Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

My evaluation lecture! I walk you through different evaluation eras I've been a part of, from prompting GPT-3 as elaborate autocomplete to today's complex agentic sandboxes (I expand on agentic more than any other topic, drawing on Florian Brand's insights). This lecture is a birds eye view of how... show more

Nathan Lambert

98,640 subscribers

39,123 görüntüleme • 1 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Anthropic engineer just released a 2-hour workshop on "Graph Engineering" for agentic systems: “80% of our engineers are using self-improving loops. Now everyone is building agentic graphs.” • 00:00 - Introduction to RAG & Graphs • 06:39 - Core of "Graph Engineering" (state, nodes) • 14:29 - 3 feedback loops of Graph agents • 23:06 - Agent evaluation with Graphs • 36:29 - Agent cycles in graphs • 1:15:22 - Agentic RAG & agent context • 1:41:20 - Evaluation datasets based on Graphs This 2-hour workshop will replace 10 paid courses on agentic engineering. Watch it today, then learn how to become a Graph Engineer in the article below.

Anthropic engineer just released a 2-hour workshop on "Graph Engineering" for agentic systems: “80% of our engineers are using self-improving loops. Now everyone is building agentic graphs.” • 00:00 - Introduction to RAG & Graphs • 06:39 - Core of "Graph Engineering" (state, nodes) • 14:29 - 3 feedback loops of Graph agents • 23:06 - Agent evaluation with Graphs • 36:29 - Agent cycles in graphs • 1:15:22 - Agentic RAG & agent context • 1:41:20 - Evaluation datasets based on Graphs This 2-hour workshop will replace 10 paid courses on agentic engineering. Watch it today, then learn how to become a Graph Engineer in the article below.

Codez

400,915 görüntüleme • 1 ay önce

Lecture 11 is a tool-use/function calling/agentic 101! I almost skipped this one, as this chapter started as the only skill-specific topic in the book, but since writing it tool-use has only become more foundational to modern models. This is a tour from the basics -- why LLMs need tools -- to some of the cutting edge challenges scaling agentic RL. Of course, there's plenty of history and fundamentals along the way. Personally, I'm excited to get much more deeply into this area as a researcher again soon. Just a few more lectures left, but I'll likely keep making a few more videos now that I have pipelines that are lightweight and fun. 00:00 Introduction & Motivations 07:29 Part 1: Why Language Models Need Tools (+ related work) 15:30 Part 2: Infra - How Tool Calls Actually Work 24:17 Part 3: Training for Tool Use & OpenThoughts-Agent 36:38 Takeaways Thanks for watching & sharing questions.

Lecture 11 is a tool-use/function calling/agentic 101! I almost skipped this one, as this chapter started as the only skill-specific topic in the book, but since writing it tool-use has only become more foundational to modern models. This is a tour from the basics -- why LLMs need tools -- to some of the cutting edge challenges scaling agentic RL. Of course, there's plenty of history and fundamentals along the way. Personally, I'm excited to get much more deeply into this area as a researcher again soon. Just a few more lectures left, but I'll likely keep making a few more videos now that I have pipelines that are lightweight and fun. 00:00 Introduction & Motivations 07:29 Part 1: Why Language Models Need Tools (+ related work) 15:30 Part 2: Infra - How Tool Calls Actually Work 24:17 Part 3: Training for Tool Use & OpenThoughts-Agent 36:38 Takeaways Thanks for watching & sharing questions.

Nathan Lambert

43,949 görüntüleme • 1 ay önce

The final lecture of my course is an intro to character training! This is a topic that I've been quietly very invested in for ~18 months, as it: * Has potential for high real world impact * Clearly used extensively at frontier labs * Almost no empirical literature exists * More accessible on academic compute This lecture covers what character training is, reviews model specs, constitutions, the differences, the motivations in real world events, some example research papers I like, and open questions in how it relates to post-training/model use generally. Hopefully this brings more people into the field (and reach out if you have questions). It is one of the more research-y chapters in my book, but one that I felt needed the reference. There is still so little, educational content on the topic online. 0:00 Intro 6:22 Part 1: Fundamentals — character, constitutions, and model specs 19:21 Part 2: Character training in practice 23:23 Part 3: Character elicitation without gradient steps 28:03 Part 4: Open questions (and the end of the course) 32:27 The course, complete Thanks for watching. No need to like and subscribe now that the course is done, you definitely wouldn't! h/t to Sharan for leading the technical work I got to do in the space, and Zafir Stojanovski for investing a lot of attention at this book chapter.

