Загрузка видео...

Не удалось загрузить видео

На главную

Prompting GPT-5 is different. In the examples below, optimized prompts: • Cut runtime by 1s • Dropped memory use 3,626 KB → 577 KB • Boosted code quality • Improved robustness (0.32→0.54) • Increased context grounding (0.80→0.95) We built a prompt migrator + optimizer so you don’t need to...

edwinarbus's profile picture

edwin

30,632 subscribers

269,129 просмотров • 10 месяцев назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:
21:52

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:

Alex Finn

19,155 просмотров • 10 месяцев назад

GPT-5 vs Grok-4 exact same prompts, wildly different output in web lmarena
0:59

GPT-5 vs Grok-4 exact same prompts, wildly different output in web lmarena

Lisan al Gaib

567,727 просмотров • 11 месяцев назад

The biggest Claude Code hack nobody talks about: Meta-prompts Basically you use AI to create prompts, skills, commands or agents → AI prompting AI → Saves me hours every week Example: a skill that creates skills See the exact prompt below:
1:07

The biggest Claude Code hack nobody talks about: Meta-prompts Basically you use AI to create prompts, skills, commands or agents → AI prompting AI → Saves me hours every week Example: a skill that creates skills See the exact prompt below:

Melvyn • Builder

76,360 просмотров • 5 месяцев назад

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.
0:35

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.

Cline

72,096 просмотров • 7 месяцев назад

Use AI in every app on Mac, enriched by context from the app you're in. Generate replies in Gmail, summarise your Slack, or let GPT fill out the contents of a web form! Try it now for the best (and cheapest) way to use GPT-4!
0:47

Use AI in every app on Mac, enriched by context from the app you're in. Generate replies in Gmail, summarise your Slack, or let GPT fill out the contents of a web form! Try it now for the best (and cheapest) way to use GPT-4!

Michael Jelly 🏴‍☠️

2,550,763 просмотров • 2 лет назад

factory cli now lets you choose a different model for plan mode and execute mode when you switch modes, the model changes too. my go-to right now: plan: gpt-5-high code: gpt-5-codex (auto)
0:21

factory cli now lets you choose a different model for plan mode and execute mode when you switch modes, the model changes too. my go-to right now: plan: gpt-5-high code: gpt-5-codex (auto)

Ian Nuttall

27,156 просмотров • 8 месяцев назад

GPT-5 is 25x cheaper than GPT-4 at launch It raced to billions of tokens/minute within 2 hours of launch I talked to OpenAI's Olivier Godement about: • GPT-5, gpt-oss, and OpenAI's release strategy • How open-source models solve the enterprise puzzle • The fastest tech adoption in recent memory Check out our full conversation below:
57:14

GPT-5 is 25x cheaper than GPT-4 at launch It raced to billions of tokens/minute within 2 hours of launch I talked to OpenAI's Olivier Godement about: • GPT-5, gpt-oss, and OpenAI's release strategy • How open-source models solve the enterprise puzzle • The fastest tech adoption in recent memory Check out our full conversation below:

Zain Kahn

438,660 просмотров • 9 месяцев назад

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.
0:29

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.

Kōda

10,616 просмотров • 1 месяц назад

Stop paying for 5 different AI subscriptions. ChatLLM by Abacus AI puts GPT-5.5, Claude 4.7, Gemini 3.1, DeepSeek-V4, Kimi-2.6 in one place. One prompt → routed to the best model → output. Pay once. Use all of them.
0:35

Stop paying for 5 different AI subscriptions. ChatLLM by Abacus AI puts GPT-5.5, Claude 4.7, Gemini 3.1, DeepSeek-V4, Kimi-2.6 in one place. One prompt → routed to the best model → output. Pay once. Use all of them.

Abacus.AI

26,747,516 просмотров • 1 месяц назад

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️
1:24

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️

Arena.ai

246,337 просмотров • 6 месяцев назад

OpenAI researcher, Michelle Pokrass: the challenge in building GPT‑5 is finding the right balance between reasoning and conversation. o3 thinks hard, but it isn't ideal for casual chat. GPT‑4.1 improved at coding by sacrificing some chit-chat quality. now, the goal is to train a model that knows when to think hard and when to talk
0:45

OpenAI researcher, Michelle Pokrass: the challenge in building GPT‑5 is finding the right balance between reasoning and conversation. o3 thinks hard, but it isn't ideal for casual chat. GPT‑4.1 improved at coding by sacrificing some chit-chat quality. now, the goal is to train a model that knows when to think hard and when to talk

Haider.

