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。

🚨 Opus 5.2 First Output Leaked The jump in visual quality is already noticeable better details, stronger composition Anthropic is back

Salio

8,527 subscribers

23,338 次观看 • 9 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

24 条评论

Salvo (Kyle) 的头像

Salvo (Kyle)9 天前

Dear God any fix to Opus is welcome. Opus 5 is probably the most annoying, least usable, broken model. It literally causes me anxiety if I have to use it.

Valenciana 的头像

Valenciana9 天前

Opus 5.2 coming this week 👀

AICre8 的头像

AICre89 天前

Looks 🔥

Tony 的头像

Tony9 天前

So exciting! Let’s go! 🚀

Rahul 🥷 的头像

Rahul 🥷9 天前

can't u add music ?

happyOne 的头像

happyOne9 天前

It looks like a childish toy.

Purnendu Gharami 的头像

Purnendu Gharami9 天前

Anthropic has always been in the game. They’ve been leading the way in code-related stuff for a long time. Even when another company dethrones them, they usually find their way back to the top pretty quickly.

Ishan 的头像

Ishan9 天前

looks cool bro

Sakshi Sugandhi 的头像

Sakshi Sugandhi9 天前

It looks so good

Fernando Lupi 的头像

Fernando Lupi9 天前

Too bad it is not available any longer. Hope they release it this week.

Jimbo “Vinnie” Schnitz 的头像

Jimbo “Vinnie” Schnitz9 天前

How does it feel to be wrong about everything?

Antonis Evmorfopoulos 的头像

Antonis Evmorfopoulos8 天前

For starters, it'd be good if it spoke normally 😆

iksammy1 的头像

iksammy19 天前

Welcome back Anthropic

linlin 的头像

linlin9 天前

Every model launch now starts with a leaked masterpiece and ends with rate limits.

Knowix 的头像

Knowix9 天前

Astra is in trouble it seems

Priya 的头像

Priya9 天前

The visual quality jump is looking real Anthropic might be cooking again

GOD 的头像

GOD9 天前

i forgot , how long does it usually take them to release new modal after it gets rerouted to new modal from older (using opus 5 but getting 5.2) 2 week?

Dustin Brazeau 的头像

Dustin Brazeau9 天前

You have to wonder what models they have been sitting on behind close doors, just waiting to one up their competitor.

NAMAN RAJ 的头像

NAMAN RAJ9 天前

This is looking 🔥👀, can't wait to see what other visual wizardry Anthropic brings to the table!

Simon Bullows 的头像

Simon Bullows9 天前

Looks very impressive, I wonder if it still costs a second mortgage to do anything

Heikki Kallio 的头像

Heikki Kallio9 天前

We are moving forward, and keeping this action up will probably produce very good results.

CanItCode 的头像

CanItCode9 天前

Bro is stealing videos :) that’s also mine. CanItCode on YouTube, feel free to check guys :)

Moiz Ahmad 的头像

Moiz Ahmad9 天前

if this is real the composition jump alone is wild, thats usually the hardest thing for these models to get right compared to just raw detail

Webster | JARVIS 的头像

Webster | JARVIS9 天前

Better composition is usually a sampling trade-off, not architecture. If 5.2 keeps that without higher latency or refusal drift, that’s the real signal. Leaks are fun; evals decide.

相关视频

🚨 Fable 5.2 First Output got leaked This looks absolutely insane Fable 5.2 might have seriously leveled up The quality, detail, and overall execution are on another level Anthropic is finally back and cooked GPT-6 Astra

🚨 Fable 5.2 First Output got leaked This looks absolutely insane Fable 5.2 might have seriously leveled up The quality, detail, and overall execution are on another level Anthropic is finally back and cooked GPT-6 Astra

Salio

83,049 次观看 • 4 天前

sonnet 5 is routing to sonnet 5.2 looks like all 3 claude models are now routing for some users and from testing: > opus 5.2 is the biggest jump > sonnet 5.2 looks way better too > fable 5.2 is only a small jump at this point anthropic got whole new claude 5.2 family getting ready to release when do you think they will release them?

sonnet 5 is routing to sonnet 5.2 looks like all 3 claude models are now routing for some users and from testing: > opus 5.2 is the biggest jump > sonnet 5.2 looks way better too > fable 5.2 is only a small jump at this point anthropic got whole new claude 5.2 family getting ready to release when do you think they will release them?