The final lecture of my course is an intro to character training! This is a topic that I've been quietly very invested in for ~18 months, as it: * Has potential for high real world impact * Clearly used extensively at frontier labs * Almost no empirical literature exists * More accessible on academic compute This lecture covers what character training is, reviews model specs, constitutions, the differences, the motivations in real world events, some example research papers I like, and open questions in how it relates to post-training/model use generally. Hopefully this brings more people into the field (and reach out if you have questions). It is one of the more research-y chapters in my book, but one that I felt needed the reference. There is still so little, educational content on the topic online. 0:00 Intro 6:22 Part 1: Fundamentals — character, constitutions, and model specs 19:21 Part 2: Character training in practice 23:23 Part 3: Character elicitation without gradient steps 28:03 Part 4: Open questions (and the end of the course) 32:27 The course, complete Thanks for watching. No need to like and subscribe now that the course is done, you definitely wouldn't! h/t to Sharan for leading the technical work I got to do in the space, and Zafir Stojanovski for investing a lot of attention at this book chapter.

Nathan Lambert

57,041 görüntüleme • 1 ay önce

NEW Greylock Change Agents: Evaluating Agents with Braintrust There's been a lot of discourse around evals recently, so it's timely to drop the recording of Change Agents with Ankur Goyal on the topic of how he thinks about Evaluating Agents. Timestamps: (0:00) - Intro (1:22) - Building Braintrust (5:19) - Evaluating agentic systems (11:04) - Experimentation with evals (13:18) - Adopting evals (17:09) - Evals and complex agents (21:19) - Custom scoring (25:02) - LLM as a judge (26:44) - Human-manual evaluation (30:07) - How the best in-class teams manage evals (33:57) - Future of evals for agents (37:38 ) - Audience Q&A

NEW Greylock Change Agents: Evaluating Agents with Braintrust There's been a lot of discourse around evals recently, so it's timely to drop the recording of Change Agents with Ankur Goyal on the topic of how he thinks about Evaluating Agents. Timestamps: (0:00) - Intro (1:22) - Building Braintrust (5:19) - Evaluating agentic systems (11:04) - Experimentation with evals (13:18) - Adopting evals (17:09) - Evals and complex agents (21:19) - Custom scoring (25:02) - LLM as a judge (26:44) - Human-manual evaluation (30:07) - How the best in-class teams manage evals (33:57) - Future of evals for agents (37:38 ) - Audience Q&A

Corinne Marie Riley

12,743 görüntüleme • 11 ay önce

one thing that has saved my projects more time than I can count is evals boy was I excited when florian, quite literally an expert in benchmarks, agreed to hop into a ~2h interview to do a walkthrough of what the eval landscape looks like in 2026 (and also answer my personal business questions on the subject) given that now running frontier model through benchmarks is a vector for hacking other systems in order to avoid doing work (looking at you sol), I think it's more important than ever to educate folks on the evals situation. had a lot of fun throughout this session and I hope that you learn a thing or two! enjoy! 🌹 table of content: 0:00:00: are AI Benchmark broken? 0:05:45: Florian Brand background 0:09:00: what motivates florian to work on evaluation? 0:13:33: what is the mirrorcode benchmark about? 0:18:20: cheating in agent benchmark is insaneeeee 0:24:08: LLM benchmarks in era of agents 0:26:30: what’s up with the pelican man 0:28:27: evals are about capabilities 0:31:46: components of running evals 0:35:30: the volume of things to audit is huge!!! 0:40:20: expert answers are wrong hahahaha 0:46:00: api providers aren’t the same 0:48:00: benchmark narrow capabilities (synthetically) 0:50:56: link between eval and environment 0:53:45: small validated benchmark or massive bench? 0:56:11: what is your flow to review a benchmark? 0:58:30: tracking work capabilities with evaluation 1:00:20: slide deck in industry is all vibecoded 1:03:30: harness impact in the evaluation 1:07:39: hardware/sandboxes impact evaluation too! 1:11:00: “is it going to get worse?” 1:12:40: all components influence the final score 1:13:50: training models on different harnesses? 1:17:20: is the model just the weights or it’s all of it? 1:19:30: how to craft benchmark that prevent to cheating and undereliciting models in 2026 1:23:19: ways agents cheat and steal 1:26:00: correct elicitation of capabilities is important 1:36:00: building evaluation on prime intellect 1:45:10: how do you design interactivity benchmarks? 1:48:40: do you think evals are well set to reflect real world performance? 1:52:50: what will the benchmarking landscape will look like in 1 year

