正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I knew K2.6 will be this strong, but I had doubts they'll open source it. Because this is it, the Big League, the frontier. This is our standard test of building a basic HTML ASCII roguelike, then evolving it in three steps (step 2: topdown/isometric, step 3: full voxel... show more

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)

71,652 subscribers

86,700 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

One year ago, I unveiled LugandaGPT. Today, it’s open for you to test. We have a long road ahead, but I’m inspired knowing this is the worst it will ever be. It only gets better from here. Step by step, we are breaking down language barriers.

One year ago, I unveiled LugandaGPT. Today, it’s open for you to test. We have a long road ahead, but I’m inspired knowing this is the worst it will ever be. It only gets better from here. Step by step, we are breaking down language barriers.

Felix Kitaka

35,367 次观看 • 7 个月前

⚡ First-step speed is trainable. It is not just “be quicker”. It is body position, timing, the push into the ground, and the first two steps. This is the detail that wins the moment. Full programme:

⚡ First-step speed is trainable. It is not just “be quicker”. It is body position, timing, the push into the ground, and the first two steps. This is the detail that wins the moment. Full programme:

Joner Football

15,325 次观看 • 4 个月前

Markdown was doomed from the start. It's just a format with low information density. HTML is better for humans, and agents can now consume and produce it without issues. But nobody wants to type HTML, so here is an alternative: This is an open-source tool for generating dashboards from data without writing a single HTML tag. You define your dashboard in YAML or TSK, and the tool will serve the HTML file for you. It comes with skills for Claude Code and Codex, so they know how to build these dashboards. And you can connect this to Postgres, MySQL, Snowflake, BigQuery, Redshift, Databricks, and many other databases. Repo link below.

Markdown was doomed from the start. It's just a format with low information density. HTML is better for humans, and agents can now consume and produce it without issues. But nobody wants to type HTML, so here is an alternative: This is an open-source tool for generating dashboards from data without writing a single HTML tag. You define your dashboard in YAML or TSK, and the tool will serve the HTML file for you. It comes with skills for Claude Code and Codex, so they know how to build these dashboards. And you can connect this to Postgres, MySQL, Snowflake, BigQuery, Redshift, Databricks, and many other databases. Repo link below.

Santiago

86,565 次观看 • 4 个月前

Our container is on it's way to India from China. It has 5 products we will Build in Bharat. It has everything: - moulds - machines - parts - racks etc. But to be honest: It hurts that so much still had to come from China. So we’re fixing it step by step. Every shipment from China must be reduced - 40’HQ container this time - 20’ container next time The final goal is clear: Export 40’HQ containers from Bharat to the world. It’s time for the tide to turn.

Our container is on it's way to India from China. It has 5 products we will Build in Bharat. It has everything: - moulds - machines - parts - racks etc. But to be honest: It hurts that so much still had to come from China. So we’re fixing it step by step. Every shipment from China must be reduced - 40’HQ container this time - 20’ container next time The final goal is clear: Export 40’HQ containers from Bharat to the world. It’s time for the tide to turn.

Prakash Dadlani

32,139 次观看 • 7 个月前

I’m excited to announce a new course with DeepLearning.AI - Building Agentic RAG 💫 In this course, you’ll learn how to build a research assistant that can reason over multiple documents and answer complex questions. You’ll also learn how to step through the execution of the agent and steer it with human feedback. This represents a big step beyond any standard RAG pipeline, which is mostly good for simple questions over a small set of documents. Learn the layers first and then put them together: ✅ Routing ✅ Tool Use ✅ Multi-step reasoning with Memory ✅ Tool retrieval ✅ Debugging + user input Check it out!

I’m excited to announce a new course with DeepLearning.AI - Building Agentic RAG 💫 In this course, you’ll learn how to build a research assistant that can reason over multiple documents and answer complex questions. You’ll also learn how to step through the execution of the agent and steer it with human feedback. This represents a big step beyond any standard RAG pipeline, which is mostly good for simple questions over a small set of documents. Learn the layers first and then put them together: ✅ Routing ✅ Tool Use ✅ Multi-step reasoning with Memory ✅ Tool retrieval ✅ Debugging + user input Check it out!

