Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I use Opus Medium as a default smart model I use Sol High when I'm doing computer configuration stuff across devices or computer use I use Sol Low when I'm doing a very quick and simple computer task that's unlikely to get messed up I use Sonnet Medium when...

AdamHoltererer's profile picture

Adam Holter

24,174 subscribers

15,872 görüntüleme • 5 gün önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

My uncle, when I let him use the computer for a while 🤣🤣🤣 Writer: Samuel
0:11

My uncle, when I let him use the computer for a while 🤣🤣🤣 Writer: Samuel

Mario Nawfal

96,023 görüntüleme • 1 ay önce

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 görüntüleme • 1 ay önce

computer use on mac just got a lot faster. i built arc-driver - a lean & powerful computer-use driver for macos. >faster than cua-driver on most tasks. up to 8x on some. >plug it into your coding agents with a single command. open source. link below.
0:17

computer use on mac just got a lot faster. i built arc-driver - a lean & powerful computer-use driver for macos. >faster than cua-driver on most tasks. up to 8x on some. >plug it into your coding agents with a single command. open source. link below.

shiv

40,564 görüntüleme • 1 ay önce

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING OPUS 5 This is the most important prompting guide for anyone using Claude. Bookmark this before you forget. Most people still prompt Opus 5 like older models. That's the mistake. > give the complete task upfront — don't drip-feed instructions. > explicitly ask for shorter responses if you want them. > use low/medium effort by default. increase effort only when needed. > let it finish the entire feature instead of asking for partial implementations. > use subagents intentionally for large codebases, not every task. Opus 5 is at its best when you stop micromanaging it and let it own the work. Read it before writing your next prompt. Claude → Opus 5 → Agentic Execution → Production-Ready Output → Money
0:11

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING OPUS 5 This is the most important prompting guide for anyone using Claude. Bookmark this before you forget. Most people still prompt Opus 5 like older models. That's the mistake. > give the complete task upfront — don't drip-feed instructions. > explicitly ask for shorter responses if you want them. > use low/medium effort by default. increase effort only when needed. > let it finish the entire feature instead of asking for partial implementations. > use subagents intentionally for large codebases, not every task. Opus 5 is at its best when you stop micromanaging it and let it own the work. Read it before writing your next prompt. Claude → Opus 5 → Agentic Execution → Production-Ready Output → Money

Rahul

408,531 görüntüleme • 3 ay önce

I can no longer recommend folks use Openclaw its amazing and i have two mac minis but Claude Cowork Computer basically does all the same things but 1000% easier like this is what most people will use it for and its so much easier to get going than openclaw
0:15

I can no longer recommend folks use Openclaw its amazing and i have two mac minis but Claude Cowork Computer basically does all the same things but 1000% easier like this is what most people will use it for and its so much easier to get going than openclaw

ashen

231,910 görüntüleme • 7 ay önce

let me reintroduce myself hello i am shayla. i'm a black enby, i use they/she >:) i use fem and masc terms. and i am part of a system. i am on #dolltwt and #mhtwt, I have been a Monster High fan ever since 2010. I'm an all gen fan. My fav characters are Holt and Frankie ⚡
0:14

let me reintroduce myself hello i am shayla. i'm a black enby, i use they/she >:) i use fem and masc terms. and i am part of a system. i am on #dolltwt and #mhtwt, I have been a Monster High fan ever since 2010. I'm an all gen fan. My fav characters are Holt and Frankie ⚡

shay 🍉

202,158 görüntüleme • 3 yıl önce

Yes, Claude is controlling my computer from my phone with Dispatch I don’t like posting about anything I haven’t actually tried myself Reposting a video is easy, quality content comes from actually experimenting with new features So I saw the announcement that Claude Dispatch now controls your computer and I simply asked it to open Twitter and like a Claude post Done ✅ Now we need SKILL.md files with instructions to use other apps on your computer… OMG! this is getting more interesting and more dangerous by the minute
0:16

Yes, Claude is controlling my computer from my phone with Dispatch I don’t like posting about anything I haven’t actually tried myself Reposting a video is easy, quality content comes from actually experimenting with new features So I saw the announcement that Claude Dispatch now controls your computer and I simply asked it to open Twitter and like a Claude post Done ✅ Now we need SKILL.md files with instructions to use other apps on your computer… OMG! this is getting more interesting and more dangerous by the minute

Daniel San

224,361 görüntüleme • 7 ay önce

Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, Nous Research Hermes 405B instruct free is performing better than OpenAI GPT 5.4.... 👀
0:15

Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, Nous Research Hermes 405B instruct free is performing better than OpenAI GPT 5.4.... 👀

Rohan Arun

22,946 görüntüleme • 6 ay önce

Perplexity Computer just opened a PR on my repo, starting with a simple task... improving SEO What stands out is how it executes. Exploring with Gemini, then switching to Opus when it’s time to actually write code (I haven’t seen it use Codex or Grok) I’m going to ramp up the complexity from here. So far, it’s delivered on every task. I have a few more in progress that I’ll be sharing over the next few days.
0:18

Perplexity Computer just opened a PR on my repo, starting with a simple task... improving SEO What stands out is how it executes. Exploring with Gemini, then switching to Opus when it’s time to actually write code (I haven’t seen it use Codex or Grok) I’m going to ramp up the complexity from here. So far, it’s delivered on every task. I have a few more in progress that I’ll be sharing over the next few days.