Yacine Mahdid

12,923 görüntüleme • 1 ay önce

Anthropic engineer: "At Antropic, >80% of our engineers are building with self-improving loops. in 3-6 months, it will be 100%. my agentic loops can run for hours without spending hundreds of $$$." in 40-minute lecture, an Anthropic engineer shows how to build 4 types of agentic loops from scratch. Worth more than a $500 agentic course on the internet. Watch it now, then read how quants are building trading loops from scratch.

Anthropic engineer: "At Antropic, >80% of our engineers are building with self-improving loops. in 3-6 months, it will be 100%. my agentic loops can run for hours without spending hundreds of $$$." in 40-minute lecture, an Anthropic engineer shows how to build 4 types of agentic loops from scratch. Worth more than a $500 agentic course on the internet. Watch it now, then read how quants are building trading loops from scratch.

Movez

107,020 görüntüleme • 1 ay önce

Anthropic engineer: “80% of our engineers are using self-improving loops. Now everyone is exploring how to build the right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of building agents.” In this 40-minute lecture, an Anthropic engineer shows how to build a self-improving agentic workflow from scratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Anthropic engineer: “80% of our engineers are using self-improving loops. Now everyone is exploring how to build the right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of building agents.” In this 40-minute lecture, an Anthropic engineer shows how to build a self-improving agentic workflow from scratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Movez

21,136 görüntüleme • 1 ay önce

The real power of AI agents is collaboration. Box CTO Ben Kus joins LangChain CEO Harrison Chase to discuss what the future looks like when AI systems can work more like teammates than just assistants. Timestamps: 00:52 - Harrison's path to starting LangChain 01:54 - The different definitions of AI agents 03:16 - How agentic systems differ from traditional automation 06:20 - The evolution of AI agents 13:06 - The impact of deep research 17:22 - Deep agent capabilities and benefits 22:16 - How to recognize different modes 25:25 - The future of evaluation

The real power of AI agents is collaboration. Box CTO Ben Kus joins LangChain CEO Harrison Chase to discuss what the future looks like when AI systems can work more like teammates than just assistants. Timestamps: 00:52 - Harrison's path to starting LangChain 01:54 - The different definitions of AI agents 03:16 - How agentic systems differ from traditional automation 06:20 - The evolution of AI agents 13:06 - The impact of deep research 17:22 - Deep agent capabilities and benefits 22:16 - How to recognize different modes 25:25 - The future of evaluation

Box

54,980 görüntüleme • 9 ay önce

You’re wasting insane amounts of money on all of your agentic workflows. I calculated the cost, it is staggering. You could be saving over 100x in tokens by changing the workflow’s orchestration loop by just adding one extra step into your agentic workflow setup. This completely changes the economics of deploying agentic systems for both simple and complex agentic workflows. I am writing an article on this right now to teach you how to do it so you can save money on your agentic workflows. Errrrrm… back to typing I guess? Turn my notifications on as I’m aiming to post it later on tonight. Speak to you shortly.

You’re wasting insane amounts of money on all of your agentic workflows. I calculated the cost, it is staggering. You could be saving over 100x in tokens by changing the workflow’s orchestration loop by just adding one extra step into your agentic workflow setup. This completely changes the economics of deploying agentic systems for both simple and complex agentic workflows. I am writing an article on this right now to teach you how to do it so you can save money on your agentic workflows. Errrrrm… back to typing I guess? Turn my notifications on as I’m aiming to post it later on tonight. Speak to you shortly.

hoeem

16,427 görüntüleme • 3 ay önce

"I don't think anybody out there wants to walk in Coach Caldwell's or mine shoes." "We're not here to be good. Good will get you fired." "Before you go criticizing coaches... on social media, you come walk in their shoes." "Other than their parents, nobody loves them more than I do." "The film don't lie." Vic Schaefer was asked about how the team responded to his evaluation after their loss to Vanderbilt. This is just part of his response!!