195,733 просмотров • 1 год назад

Sam Altman on GPT-5 in Berlin today “How many of you think you will still be smarter than GPT-5 ? I don’t think I’m gonna be smarter than GPT-5” #Gpt5 Sam Altman 👀
1:06

Sam Altman on GPT-5 in Berlin today “How many of you think you will still be smarter than GPT-5 ? I don’t think I’m gonna be smarter than GPT-5” #Gpt5 Sam Altman 👀

Raphaël Dabadie (YC P26)

763,785 просмотров • 1 год назад

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."
0:28

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Ethan Mollick

188,306 просмотров • 3 месяцев назад

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease.
0:50

GPT-5 just dropped in Azure AI Foundry. Devs can tap into the full suite of GPT-5 models with a single endpoint using Foundry’s AI-powered model router. Intelligent model selection, so you can build with ease.

Microsoft Azure

18,859,065 просмотров • 10 месяцев назад

.Andrew Mayne on: - creating the prompt engineering discipline - his journey from the circus to OpenAI (not a joke) - hitting the wall on AI progress - prompt engineering v2 - GPT-3 > GPT-5 ? - AI saving him from a shark Episode available at links below. Enjoy!
1:08:23

.Andrew Mayne on: - creating the prompt engineering discipline - his journey from the circus to OpenAI (not a joke) - hitting the wall on AI progress - prompt engineering v2 - GPT-3 > GPT-5 ? - AI saving him from a shark Episode available at links below. Enjoy!

Logan Kilpatrick

32,491 просмотров • 2 лет назад

Here's a realtime, 5-minute FPS game made by GPT-4V. Updated tldraw's "draw my ui" prompt to work with mrdoob's threejs + improved iteration process by utilising history (PR soon) 1/2
2:17

Here's a realtime, 5-minute FPS game made by GPT-4V. Updated tldraw's "draw my ui" prompt to work with mrdoob's threejs + improved iteration process by utilising history (PR soon) 1/2

firtoz

206,631 просмотров • 2 лет назад

Kind of shocking how much better GPT-5-Codex is vs the regular 'Thinking' models in ChatGPT. My subjective rankings for the fruit machine test: 1. GPT-5-Codex-Medium 2. GPT-5-Thinking-Heavy 3. GPT-5-Pro 4. GPT-5-Codex-High 5. GPT-5-Codex-Low 6. GPT-5-Thinking-Standard 7. GPT-5-Thinking-Extended 8. GPT-5-Thinking-Light OpenAI Codex team have suggested 'Medium' should be the default, but I didn't expect that it would actually beat the 'High' setting model in my test.
0:44

Kind of shocking how much better GPT-5-Codex is vs the regular 'Thinking' models in ChatGPT. My subjective rankings for the fruit machine test: 1. GPT-5-Codex-Medium 2. GPT-5-Thinking-Heavy 3. GPT-5-Pro 4. GPT-5-Codex-High 5. GPT-5-Codex-Low 6. GPT-5-Thinking-Standard 7. GPT-5-Thinking-Extended 8. GPT-5-Thinking-Light OpenAI Codex team have suggested 'Medium' should be the default, but I didn't expect that it would actually beat the 'High' setting model in my test.

Peter Gostev

101,848 просмотров • 9 месяцев назад

GPT-5 is now built into Xcode 26!
0:56

GPT-5 is now built into Xcode 26!

OpenAI Developers

568,197 просмотров • 9 месяцев назад

I built a GPT that finds the best GPTs using data from 500+ submissions. Simply ask it: What's the best GPT for [x]. Link below!
0:21

I built a GPT that finds the best GPTs using data from 500+ submissions. Simply ask it: What's the best GPT for [x]. Link below!

Rowan Cheung

240,249 просмотров • 2 лет назад

Today is the 1 year anniversary of Repo Prompt 1.0 To highlight the occasion, here's a video combining agentic context building, with old school copy pasting, to enable you to use ChatGPT's GPT-5.4 Pro to get some of the deepest code reviews around.
5:05

Today is the 1 year anniversary of Repo Prompt 1.0 To highlight the occasion, here's a video combining agentic context building, with old school copy pasting, to enable you to use ChatGPT's GPT-5.4 Pro to get some of the deepest code reviews around.

eric provencher

17,114 просмотров • 3 месяцев назад