Jerry Liu

76,298 次观看 • 2 年前

I made this step by step video for a friend who is going to use PlusLife for the first time and figured I’d share it here as well. PlusLife is a nucleic acid amplification test for the detection of SARS-CoV-2 and other viruses. More info about it here:

I made this step by step video for a friend who is going to use PlusLife for the first time and figured I’d share it here as well. PlusLife is a nucleic acid amplification test for the detection of SARS-CoV-2 and other viruses. More info about it here:

A. 🇵🇭🇪🇸🏳️‍🌈😷🍉💜

22,088 次观看 • 1 年前

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

codila

11,581 次观看 • 2 个月前

I just shipped the JS Endpoint Extractor in rep+. It grabs endpoints from captured JS and shows them in a clean table (UI still needs work). Next step is letting you fuzz them with different methods and maybe even extract possible params from the js code. Not ready yet, but I think this will be super useful. Would love to hear your techniques so I can get inspired and build this the right way !

I just shipped the JS Endpoint Extractor in rep+. It grabs endpoints from captured JS and shows them in a clean table (UI still needs work). Next step is letting you fuzz them with different methods and maybe even extract possible params from the js code. Not ready yet, but I think this will be super useful. Would love to hear your techniques so I can get inspired and build this the right way !

Bour Abdelhadi

11,339 次观看 • 10 个月前

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was *especially* amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was especially amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!

Peter Bakkum

144,441 次观看 • 2 年前

Using Claude in Chrome product. Prompt: replicate this image (my profile picture) in jspaint, use brushes to replicate it as closely as possible. I want you to use brushes and clicking. Do not use javascript tool, but the final result has to be very close to this image. DO NOT CHEAT 1. I specified the do not use javascript tool because otherwise it uses javascript and it is faster but it seems like people cared more about clicking :D 2. The task took 45 minutes, but I don't think it's that much slower than competitors 😄 3. Prompt is important. (See thread)

Kiana Ehsani

404,430 次观看 • 10 天前

Kimi K3 vs GPT 5.6 Sol (extra high) Voxel Death Star trench run I do want to point out that this was supposed to be a static world, but when I gave this prompt to Kimi K3, it said: “Since I can't output raster images, I've done something better: a real-time, fully animated voxel rendering of the assault in a single HTML file. —” So this ended up being an animated competition The way I would subjectively score it is that GPT 5.6 had a better lighting/effects but K3s was much smoother. You can definitely tell open source is getting really good.

Kimi K3 vs GPT 5.6 Sol (extra high) Voxel Death Star trench run I do want to point out that this was supposed to be a static world, but when I gave this prompt to Kimi K3, it said: “Since I can't output raster images, I've done something better: a real-time, fully animated voxel rendering of the assault in a single HTML file. —” So this ended up being an animated competition The way I would subjectively score it is that GPT 5.6 had a better lighting/effects but K3s was much smoother. You can definitely tell open source is getting really good.

Chris

50,121 次观看 • 2 个月前

Neil on open source v. frontier models: "The labs pay an immense premium to be 3-6 months ahead of everything else. I think that's probably still worth it. But I don't know that the premium is going to last that long. If you look at enterprise deployments, they don't move at three to six month speed. A lot of enterprises are probably still on Opus 4.6 or Opus 4.7. I don't think there's any way to call a winner in this race, and certainly I don't even think this is a race that can be decided ever. It's a continual process. I don't think open source ever goes away. If there's a vacuum because one leader steps out, a new leader will step in. It just gets easier every day to train a frontier class model."

Neil on open source v. frontier models: "The labs pay an immense premium to be 3-6 months ahead of everything else. I think that's probably still worth it. But I don't know that the premium is going to last that long. If you look at enterprise deployments, they don't move at three to six month speed. A lot of enterprises are probably still on Opus 4.6 or Opus 4.7. I don't think there's any way to call a winner in this race, and certainly I don't even think this is a race that can be decided ever. It's a continual process. I don't think open source ever goes away. If there's a vacuum because one leader steps out, a new leader will step in. It just gets easier every day to train a frontier class model."

Patrick OShaughnessy

32,180 次观看 • 26 天前

Sam Altman, CEO of OpenAI: "GPT 5.6 is 54% more efficient on agentic coding, and it's still the best on the market for half the cost." AI spend has never mattered as much as it does today. As a result the models keep getting better and cheaper at the same time. This is going to widen the gap between the people using AI agents and everyone else, because now it's not just powerful, it's cheap. That's exactly why i wrote a full step by step guide on agents, what they are and how to build your own from scratch. Read it below.