"I don't think anybody out there wants to walk in Coach Caldwell's or mine shoes." "We're not here to be good. Good will get you fired." "Before you go criticizing coaches... on social media, you come walk in their shoes." "Other than their parents, nobody loves them more than I do." "The film don't lie." Vic Schaefer was asked about how the team responded to his evaluation after their loss to Vanderbilt. This is just part of his response!!

Paige Dauer

120,838 görüntüleme • 6 ay önce

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,593 görüntüleme • 6 ay önce

Where do autoraters break down? Arena researchers Li Chen and I-Hung Hsu walk through how they'd build an autorater from scratch — different kinds of autoraters, training objectives, what dimensions actually matter to rate on — then get into what makes it hard in practice: preference drift, multi-turn evaluation, tie threshold variance, and the gap between LLM-as-a-judge and real human subjectivity. Watch on YouTube to see the whiteboard details (link in 🧵 thread) 0:00 Evaluation granularity: general vs. per-category vs. per-response 2:05 Applications of autoraters as RL reward signals and test-time scaling 3:03 Output design for pairwise autorater: scores, comparison, and ties 4:03 Verbal and visual feedback autoraters 4:48 Training for pairwise autorater: Bradley-Terry loss, threshold design 9:43 Real-world challenges: preference shifts over time 10:30 Multi-turn autorating and usage simulation 11:35 Tie threshold variance across annotators 12:18 Long-context evaluation challenges 13:02 Confidence intervals and score uncertainty 14:00 Why LLM-as-a-judge fails to capture subjective human preference 15:20 The private information unobservable in human evaluation 16:14 Model evolved to be stronger makes training data harder 17:08 Signal vs. noise in human preference data 18:04 How do you autorate an autorater?

Where do autoraters break down? Arena researchers Li Chen and I-Hung Hsu walk through how they'd build an autorater from scratch — different kinds of autoraters, training objectives, what dimensions actually matter to rate on — then get into what makes it hard in practice: preference drift, multi-turn evaluation, tie threshold variance, and the gap between LLM-as-a-judge and real human subjectivity. Watch on YouTube to see the whiteboard details (link in 🧵 thread) 0:00 Evaluation granularity: general vs. per-category vs. per-response 2:05 Applications of autoraters as RL reward signals and test-time scaling 3:03 Output design for pairwise autorater: scores, comparison, and ties 4:03 Verbal and visual feedback autoraters 4:48 Training for pairwise autorater: Bradley-Terry loss, threshold design 9:43 Real-world challenges: preference shifts over time 10:30 Multi-turn autorating and usage simulation 11:35 Tie threshold variance across annotators 12:18 Long-context evaluation challenges 13:02 Confidence intervals and score uncertainty 14:00 Why LLM-as-a-judge fails to capture subjective human preference 15:20 The private information unobservable in human evaluation 16:14 Model evolved to be stronger makes training data harder 17:08 Signal vs. noise in human preference data 18:04 How do you autorate an autorater?

Arena.ai

20,757 görüntüleme • 4 ay önce

99% of AI engineers still don't know about Claude skills. Andrew Ng just dropped a 2 hour course with Anthropic on building AI agentic skills from scratch. • 00:00 - build agentic skills with Claude • 22:29 - Claude pre-built skills • 41:04 - skills vs MCP and subagents • 1:06:03 - skills for long running agents • 1:51:59 - live demo to build agentic skills Prompting is dead. Claude skills is how top engineers build AI agents now. I watched it last night. Halfway through, I realized I have been using Claude completely wrong for years. Bookmark this and read the article below.

99% of AI engineers still don't know about Claude skills. Andrew Ng just dropped a 2 hour course with Anthropic on building AI agentic skills from scratch. • 00:00 - build agentic skills with Claude • 22:29 - Claude pre-built skills • 41:04 - skills vs MCP and subagents • 1:06:03 - skills for long running agents • 1:51:59 - live demo to build agentic skills Prompting is dead. Claude skills is how top engineers build AI agents now. I watched it last night. Halfway through, I realized I have been using Claude completely wrong for years. Bookmark this and read the article below.