Daniel San

15,317 görüntüleme • 8 ay önce

SHAME on Google Maps As a lake I don’t have much use for mapping apps except when I verify that Big Ass Lake really does exist. But I will now use a different one.
0:10

SHAME on Google Maps As a lake I don’t have much use for mapping apps except when I verify that Big Ass Lake really does exist. But I will now use a different one.

Lake Michigan

55,798 görüntüleme • 2 ay önce

Don't worry I use my computer well and make better work instead of subpar AI slop lol.
0:19

Don't worry I use my computer well and make better work instead of subpar AI slop lol.

Taran Singh

13,113 görüntüleme • 8 ay önce

I use to like doing this little dance on my tiktok for a while. I should start doing it again 🐈‍⬛ #tiktok #latina
0:12

I use to like doing this little dance on my tiktok for a while. I should start doing it again 🐈‍⬛ #tiktok #latina

RaddCatt

26,342 görüntüleme • 7 ay önce

me: when i use dark humor on the wrong person, now i'm getting a lecture on human rights, racism and mental health
0:10

me: when i use dark humor on the wrong person, now i'm getting a lecture on human rights, racism and mental health

𝒵𝒾𝓀✯

40,218 görüntüleme • 2 ay önce

Claim: Computer-Use agents are embodied generalists Back in August, we used a single computer-use agent across 4 different embodied AI-related competitions at ECCV, and we ranked 1st, 2nd, 3rd, and 6th places. How? We constructed simple GUI software for each competition that connects to the benchmark tasks (e.g., using a keyboard to navigate inside a 3D house rendered in a web interface), and that's it. The agent itself stays the same. I have been meaning to write about it for a long time, but here it is now: Now to the position: we believe that computer-use agents are embodied generalists. Why? TLDR: We believe computer-use agents share striking similarities with models for embodied AI, and embodied tasks can be formulated as interactions with digital software. Once we have that, we can learn from what worked for computer use over the past 2 years, focus on digital scaling, and avoid mistakes or local minima in the grand scheme of things. I would urge anyone working in computer use or embodied AI to take a quick read of the paper, or at least go through the website. We do not think many people would agree now, and only time will tell. But we do think this is an important line of thought that everyone should consider. We look forward to feedback and constructive criticism!
0:20

Claim: Computer-Use agents are embodied generalists Back in August, we used a single computer-use agent across 4 different embodied AI-related competitions at ECCV, and we ranked 1st, 2nd, 3rd, and 6th places. How? We constructed simple GUI software for each competition that connects to the benchmark tasks (e.g., using a keyboard to navigate inside a 3D house rendered in a web interface), and that's it. The agent itself stays the same. I have been meaning to write about it for a long time, but here it is now: Now to the position: we believe that computer-use agents are embodied generalists. Why? TLDR: We believe computer-use agents share striking similarities with models for embodied AI, and embodied tasks can be formulated as interactions with digital software. Once we have that, we can learn from what worked for computer use over the past 2 years, focus on digital scaling, and avoid mistakes or local minima in the grand scheme of things. I would urge anyone working in computer use or embodied AI to take a quick read of the paper, or at least go through the website. We do not think many people would agree now, and only time will tell. But we do think this is an important line of thought that everyone should consider. We look forward to feedback and constructive criticism!

Pranjal Aggarwal

11,392 görüntüleme • 4 gün önce

Claude Code with: > Opus 4.8 > Ultracode > Dynamic Workflows > Auto-mode ON ...is amazing. This is the way. I only use it with my Enterprise account. On work that will return material value to my company. I'd use it in my personal account but I don't want my family to be destitute after one prompt.
0:15

Claude Code with: > Opus 4.8 > Ultracode > Dynamic Workflows > Auto-mode ON ...is amazing. This is the way. I only use it with my Enterprise account. On work that will return material value to my company. I'd use it in my personal account but I don't want my family to be destitute after one prompt.

Dan McAteer

73,405 görüntüleme • 5 ay önce

GPT 5.6 Luna Max vs 5.6 Sol Medium… Yeah, it’s not even a question 😭 Sol on MEDIUM produced a much better result than Luna on MAX—and needed only around HALF the time. Same harness. Better generation. Faster result. Luna may be cheaper, but if you have the budget, I would absolutely use Sol. Saving money is not worth it when the weaker output creates hours of extra work later.
0:16

GPT 5.6 Luna Max vs 5.6 Sol Medium… Yeah, it’s not even a question 😭 Sol on MEDIUM produced a much better result than Luna on MAX—and needed only around HALF the time. Same harness. Better generation. Faster result. Luna may be cheaper, but if you have the budget, I would absolutely use Sol. Saving money is not worth it when the weaker output creates hours of extra work later.

OmedTheVibeCoder

100,863 görüntüleme • 3 ay önce

Lost my folder of funny videos back when my computer died in February and I think I'm officially giving up on recovering them. Please share some new videos for my folder
0:17

Lost my folder of funny videos back when my computer died in February and I think I'm officially giving up on recovering them. Please share some new videos for my folder

ToadBup

15,765 görüntüleme • 3 ay önce