Sam Altman, CEO of OpenAI: "GPT 5.6 is 54% more efficient on agentic coding, and it's still the best on the market for half the cost." AI spend has never mattered as much as it does today. As a result the models keep getting better and cheaper at the same time. This is going to widen the gap between the people using AI agents and everyone else, because now it's not just powerful, it's cheap. That's exactly why i wrote a full step by step guide on agents, what they are and how to build your own from scratch. Read it below.

Anatoli Kopadze

91,858 次观看 • 2 个月前

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems In this 15-minute workshop, he shows exactly how to build one from scratch AI → Agents → Harness → Loops → Graphs step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter Anthropic calls this "dreaming" Most people spend weeks building this by hand You don't have to Bookmark and watch it Then read the full harness engineering guide below ↓

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems In this 15-minute workshop, he shows exactly how to build one from scratch AI → Agents → Harness → Loops → Graphs step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter Anthropic calls this "dreaming" Most people spend weeks building this by hand You don't have to Bookmark and watch it Then read the full harness engineering guide below ↓

rari

183,635 次观看 • 18 天前

We are the middle of an authoritarian takeover. It's not too late to stop it. But we're short on time. It's important we see beyond the daily outrage and understand Trump's coordinated step-by-step plan. In this video, I lay it out for you. You need to know it to fight it.

We are the middle of an authoritarian takeover. It's not too late to stop it. But we're short on time. It's important we see beyond the daily outrage and understand Trump's coordinated step-by-step plan. In this video, I lay it out for you. You need to know it to fight it.

Chris Murphy 🟧

105,911 次观看 • 11 个月前

🇺🇸🇨🇱Truck Talk🇨🇱🇺🇸 I Told you PDJT Already had a deal and it was already done. But there still was going to be some more stuff get blown up. All part of the plan/show. DON’T BE A PANICAN. Everything is planned and being carried out step by step by the plan. This was all decided long ago. I told you it was going to be like this and it has. So stop worrying about it and stand in your peace. God has got it. 1000% The Military has always been the way. They are in control completely so do listen to the naysayers and the doomers. Why because they are full of S*it. Be the lighthouse God has prepared you to be. More to come. Capt Capt Kyle

🇺🇸🇨🇱Truck Talk🇨🇱🇺🇸 I Told you PDJT Already had a deal and it was already done. But there still was going to be some more stuff get blown up. All part of the plan/show. DON’T BE A PANICAN. Everything is planned and being carried out step by step by the plan. This was all decided long ago. I told you it was going to be like this and it has. So stop worrying about it and stand in your peace. God has got it. 1000% The Military has always been the way. They are in control completely so do listen to the naysayers and the doomers. Why because they are full of S*it. Be the lighthouse God has prepared you to be. More to come. Capt Capt Kyle

Capt Kyle

12,026 次观看 • 3 个月前

Reporter: Who is paying for the cost of this war? Will the Arab countries step up? Leavitt: I think it is something the president would be quite interested in calling them to do. Certainly, it's an idea I know he has and something you will hear more from him on

Reporter: Who is paying for the cost of this war? Will the Arab countries step up? Leavitt: I think it is something the president would be quite interested in calling them to do. Certainly, it's an idea I know he has and something you will hear more from him on

Acyn

328,849 次观看 • 5 个月前

THE S&P 500 RALLY HAS NO BUYERS I know what you're thinking - "but the price is going up" That's exactly the trap When the market rallies on dead volume, it's not buyers pushing it higher It's the absence of sellers. Two completely different things Here's how it works: Step 1: low volume rally - you're looking at it right now Step 2: volume returns, but it's not buying Step 3: the part that makes you wish you sold at step 1 I'm not in this rally. And I'm not changing my mind until volume confirms it FOLLOW + NOTIFS ON!

THE S&P 500 RALLY HAS NO BUYERS I know what you're thinking - "but the price is going up" That's exactly the trap When the market rallies on dead volume, it's not buyers pushing it higher It's the absence of sellers. Two completely different things Here's how it works: Step 1: low volume rally - you're looking at it right now Step 2: volume returns, but it's not buying Step 3: the part that makes you wish you sold at step 1 I'm not in this rally. And I'm not changing my mind until volume confirms it FOLLOW + NOTIFS ON!

bee🐝

130,780 次观看 • 4 个月前

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 次观看 • 2 个月前