Roan

22,509 görüntüleme • 1 ay önce

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

elvis

79,795 görüntüleme • 8 ay önce

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Movez

16,545 görüntüleme • 1 ay önce

Jongin talking about Kyungsoo during his live with Na PD Na: after u discharged who did u met? 🐻: other than my members, I dont met anyone Na: did u met Kyungsoo? 🐻: ofc I met him, we hv a meal tgt recently Na: then did Kyungsoo said smth (abt ur cb)? 🐻: the funny things about kyungsoo hyung is he watched my contents Na: really? He looks like he walks around as if he doesn't care abt the world 🐻: I also surprised! He's really looking after my contents. And the next thing is he's always give an evaluation Na: 🤣🤣🤣 really? 🐻: yes! I never asked for an evaluation Na: oh I never saw that kind of side of Kyungsoo tho.. then what kind of evaluation did he gave? Then did he gave an evaluation abt that (Wait on Me) MV too? 🐻: no, not yet bc it's just released ytd, he hasn't gave any evaluation. But he gave an evaluation abt Adult Swim Na: oh adult swim? 🐻: yes, he suddenly video called me, I was thought "oh I think D.O. hyung is bored" Na: 🤣🤣🤣🤣 oh he can be bored ofc 🐻: so he called me within this angle (put his phone under his face) usually people would put his phone in front of their face right? But he did that so I could see his chin. So at first I was like "what is this? Hyung, why?". So he asked me "how u've been doing?" So I said "I'm fine while doing my scheds" then he said "I saw that!" Na: he said he watched yours (mv) 🐻: yes. So I asked "really? How is it?" Then he said "oh, it's good tho? U dance well!". But he also ever gave me a cold evaluation before Na: what's the song that he gave u a cold evaluation? 🐻: I didnt rmb the exact song, but he saw one of the song and said "jongin-ah u need to show ur dance more here" Na: 🤣😂🤣😂 like he even dance 🐻: he doesn't even dance on his own mv😆 Na: when he's only sing (on his mv) 🐻: he just hold an antenna during Blossom but when he saw my MV he said "u need to show ur dance more" but that's a sharp point Na: but that's about hving colleagues, right? He knows what his colleagues are good at 🐻: but I like it when D.O. hyung is giving me an evaluation. Bc he said the right thing. Yes, he said the right thing and I can feel it as well. Even tho it's better if he gave more detail like how should I dance. But he only said "I need to show my dance more" so I asked "then hyung how should I dance?" Na: *jokingly imitates the phone call got off* 🐻: I supposed to get more feedback, right? But theres no much feedback Na: so he asked u to dance with ur own feeling? 🐻: but when he saw Adult Swim he said "it's good" so I had that pleasure like- I was got recognized by this person🤣 that's bc he always gave an evaluation on every album like he's an album critic Na: I think you become a bit tame 🐻: yes I think so Na: oh it's fun to rcvd a sharp evaluation fr a colleagues, and Kyungsoo gave a good evaluation for Adult Swim

