Загрузка видео...

Не удалось загрузить видео

На главную

someone submitted a pr that added "beast prompt" to opencode for gpt models it makes 4.1 actually good at tool calling look how fast this thing goes, video not sped up

thdxr's profile picture

dax

136,511 subscribers

80,952 просмотров • 1 год назад •via X (Twitter)

Наука и технологииИгрыОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

this is not sped up. Cognition SWE-1.6 is just moving fast enough that the interaction feels like a different product category the nice thing about a model this fast is you stop treating it like a task runner and start treating it like something you can actually riff with!
0:19

this is not sped up. Cognition SWE-1.6 is just moving fast enough that the interaction feels like a different product category the nice thing about a model this fast is you stop treating it like a task runner and start treating it like something you can actually riff with!

nader dabit

12,807 просмотров • 2 месяцев назад

Most people don’t get much out of ChatGPT & AI. Why? because they treat it like a Google search. This GPT-4.1 prompting guide shows you how to treat ChatGPT like an operator — not a google search bar. – Covers prompt design, formatting & role instructions – Works for n8n ai agents, workflows, content, research – Zero fluff. All tactical examples – Built for GPT-4.1+ capabilities – Free PDF — no paywall, no email grab Follow + Repost + Reply “Prompt” & I’ll DM it to you (no strings/free).
0:17

Most people don’t get much out of ChatGPT & AI. Why? because they treat it like a Google search. This GPT-4.1 prompting guide shows you how to treat ChatGPT like an operator — not a google search bar. – Covers prompt design, formatting & role instructions – Works for n8n ai agents, workflows, content, research – Zero fluff. All tactical examples – Built for GPT-4.1+ capabilities – Free PDF — no paywall, no email grab Follow + Repost + Reply “Prompt” & I’ll DM it to you (no strings/free).

Damian Player

1,878,155 просмотров • 1 год назад

🚀 New Video Alert – GPT-5 in Copilot Studio! GPT-5 has officially arrived in Microsoft Copilot Studio, and I couldn’t resist putting it to the test. In this video, I explore: 🔍 GPT-5 Auto & GPT-5 Reasoning models for custom agents. 🛠 How I leveraged GPT-5 Chat inside a custom prompt for more tailored outputs. ⚖️ GPT-5 Chat Vs. GPT-4.1 to highlight improvements and trade-offs If you’ve been wondering what GPT-5 brings to Copilot Studio—this video is packed with real examples, practical tests, and insights to help you understand what these new experimental models have to offer. 🎥 Watch here: #CopilotStudio #GPT5 #AIBuilder #MicrosoftCopilot #LowCodeAI #OpenAI #AI #CopilotStudio #GPT5Auto #GPT5Reasoning #GPT5Chat
0:16

🚀 New Video Alert – GPT-5 in Copilot Studio! GPT-5 has officially arrived in Microsoft Copilot Studio, and I couldn’t resist putting it to the test. In this video, I explore: 🔍 GPT-5 Auto & GPT-5 Reasoning models for custom agents. 🛠 How I leveraged GPT-5 Chat inside a custom prompt for more tailored outputs. ⚖️ GPT-5 Chat Vs. GPT-4.1 to highlight improvements and trade-offs If you’ve been wondering what GPT-5 brings to Copilot Studio—this video is packed with real examples, practical tests, and insights to help you understand what these new experimental models have to offer. 🎥 Watch here: #CopilotStudio #GPT5 #AIBuilder #MicrosoftCopilot #LowCodeAI #OpenAI #AI #CopilotStudio #GPT5Auto #GPT5Reasoning #GPT5Chat

Daniel Christian

14,705 просмотров • 11 месяцев назад

The aurora last night in Beaver, Alaska was just incredible. This is a real-time video (not sped up) of the crazy motion I saw. Also, look how BRIGHT it is, wow!
0:18

The aurora last night in Beaver, Alaska was just incredible. This is a real-time video (not sped up) of the crazy motion I saw. Also, look how BRIGHT it is, wow!