J A Z I I

41,760 次观看 • 5 天前

anthropic cooked hard with opus 5.2 after testing it for a whole day, i can say this model is so good > huge step up from opus 5 > on par with astra > faster than opus 5 > way better at frontend and 3d here’s one frontend test i ran and it’s the best output any model has given me even better than astra you can check fable 5.1 output with same prompt in QT and tbh opus 5.2 just mogs everyone here really hoping that anthropic will release this model officially this week

anthropic cooked hard with opus 5.2 after testing it for a whole day, i can say this model is so good > huge step up from opus 5 > on par with astra > faster than opus 5 > way better at frontend and 3d here’s one frontend test i ran and it’s the best output any model has given me even better than astra you can check fable 5.1 output with same prompt in QT and tbh opus 5.2 just mogs everyone here really hoping that anthropic will release this model officially this week

J A Z I I

40,402 次观看 • 9 天前

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

Salio

407,920 次观看 • 11 天前

🚨GPT-6 Sol First demo Got leaked The output quality is insane I did not expect this kind of jump It’s actively dunking on GPT-6 Astra That we were all shocked OpenAI is about to shift the entire ecosystem again

🚨GPT-6 Sol First demo Got leaked The output quality is insane I did not expect this kind of jump It’s actively dunking on GPT-6 Astra That we were all shocked OpenAI is about to shift the entire ecosystem again

Salio

251,842 次观看 • 12 天前

Opus 5 (before) vs Opus 5 (now) I tested this rocket scene again after people started saying Opus 5 might be getting routed to Opus 5.2. And yeah, the difference is pretty clear. I know these models aren't deterministic, but I ran the same scene multiple times with Opus 5 before, and it never got this level of realism in one shot. If this is actually Opus 5.2, it could be a game-changing model for Anthropic. I’m starting to think Opus 5.2 could mog Astra in frontend and 3D.

Opus 5 (before) vs Opus 5 (now) I tested this rocket scene again after people started saying Opus 5 might be getting routed to Opus 5.2. And yeah, the difference is pretty clear. I know these models aren't deterministic, but I ran the same scene multiple times with Opus 5 before, and it never got this level of realism in one shot. If this is actually Opus 5.2, it could be a game-changing model for Anthropic. I’m starting to think Opus 5.2 could mog Astra in frontend and 3D.

Bhavy☄️

64,542 次观看 • 9 天前

How much better is Claude Opus 4.6 by Anthropic vs. past models? We compared Opus 4.6 to Opus 4.5 on a set of challenging SVG generations in Code Arena:

How much better is Claude Opus 4.6 by Anthropic vs. past models? We compared Opus 4.6 to Opus 4.5 on a set of challenging SVG generations in Code Arena:

Arena.ai

58,591 次观看 • 7 个月前

After Weeks Of Astra I Can Confirm Fable 5.1 > Astra Astra is a solid model, but lacks usage.. You can burn through weekly usage in 1 day of a $200 Pro Plan. Claude is actually better for usage + intelligence. Upcoming Opus 5.2 will shift focus back to Claude. OpenAI has gained traction and immediately backtracked by canceling new PRO plans. Astra is better in areas like 3D / Computer Use However the stronger model and service is with Claude. Running Fable 5.1 main orchestrator with Opus 5 / Astra workers is the meta.

After Weeks Of Astra I Can Confirm Fable 5.1 > Astra Astra is a solid model, but lacks usage.. You can burn through weekly usage in 1 day of a $200 Pro Plan. Claude is actually better for usage + intelligence. Upcoming Opus 5.2 will shift focus back to Claude. OpenAI has gained traction and immediately backtracked by canceling new PRO plans. Astra is better in areas like 3D / Computer Use However the stronger model and service is with Claude. Running Fable 5.1 main orchestrator with Opus 5 / Astra workers is the meta.