Jongin talking about Kyungsoo during his live with Na PD Na: after u discharged who did u met? 🐻: other than my members, I dont met anyone Na: did u met Kyungsoo? 🐻: ofc I met him, we hv a meal tgt recently Na: then did Kyungsoo said smth (abt ur cb)? 🐻: the funny things about kyungsoo hyung is he watched my contents Na: really? He looks like he walks around as if he doesn't care abt the world 🐻: I also surprised! He's really looking after my contents. And the next thing is he's always give an evaluation Na: 🤣🤣🤣 really? 🐻: yes! I never asked for an evaluation Na: oh I never saw that kind of side of Kyungsoo tho.. then what kind of evaluation did he gave? Then did he gave an evaluation abt that (Wait on Me) MV too? 🐻: no, not yet bc it's just released ytd, he hasn't gave any evaluation. But he gave an evaluation abt Adult Swim Na: oh adult swim? 🐻: yes, he suddenly video called me, I was thought "oh I think D.O. hyung is bored" Na: 🤣🤣🤣🤣 oh he can be bored ofc 🐻: so he called me within this angle (put his phone under his face) usually people would put his phone in front of their face right? But he did that so I could see his chin. So at first I was like "what is this? Hyung, why?". So he asked me "how u've been doing?" So I said "I'm fine while doing my scheds" then he said "I saw that!" Na: he said he watched yours (mv) 🐻: yes. So I asked "really? How is it?" Then he said "oh, it's good tho? U dance well!". But he also ever gave me a cold evaluation before Na: what's the song that he gave u a cold evaluation? 🐻: I didnt rmb the exact song, but he saw one of the song and said "jongin-ah u need to show ur dance more here" Na: 🤣😂🤣😂 like he even dance 🐻: he doesn't even dance on his own mv😆 Na: when he's only sing (on his mv) 🐻: he just hold an antenna during Blossom but when he saw my MV he said "u need to show ur dance more" but that's a sharp point Na: but that's about hving colleagues, right? He knows what his colleagues are good at 🐻: but I like it when D.O. hyung is giving me an evaluation. Bc he said the right thing. Yes, he said the right thing and I can feel it as well. Even tho it's better if he gave more detail like how should I dance. But he only said "I need to show my dance more" so I asked "then hyung how should I dance?" Na: jokingly imitates the phone call got off 🐻: I supposed to get more feedback, right? But theres no much feedback Na: so he asked u to dance with ur own feeling? 🐻: but when he saw Adult Swim he said "it's good" so I had that pleasure like- I was got recognized by this person🤣 that's bc he always gave an evaluation on every album like he's an album critic Na: I think you become a bit tame 🐻: yes I think so Na: oh it's fun to rcvd a sharp evaluation fr a colleagues, and Kyungsoo gave a good evaluation for Adult Swim

(slow) 귀여운 복쯍아🍑

114,712 görüntüleme • 1 yıl önce

FREE sinus lecture today!! In honor of the FREE sinus lecture I am giving today to promote the Radiopaedia.org 2025 conference, here is a little sample of sinus anatomy!! Lecture is today at 2pm EST!! Here is the link Honestly, I get more engagement from my sinus lectures than I do from my brain lectures!! Everyone has to read them but no one really teaches them! If you are watching this after June 13, 2025 you can still watch it on demand at the Radiopaedia YouTube channel!

FREE sinus lecture today!! In honor of the FREE sinus lecture I am giving today to promote the Radiopaedia.org 2025 conference, here is a little sample of sinus anatomy!! Lecture is today at 2pm EST!! Here is the link Honestly, I get more engagement from my sinus lectures than I do from my brain lectures!! Everyone has to read them but no one really teaches them! If you are watching this after June 13, 2025 you can still watch it on demand at the Radiopaedia YouTube channel!

Lea Alhilali, MD

24,308 görüntüleme • 1 yıl önce

[#SDF] 〈1:1 시그니처 안무 대중 평가〉 안내 지금부터 〈1:1 시그니처 안무 대중 평가〉가 시작됩니다. 유튜브 The CHOOM 채널에서 각 안무가들의 뉴 시그니처 안무를 평가해주세요 📍투표 기간 ~ 5/21(목) 8:00 AM (KST) 📍투표 방법 ① 유튜브 The CHOOM 채널에서 ‘뉴 시그니처 안무 평가 영상’ 시청하기 ② 뉴 시그니처 안무가 오리지널 안무보다 더 뛰어나다면 ‘뉴 시그니처 안무 평가 영상‘에 '좋아요' 누르기 📍유의사항 • 평가 점수는 유튜브 The CHOOM 채널에 게시된 평가 영상의 '좋아요' 수로 산정됩니다. • ‘오리지널 시그니처 안무 영상’은 평가 영상이 아닙니다. ‘뉴 시그니처 안무 평가’를 위한 참고 영상입니다. 안무가들의 디렉 전쟁 〈스트릿 월드 파이터 : 디렉터스 워〉 2026.08 COMING SOON _ 〈1:1 Signature Move Public Evaluation〉 Announcement 〈1:1 Signature Move Public Evaluation〉 begins NOW. Please evaluate each choreographer's new signature move on YouTube channel The CHOOM. 📍Voting Period ~ May 21 (Thur) 8:00 AM (KST) 📍How to Vote ① Watch 'The New Signature Move Evaluation Video' on YouTube Channel 'The CHOOM’. ② If the new signature move stands out more than the original move, please 'Like' 'The New Signature Move Evaluation Video'. 📍Notes • Evaluation Scores will be calculated based on the number of 'Likes' on the evaluation videos posted on YouTube channel The CHOOM. • 'The Original Signature Move Video' is NOT an evaluation video. It is a reference video for 'The New Signature Move Evaluation'. Choreographers’ Directing Battle 〈STREET WORLD FIGHTER : Directors' War〉 2026.08 COMING SOON #스트릿월드파이터_디렉터스워 #스디파 #엠넷 #댄스 #StreetWorldFighter_DirectorsWar #Mnet #Dance

