Загрузка видео...

Не удалось загрузить видео

На главную

We’re rolling out effort controls in Computer’s model selector. Effort presets combine the orchestrator model and reasoning depth to control how deeply and efficiently Computer works through a task. Available now on web. Coming to mobile and desktop soon.

perplexity_ai's profile picture

Perplexity

510,366 subscribers

176,770 просмотров • 1 месяц назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

You can now quickly eval GPT-5 and reasoning efforts across your existing responses. With the built-in grader, compare responses to find the best model and reasoning effort for you. ⚡️👀
0:13

You can now quickly eval GPT-5 and reasoning efforts across your existing responses. With the built-in grader, compare responses to find the best model and reasoning effort for you. ⚡️👀

OpenAI Developers

79,960 просмотров • 1 год назад

Opus 5.5 works best on 'low' reasoning effort. I ran some tests as part of a project I'm working on. Opus 5.5 on 'low' reasoning vs. 'max' was at parity on task completion but 12x lower cost! Set 'low' reasoning effort by default and increase it for the hardest problems.
0:12

Opus 5.5 works best on 'low' reasoning effort. I ran some tests as part of a project I'm working on. Opus 5.5 on 'low' reasoning vs. 'max' was at parity on task completion but 12x lower cost! Set 'low' reasoning effort by default and increase it for the hardest problems.

Dan McAteer

124,325 просмотров • 1 месяц назад

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.
0:16

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

elvis

13,699 просмотров • 3 месяцев назад

Price Alerts for Indian stocks are now available to all Perplexity Pro and Max users in India! Currently supported on web and mobile web. Mobile app support and availability for free users coming shortly! 🇮🇳
0:18

Price Alerts for Indian stocks are now available to all Perplexity Pro and Max users in India! Currently supported on web and mobile web. Mobile app support and availability for free users coming shortly! 🇮🇳

Aravind Srinivas

38,340 просмотров • 1 год назад

The model picker got a little facelift. Star your favorites. Dial the thinking up (or down) with effort controls. Because not every task needs max brainpower.
0:19

The model picker got a little facelift. Star your favorites. Dial the thinking up (or down) with effort controls. Because not every task needs max brainpower.

Notion

37,907 просмотров • 2 месяцев назад

agentic commerce in the wild Glossier, SKIMS, and SPANX are now selling in ChatGPT and we’re rolling out to more merchants soon
0:10

agentic commerce in the wild Glossier, SKIMS, and SPANX are now selling in ChatGPT and we’re rolling out to more merchants soon

Shopify

36,320 просмотров • 11 месяцев назад

Introducing the Computer Command Panel. Type / to see every mode and skill available in Computer, including Deep Research and Plan Mode. Live now on the web for all Computer users.
0:10

Introducing the Computer Command Panel. Type / to see every mode and skill available in Computer, including Deep Research and Plan Mode. Live now on the web for all Computer users.

Computer

39,181 просмотров • 4 месяцев назад

introducing Camera Controls. now Hailuo AI-MiniMax Hub video model supports over 20 different camera control presets. try them now!
0:13

introducing Camera Controls. now Hailuo AI-MiniMax Hub video model supports over 20 different camera control presets. try them now!

Krea

55,941 просмотров • 1 год назад

GPT-5 is rolling out to Visual Studio Code today! Starting today, GPT-5 is rolling out to all paid GitHub Copilot plans. GPT-5 is OpenAI's most capable model yet, bringing new advances in reasoning, coding, and chat. Learn more about the GPT-5 model availability:
0:16

GPT-5 is rolling out to Visual Studio Code today! Starting today, GPT-5 is rolling out to all paid GitHub Copilot plans. GPT-5 is OpenAI's most capable model yet, bringing new advances in reasoning, coding, and chat. Learn more about the GPT-5 model availability:

Visual Studio Code

222,411 просмотров • 1 год назад

GPT-5.1 is now available on Replicate. A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.
0:16

GPT-5.1 is now available on Replicate. A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.

Replicate

84,064 просмотров • 11 месяцев назад

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:
0:10

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:

Daniel San

66,147 просмотров • 7 месяцев назад

Poonam Soni if you see a "think" button, turn it on to use the reasoning model. rolling out to as many people as possible asap
0:11

Poonam Soni if you see a "think" button, turn it on to use the reasoning model. rolling out to as many people as possible asap

Eric Zelikman

1,690,071 просмотров • 1 год назад

Open weight models are now available in Kiro. Three open weight models are available in the IDE and CLI, so you don’t have to default to the largest model for every task. Choose the right model based on speed, cost, or long-running agentic workflows. What model would you like to see supported next? #Kiro #BuildwithKiro #AICoding
0:15

Open weight models are now available in Kiro. Three open weight models are available in the IDE and CLI, so you don’t have to default to the largest model for every task. Choose the right model based on speed, cost, or long-running agentic workflows. What model would you like to see supported next? #Kiro #BuildwithKiro #AICoding

Kiro

22,214 просмотров • 8 месяцев назад

Unlock more choices and more freedom in managing your crypto.⚡ Transak is now live in Ledger Live’s Sell section—allowing you to sell $BTC, $ETH, $USDC, $USDT, and more with ease and security. Rolling out progressively on Ledger Live Desktop & Ledger Live Mobile. Sell seamlessly. Stay in control. 🔐
0:12

Unlock more choices and more freedom in managing your crypto.⚡ Transak is now live in Ledger Live’s Sell section—allowing you to sell $BTC, $ETH, $USDC, $USDT, and more with ease and security. Rolling out progressively on Ledger Live Desktop & Ledger Live Mobile. Sell seamlessly. Stay in control. 🔐

Ledger

11,600 просмотров • 1 год назад

introducing FLUX 3. beyond video, this is the first model to support interactions with the real world through a new action-prediction system. available now on Krea, more modalities coming soon.
0:19

introducing FLUX 3. beyond video, this is the first model to support interactions with the real world through a new action-prediction system. available now on Krea, more modalities coming soon.

Krea

32,973 просмотров • 3 месяцев назад

"Me replaying the same 10 seconds of a K-pop performance like it’s my full-time job. Maybe it’s time to turn those favorite moments into an edit. The CapCut plugin is coming soon to ChatGPT, offering a conversational way to explore video creation with CapCut Web. Early Access is currently available through ChatGPT desktop (PC only), with mobile and web support expected in mid-November. #CapCutDidThat #CapCutWeb #ChatGPT #CapCutWorld
0:14

"Me replaying the same 10 seconds of a K-pop performance like it’s my full-time job. Maybe it’s time to turn those favorite moments into an edit. The CapCut plugin is coming soon to ChatGPT, offering a conversational way to explore video creation with CapCut Web. Early Access is currently available through ChatGPT desktop (PC only), with mobile and web support expected in mid-November. #CapCutDidThat #CapCutWeb #ChatGPT #CapCutWorld

Onil Coder

112,266 просмотров • 13 дней назад

Gemini 3.6 Flash is available in Antigravity CLI ☄️ Set it via /model which also now has an effort level slider! Recommend using medium effort for most tasks. Give it a try and let us know what you think. 🙏
0:14

Gemini 3.6 Flash is available in Antigravity CLI ☄️ Set it via /model which also now has an effort level slider! Recommend using medium effort for most tasks. Give it a try and let us know what you think. 🙏

Jack Wotherspoon

21,910 просмотров • 3 месяцев назад

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.
0:10

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

TRAE

63,629 просмотров • 1 год назад