Vincent Ledvina

27,255 просмотров • 5 месяцев назад

There are so many models that it can get confusing so today we launched an auto-router - you get the best answers from any of the top models. At the same time, we have AI experts and model enthusiasts who will enjoy access to 10 new models we just added including: ✅ GPT-4.1 ✅ o3 & o4 Mini ✅ Grok 3 ✅ Llama 4 Maverick & Scout We're also sunsetting some older models that just can't keep up anymore.
0:10

There are so many models that it can get confusing so today we launched an auto-router - you get the best answers from any of the top models. At the same time, we have AI experts and model enthusiasts who will enjoy access to 10 new models we just added including: ✅ GPT-4.1 ✅ o3 & o4 Mini ✅ Grok 3 ✅ Llama 4 Maverick & Scout We're also sunsetting some older models that just can't keep up anymore.

Richard Socher

24,731 просмотров • 1 год назад

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in
0:11

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in

raymel 👋

37,196 просмотров • 1 месяц назад

THIS GUY VIBE CODED A FREE TOOL THAT TURNS UGLY BARCODES INTO BEAUTIFUL SVG ONES THAT STILL SCAN you paste in a barcode, and it turns it into a styled, artistic SVG that still scans perfectly the tool makes it look good AND keeps it scannable free, no account needed, AND they export as SVGs if you've ever looked at a barcode on your product packaging and thought "this is ugly" you might want to look into this
0:17

THIS GUY VIBE CODED A FREE TOOL THAT TURNS UGLY BARCODES INTO BEAUTIFUL SVG ONES THAT STILL SCAN you paste in a barcode, and it turns it into a styled, artistic SVG that still scans perfectly the tool makes it look good AND keeps it scannable free, no account needed, AND they export as SVGs if you've ever looked at a barcode on your product packaging and thought "this is ugly" you might want to look into this

Om Patel

330,429 просмотров • 3 месяцев назад

I built a custom SORA 2 GPT that writes prompts like a creative director. It turns rough ideas into realistic prompts Sora actually understands: -Exact prompt structure Sora wants -Camera angles & movements -Lighting setups for each scene -How much detail to give without killing creativity This thing breaks your concept into real cinematography language. Like, rt + reply "SORA" and I'll send it (must be following)
0:15

I built a custom SORA 2 GPT that writes prompts like a creative director. It turns rough ideas into realistic prompts Sora actually understands: -Exact prompt structure Sora wants -Camera angles & movements -Lighting setups for each scene -How much detail to give without killing creativity This thing breaks your concept into real cinematography language. Like, rt + reply "SORA" and I'll send it (must be following)

Damian Player

33,720 просмотров • 9 месяцев назад

World-class highway… until you actually drive on it. You paid tolls for this experience. Reality delivered. Look how Audi almost goes for a toss. Thanks to Nitin Gadkari ji
0:10

World-class highway… until you actually drive on it. You paid tolls for this experience. Reality delivered. Look how Audi almost goes for a toss. Thanks to Nitin Gadkari ji

Deadly Kalesh

667,132 просмотров • 12 дней назад

There’s some subtle details here that make v4 standout from v3. (My prompt engine) One is the audio, there is a subtle distortion that this mic has that my prompt engine picked up on naturally. It’s really crazy how fast it continues to improve. v5 is scheduled for May 🥳✌️
0:18

There’s some subtle details here that make v4 standout from v3. (My prompt engine) One is the audio, there is a subtle distortion that this mic has that my prompt engine picked up on naturally. It’s really crazy how fast it continues to improve. v5 is scheduled for May 🥳✌️

Franky Shaw

21,865 просмотров • 5 месяцев назад

GPT Image 2 + Seedance 2.0 Prompt Share Created on mitte.ai I used the generic Seedance 2.0 storyboard-to-video prompt again, without any additional details. To get this style, I added an environment reference created in Midjourney. Without that reference image, it generates a stylized 3D version. You can check the prompts in the comments.
0:14

GPT Image 2 + Seedance 2.0 Prompt Share Created on mitte.ai I used the generic Seedance 2.0 storyboard-to-video prompt again, without any additional details. To get this style, I added an environment reference created in Midjourney. Without that reference image, it generates a stylized 3D version. You can check the prompts in the comments.

