens the engaged. It leaves the passive exactly where they started. Same tool. Same access. The only variable is what you bring to it. The world is debating whether AI will replace human thinking. Wrong conversation. The real question is what happens when a tool built to think for you becomes the thing that forces you to think beyond yourself. That’s not a threat to humanity. That’s the entire point.

Dustin

19,849 views • 1 month ago

Pass this on to anyone in Ireland thinking of voting for any of the three muppets currently up for President. A barrister of real integrity and a woman of substance in every way, Tracey O'Mahony gave an excellent speech at "Rebels Across the Pond" recently, and here it is in its entirety.
17:49

Pass this on to anyone in Ireland thinking of voting for any of the three muppets currently up for President. A barrister of real integrity and a woman of substance in every way, Tracey O'Mahony gave an excellent speech at "Rebels Across the Pond" recently, and here it is in its entirety.

Mark Attwood

36,071 views • 10 months ago

Ordinary thinking is not yet spiritual. •Everyday thinking is automatic, associative, reactive •True thinking is consciously directed, self-sustained Most people don’t actually think —they are thought by their habits, culture, and impulses. ⸻ Thinking can become a spiritual organ: •It is the most controllable part of the soul •Unlike emotions or instincts, you can train it directly When purified, thinking becomes: •Clear •Quiet •Intentional At that point, it stops being personal noise and becomes a perceptive faculty—almost like a sense organ for truth. ⸻ Discipline is the doorway. —Knowledge of the Higher Worlds and Its Attainment, exercises: •Hold a single, simple thought (e.g., a pin, a seed) •Keep attention on it without drifting •Return to it again and again, without irritation This builds what he calls inner steadiness. ⸻ 4. Why thinking—not feelings—comes first This is where Dr Steiner differs from modern “spirituality”: •Feelings are unstable and subjective •Thinking can become exact, lawful, and reliable Only after thinking is trained does he say you can trust: •Imagination •Intuition •Spiritual perception Otherwise, you risk illusion. ⸻ 5. The turning point At a certain stage: •Thinking becomes silent but awake •You are no longer chasing thoughts—you are holding awareness itself That’s where, for Dr Steiner, spirituality actually begins—not in beliefs, not in vibes, but in mastered attention.
0:36

Ordinary thinking is not yet spiritual. •Everyday thinking is automatic, associative, reactive •True thinking is consciously directed, self-sustained Most people don’t actually think —they are thought by their habits, culture, and impulses. ⸻ Thinking can become a spiritual organ: •It is the most controllable part of the soul •Unlike emotions or instincts, you can train it directly When purified, thinking becomes: •Clear •Quiet •Intentional At that point, it stops being personal noise and becomes a perceptive faculty—almost like a sense organ for truth. ⸻ Discipline is the doorway. —Knowledge of the Higher Worlds and Its Attainment, exercises: •Hold a single, simple thought (e.g., a pin, a seed) •Keep attention on it without drifting •Return to it again and again, without irritation This builds what he calls inner steadiness. ⸻ 4. Why thinking—not feelings—comes first This is where Dr Steiner differs from modern “spirituality”: •Feelings are unstable and subjective •Thinking can become exact, lawful, and reliable Only after thinking is trained does he say you can trust: •Imagination •Intuition •Spiritual perception Otherwise, you risk illusion. ⸻ 5. The turning point At a certain stage: •Thinking becomes silent but awake •You are no longer chasing thoughts—you are holding awareness itself That’s where, for Dr Steiner, spirituality actually begins—not in beliefs, not in vibes, but in mastered attention.

Zherka

14,134 views • 4 months ago

You can’t make this sh*t up!🤣🤣🤣 TikTok account has uploaded multiple AI-generated videos showing people supposedly regretting their vote for the current administration and crying over losing their benefits. The kicker? Leftists—like the one with the big eyes—used one of these videos in a Stitch, going on a rant and mocking the AI characters, thinking the clips were real.
0:53

You can’t make this sh*t up!🤣🤣🤣 TikTok account has uploaded multiple AI-generated videos showing people supposedly regretting their vote for the current administration and crying over losing their benefits. The kicker? Leftists—like the one with the big eyes—used one of these videos in a Stitch, going on a rant and mocking the AI characters, thinking the clips were real.

I Meme Therefore I Am 🇺🇸

64,438 views • 9 months ago

o1 is more powerful than most people think! Many people forget how important and powerful o1 is because they don't think about what's behind it. Basically, it is the assumption that earned Daniel Kahneman the Nobel Prize, namely the way we think. Today's LLMs only have intuitive thinking, so-called system 1 thinking. This means that the answer follows almost immediately - in the same way that token generation follows probability. System 2 thinking, on the other hand, is long thinking. Reasoning in o1 works in the same way as solving a difficult math problem by dividing the approach into processes or trying out new approaches. There has never been anything like it! And it's much more than just CoT prompting! I have no doubt that this will lead us to AGI in the long term. Noam Brown is a genius and he explains it in an excellent way.
0:56

o1 is more powerful than most people think! Many people forget how important and powerful o1 is because they don't think about what's behind it. Basically, it is the assumption that earned Daniel Kahneman the Nobel Prize, namely the way we think. Today's LLMs only have intuitive thinking, so-called system 1 thinking. This means that the answer follows almost immediately - in the same way that token generation follows probability. System 2 thinking, on the other hand, is long thinking. Reasoning in o1 works in the same way as solving a difficult math problem by dividing the approach into processes or trying out new approaches. There has never been anything like it! And it's much more than just CoT prompting! I have no doubt that this will lead us to AGI in the long term. Noam Brown is a genius and he explains it in an excellent way.

Chubby♨️

413,435 views • 1 year ago

Continuing my hobby dev project. Now the Meta Quest’s depth data can be streamed remotely together with position and orientation to visualize the surrounding structure in real time. I am thinking of new ideas based on this, so feel free to share yours. #metaquest3 #madewithunity
0:47

Continuing my hobby dev project. Now the Meta Quest’s depth data can be streamed remotely together with position and orientation to visualize the surrounding structure in real time. I am thinking of new ideas based on this, so feel free to share yours. #metaquest3 #madewithunity

Takashi Yoshinaga

107,741 views • 9 months ago