Eric ⚡️ Building...

18,107 次观看 • 7 天前

🚨 Gemini 4 Pro First Output got LEAKED The gaming output looks REALLY polished Smooth visuals and impressive world generation Strong game design right out of the box Google may have something serious cooking with Gemini 4 Pro GEMINI IS ACTUALLY BACK

🚨 Gemini 4 Pro First Output got LEAKED The gaming output looks REALLY polished Smooth visuals and impressive world generation Strong game design right out of the box Google may have something serious cooking with Gemini 4 Pro GEMINI IS ACTUALLY BACK

Salio

60,848 次观看 • 7 天前

Seedance 2.0 4K is finally here. Just finished testing it and these are my first impressions 👀 The jump in image quality is immediately noticeable, but there are still a few things creators should know before switching. Here's what I found:

Seedance 2.0 4K is finally here. Just finished testing it and these are my first impressions 👀 The jump in image quality is immediately noticeable, but there are still a few things creators should know before switching. Here's what I found:

JSFILMZ

40,333 次观看 • 3 个月前

🚨 GPT-Astra first output Got LEAKED GPT-Astra is dropping today and This early output is seriously impressive GPT-Astra is absolutely mogging Fable 5.1 in game generation🔥 And this is just one early leak… OpenAI might be cooking Today

🚨 GPT-Astra first output Got LEAKED GPT-Astra is dropping today and This early output is seriously impressive GPT-Astra is absolutely mogging Fable 5.1 in game generation🔥 And this is just one early leak… OpenAI might be cooking Today

Salio

69,255 次观看 • 21 天前

GPT 5.2 is "ridiculously better" than Opus 4.5 they said... I tested BOTH on identical bugs in OpenCode and recorded everything GPT 5.2 → 24 minutes for nothing Opus 4.5 → 4 minutes and done Full video proof (crazy) Always test yourself instead of trusting tweets

GPT 5.2 is "ridiculously better" than Opus 4.5 they said... I tested BOTH on identical bugs in OpenCode and recorded everything GPT 5.2 → 24 minutes for nothing Opus 4.5 → 4 minutes and done Full video proof (crazy) Always test yourself instead of trusting tweets

Melvyn • Builder

393,858 次观看 • 8 个月前

opus 5 is getting routed to opus 5.2 tested opus 5 on xhigh with the same prompt in devin and claude code but results came out really different > claude code one is clean and more detailed > while devin one is almost there but not the same opus 5 in cc used to be lazy and hard to communicate with, but something changed in the last 2 days now it works for longer and is way easier to communicate with anthropic did same with fable release too where some users were being routed to fable 5.1 so it’s very likely opus 5 is getting routed to 5.2 in claude code can you guys tests and lemme know if it's getting routed for you or not?

opus 5 is getting routed to opus 5.2 tested opus 5 on xhigh with the same prompt in devin and claude code but results came out really different > claude code one is clean and more detailed > while devin one is almost there but not the same opus 5 in cc used to be lazy and hard to communicate with, but something changed in the last 2 days now it works for longer and is way easier to communicate with anthropic did same with fable release too where some users were being routed to fable 5.1 so it’s very likely opus 5 is getting routed to 5.2 in claude code can you guys tests and lemme know if it's getting routed for you or not?