Kōda

37,854 просмотров • 1 месяц назад

“Look at us, Hann! Look at it, look at that! We did it! Took us 23 years but we did it.” The fact that Hann is the one he always goes up to for this, because Hann’s the one who asked him to be in the band… it gets me every time 😭
0:10

“Look at us, Hann! Look at it, look at that! We did it! Took us 23 years but we did it.” The fact that Hann is the one he always goes up to for this, because Hann’s the one who asked him to be in the band… it gets me every time 😭

Marta ⎕

45,030 просмотров • 1 год назад

🎬Comparing AI video models with no prompt: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 3 times with no text prompt. I chose my favorite results, below. Sometimes I test certain images with no prompt to see how creative the models can be. Take a look at the results, but don't just focus on how much movement there is - pay attention to what is actually moving. The fog/mist adds to the dramatic effect:
0:10

🎬Comparing AI video models with no prompt: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 3 times with no text prompt. I chose my favorite results, below. Sometimes I test certain images with no prompt to see how creative the models can be. Take a look at the results, but don't just focus on how much movement there is - pay attention to what is actually moving. The fog/mist adds to the dramatic effect:

Heather Cooper

29,138 просмотров • 1 год назад

🚨NEW THE UK INTRODUCES DIGITAL I.D. The petition to scrap this idea is already almost at a million signatures! Watch HOW FAST it goes up every time it refreshes (every 10 seconds)!
0:13

🚨NEW THE UK INTRODUCES DIGITAL I.D. The petition to scrap this idea is already almost at a million signatures! Watch HOW FAST it goes up every time it refreshes (every 10 seconds)!

Tablesalt 🇨🇦🇺🇸

50,779 просмотров • 9 месяцев назад

I meant it ... for real... I generated those 3 videos to show you what we can do now with a simple prompt they're not perfect but good enough with a bit of editing the seedance 2 credits allowance seems quite generous the more AI makes huge leaps like this... the more it became unforgivable to not make $10K a month ps: I'm not sponsored by higgsfield I'm shared a cool tool - that's it
0:15

I meant it ... for real... I generated those 3 videos to show you what we can do now with a simple prompt they're not perfect but good enough with a bit of editing the seedance 2 credits allowance seems quite generous the more AI makes huge leaps like this... the more it became unforgivable to not make $10K a month ps: I'm not sponsored by higgsfield I'm shared a cool tool - that's it

David Attias

75,602 просмотров • 3 месяцев назад

whenever this video comes up i think about how someone tweeted that it looks like he’s fighting for his life on a crowded london tube
0:16

whenever this video comes up i think about how someone tweeted that it looks like he’s fighting for his life on a crowded london tube

౨ৎ abbie ⎕

4,031,237 просмотров • 2 лет назад

Frame mogged to oblivion 💀 This is GPT 5.4 not even pro.. In all seriousness these are videos of older models — this video was readily available so I thought it would be fun to compare how much we’ve improved in less than a year!
0:18

Frame mogged to oblivion 💀 This is GPT 5.4 not even pro.. In all seriousness these are videos of older models — this video was readily available so I thought it would be fun to compare how much we’ve improved in less than a year!

Chris

250,557 просмотров • 4 месяцев назад

seedance 2.0 + my v2 AI UGC prompting system is giving insane results i spent the last 24 hours generating over 200 seedance 2.0 videos to figure out the best prompting framework system for AI UGC this video was made with 1 prompt and 1 tool, no editing was done to the video this was just a prompt to a video this is by far the best model i've ever used and the craziest part is that it can be fully automated this is the first time we can actually automate high quality ai ugc at this level bytedance owns tiktok so this model is trained on millions of high quality ugc videos. you just need to know how to extract that and call it in your prompt. we are so early... it's insane
0:14

seedance 2.0 + my v2 AI UGC prompting system is giving insane results i spent the last 24 hours generating over 200 seedance 2.0 videos to figure out the best prompting framework system for AI UGC this video was made with 1 prompt and 1 tool, no editing was done to the video this was just a prompt to a video this is by far the best model i've ever used and the craziest part is that it can be fully automated this is the first time we can actually automate high quality ai ugc at this level bytedance owns tiktok so this model is trained on millions of high quality ugc videos. you just need to know how to extract that and call it in your prompt. we are so early... it's insane

Miko

81,141 просмотров • 5 месяцев назад

Elite body control on this inside move. Really good for guys who sit to pitch. Not a balk. Slow it down & look at it.
0:10

Elite body control on this inside move. Really good for guys who sit to pitch. Not a balk. Slow it down & look at it.

Jerry Weinstein

227,050 просмотров • 3 лет назад