[#SDF] 〈1:1 시그니처 안무 대중 평가〉 안내 지금부터 〈1:1 시그니처 안무 대중 평가〉가 시작됩니다. 유튜브 The CHOOM 채널에서 각 안무가들의 뉴 시그니처 안무를 평가해주세요 📍투표 기간 ~ 5/21(목) 8:00 AM (KST) 📍투표 방법 ① 유튜브 The CHOOM 채널에서 ‘뉴 시그니처 안무 평가 영상’ 시청하기 ② 뉴 시그니처 안무가 오리지널 안무보다 더 뛰어나다면 ‘뉴 시그니처 안무 평가 영상‘에 '좋아요' 누르기 📍유의사항 • 평가 점수는 유튜브 The CHOOM 채널에 게시된 평가 영상의 '좋아요' 수로 산정됩니다. • ‘오리지널 시그니처 안무 영상’은 평가 영상이 아닙니다. ‘뉴 시그니처 안무 평가’를 위한 참고 영상입니다. 안무가들의 디렉 전쟁 〈스트릿 월드 파이터 : 디렉터스 워〉 2026.08 COMING SOON _ 〈1:1 Signature Move Public Evaluation〉 Announcement 〈1:1 Signature Move Public Evaluation〉 begins NOW. Please evaluate each choreographer's new signature move on YouTube channel The CHOOM. 📍Voting Period ~ May 21 (Thur) 8:00 AM (KST) 📍How to Vote ① Watch 'The New Signature Move Evaluation Video' on YouTube Channel 'The CHOOM’. ② If the new signature move stands out more than the original move, please 'Like' 'The New Signature Move Evaluation Video'. 📍Notes • Evaluation Scores will be calculated based on the number of 'Likes' on the evaluation videos posted on YouTube channel The CHOOM. • 'The Original Signature Move Video' is NOT an evaluation video. It is a reference video for 'The New Signature Move Evaluation'. Choreographers’ Directing Battle 〈STREET WORLD FIGHTER : Directors' War〉 2026.08 COMING SOON #스트릿월드파이터_디렉터스워 #스디파 #엠넷 #댄스 #StreetWorldFighter_DirectorsWar #Mnet #Dance

Mnet

61,656 görüntüleme • 3 ay önce

🚨Elon Musk:“In 6-12 months GrokBot will be the #1 tool for building agentic systems. In a year, 100% of code will be written by LLMs.” At SpaceXAI, more than 70% of engineers are already using GrokBot to build self-learning agentic systems. In a 40-minute talk, Elon sits down with SpaceXAI engineers and discusses what the future of AI engineering is really going to look like.This conversation is honestly worth more than 2 hours of any Stanford lecture on AI engineering. Watch it today, then go read the article below on how to build a full Grok bot agents team from scratch. Who’s ready to see the future of AI engineering from the people actually building it?

🚨Elon Musk:“In 6-12 months GrokBot will be the #1 tool for building agentic systems. In a year, 100% of code will be written by LLMs.” At SpaceXAI, more than 70% of engineers are already using GrokBot to build self-learning agentic systems. In a 40-minute talk, Elon sits down with SpaceXAI engineers and discusses what the future of AI engineering is really going to look like.This conversation is honestly worth more than 2 hours of any Stanford lecture on AI engineering. Watch it today, then go read the article below on how to build a full Grok bot agents team from scratch. Who’s ready to see the future of AI engineering from the people actually building it?

Hosna ⚖️ בניטה

16,111 görüntüleme • 15 gün önce