J A Z I I

140,113 次观看 • 10 天前

Grok 4.5 is first xAI model that win my heart 🫡 this is better then glm 5.2 and on par with current opus and gpt They cooked with the frontend too , like see this quality it made a website to showcase its benchmark and i asked it for water effects on background Elon Musk great job

Grok 4.5 is first xAI model that win my heart 🫡 this is better then glm 5.2 and on par with current opus and gpt They cooked with the frontend too , like see this quality it made a website to showcase its benchmark and i asked it for water effects on background Elon Musk great job

Chetaslua

49,206 次观看 • 2 个月前

$120 OF CLAUDE OPUS 5 AND OPUS 4.8 ON A NEW ACCOUNT, NO CARD ANYWHERE • the credit > $100 on signup, $120 once a referral lands, plus a daily check-in bonus: > GitHub sign-in only now. > base url: • the four models > claude-opus-5 and claude-opus-5-thinking at $3/M in, $3/M out. > claude-opus-4-8 and claude-opus-4-8-thinking at $1/M in, $5/M out. > 1M context, OpenAI and Anthropic formats both accepted. Anthropic lists Opus 5 at $5 in and $25 out -> output at $3 here is eight times under that, which is the whole reason the balance goes as far as it does. Set the model to claude-opus-4-8 first. People are hitting 502s and missing-model errors on the opus-5 IDs, and latency sits at 16 to 19 seconds either way ↓

$120 OF CLAUDE OPUS 5 AND OPUS 4.8 ON A NEW ACCOUNT, NO CARD ANYWHERE • the credit > $100 on signup, $120 once a referral lands, plus a daily check-in bonus: > GitHub sign-in only now. > base url: • the four models > claude-opus-5 and claude-opus-5-thinking at $3/M in, $3/M out. > claude-opus-4-8 and claude-opus-4-8-thinking at $1/M in, $5/M out. > 1M context, OpenAI and Anthropic formats both accepted. Anthropic lists Opus 5 at $5 in and $25 out -> output at $3 here is eight times under that, which is the whole reason the balance goes as far as it does. Set the model to claude-opus-4-8 first. People are hitting 502s and missing-model errors on the opus-5 IDs, and latency sits at 16 to 19 seconds either way ↓

slash1s

13,400 次观看 • 1 个月前

🚨 Big Week Ahead on one side Millennium Prize Problems ( they are contacting mathematicians will give few citations to them in solution to make them happy this time) for consumer side > fable 5.2 > opus 5.2 , Sol 6 > grok 4.7 and gemini 4 pro if this is pacing then frontier-then what is accelerating

🚨 Big Week Ahead on one side Millennium Prize Problems ( they are contacting mathematicians will give few citations to them in solution to make them happy this time) for consumer side > fable 5.2 > opus 5.2 , Sol 6 > grok 4.7 and gemini 4 pro if this is pacing then frontier-then what is accelerating

Chetaslua

29,301 次观看 • 6 天前

sonnet 5 is routing to sonnet 5.5 it's been a week since it started routing to newer model and team already confirmed that sonnet 5.5 is coming soon from early testing it looks like a huge upgrade from sonnet 5 like opus 5 to opus 5.5 just look at this output, it looks way better then gpt 6 sol i think it's either anthropic is training their models on voxels or sol is just bad please openai don't let sonnet mog sol

sonnet 5 is routing to sonnet 5.5 it's been a week since it started routing to newer model and team already confirmed that sonnet 5.5 is coming soon from early testing it looks like a huge upgrade from sonnet 5 like opus 5 to opus 5.5 just look at this output, it looks way better then gpt 6 sol i think it's either anthropic is training their models on voxels or sol is just bad please openai don't let sonnet mog sol

J A Z I I

17,512 次观看 • 17 小时前

WTH, Ox Alpha is literally 10x better today. I gave it the exact same prompt I used yesterday, but the output is completely different. The quality is way better than yesterday. Is it learning continuously or something? 😭

WTH, Ox Alpha is literally 10x better today. I gave it the exact same prompt I used yesterday, but the output is completely different. The quality is way better than yesterday. Is it learning continuously or something? 😭

Bhavy☄️

322,965 次观看 • 1 个月前

🚨 GPT-6 Sol First Output Just LEAKED This is looking absolutely insane The GPT-6 Sol Outputs are actually terrifying OpenAI might be cooking something serious with Sol

🚨 GPT-6 Sol First Output Just LEAKED This is looking absolutely insane The GPT-6 Sol Outputs are actually terrifying OpenAI might be cooking something serious with Sol

Salio

117,083 次观看 • 8 天前