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。

MiniMax M3: Opus-level coding at DeepSeek pricing. On Terminal-Bench 2.1, it scores 66.0, only 0.1 behind Opus 4.7. I gave it a quick try on a few frontend tasks, and the output quality genuinely feels close to Opus 4.7.

Kai

5,846 subscribers

25,648 次观看 • 16 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

SOMEONE BUILT A PERSONAL AI DASHBOARD WITH CLAUDE DESIGN AND OPUS 4.7 AND IT FEELS LIKE A PERSONAL OS

SOMEONE BUILT A PERSONAL AI DASHBOARD WITH CLAUDE DESIGN AND OPUS 4.7 AND IT FEELS LIKE A PERSONAL OS

leopardracer

315,700 次观看 • 1 个月前

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

ClaudeDevs

361,732 次观看 • 2 个月前

Fast mode now defaults to Opus 4.7 in Claude Code. Try it out today with /fast

Fast mode now defaults to Opus 4.7 in Claude Code. Try it out today with /fast

ClaudeDevs

1,276,592 次观看 • 1 个月前

Gemini 3.0 pro and Opus 4.5 both models are far ahead in terms of coding specially frontend I am thinking about next sonnet 4.7 and gemini 3.0 pro GA

Gemini 3.0 pro and Opus 4.5 both models are far ahead in terms of coding specially frontend I am thinking about next sonnet 4.7 and gemini 3.0 pro GA

Chetaslua

70,198 次观看 • 5 个月前

My first time building with Opus 4.7 and I love it! I quickly built this Base AI Ecosystem map with names, links logos in the form of a galaxy that you can navigate through 🛰️ With some rigorous prompting, Opus 4.7 did everything for me including descriptions and logos!

My first time building with Opus 4.7 and I love it! I quickly built this Base AI Ecosystem map with names, links logos in the form of a galaxy that you can navigate through 🛰️ With some rigorous prompting, Opus 4.7 did everything for me including descriptions and logos!

Youssef

17,052 次观看 • 1 个月前

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high) → 56.0 MiniMax 2.5 → 55.4

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high) → 56.0 MiniMax 2.5 → 55.4

Morph

56,540 次观看 • 3 个月前

If you want to use Claude Opus 4.7 in the codex app

If you want to use Claude Opus 4.7 in the codex app

Riley Brown

26,474 次观看 • 2 个月前

we compared Gemini 3.1 Pro, Opus 4.7, and GPT 5.5 to Kimi K2.6, Xiaomi Mimo v2.5, and Qwen 3.6 Max in average, closed source are faster. GPT 5.5 and Opus 4.7 the fastest. Kimi K2.6 comes after. It keeps up thanks to its native INT4 quantization. MiMo took the longest, but the refinement and aesthetic only ranks after Gemini 3.1. as if a mini Gemini. Its slow cuz it's trained for long-horizon agentic work. Claude Opus 4.7 is blooming in a very different style, probably because Anthropic trains for taste, not just accuracy.

we compared Gemini 3.1 Pro, Opus 4.7, and GPT 5.5 to Kimi K2.6, Xiaomi Mimo v2.5, and Qwen 3.6 Max in average, closed source are faster. GPT 5.5 and Opus 4.7 the fastest. Kimi K2.6 comes after. It keeps up thanks to its native INT4 quantization. MiMo took the longest, but the refinement and aesthetic only ranks after Gemini 3.1. as if a mini Gemini. Its slow cuz it's trained for long-horizon agentic work. Claude Opus 4.7 is blooming in a very different style, probably because Anthropic trains for taste, not just accuracy.

GMI Cloud

37,446 次观看 • 1 个月前

We’re excited to add support for Opus 4.6. With adaptive thinking, Opus 4.6 will decide the right amount of reasoning for your query, reducing latency and improving quality. Internally, we've already resolved bugs that Opus 4.5 couldn't tackle. Try it out on the latest!

We’re excited to add support for Opus 4.6. With adaptive thinking, Opus 4.6 will decide the right amount of reasoning for your query, reducing latency and improving quality. Internally, we've already resolved bugs that Opus 4.5 couldn't tackle. Try it out on the latest!

Warp

12,378 次观看 • 4 个月前

We're teaming up with Anthropic to launch Opus 4.7! Open to all builders, all backgrounds. Join our global virtual hackathon powered by Claude Code. One week to push the boundaries of what's possible with Opus 4.7. April 21–28 500 builders Win up to $100k in Claude API credits Applications close Sunday, April 19th Apply Here👇

We're teaming up with Anthropic to launch Opus 4.7! Open to all builders, all backgrounds. Join our global virtual hackathon powered by Claude Code. One week to push the boundaries of what's possible with Opus 4.7. April 21–28 500 builders Win up to $100k in Claude API credits Applications close Sunday, April 19th Apply Here👇

Cerebral Valley

46,754 次观看 • 2 个月前

Devin for Terminal is a local agent that works with all frontier models, including Opus 4.7, GPT 5.5, and SWE-1.6. You can switch model mid-session, or handoff to Devin in the cloud.

Devin for Terminal is a local agent that works with all frontier models, including Opus 4.7, GPT 5.5, and SWE-1.6. You can switch model mid-session, or handoff to Devin in the cloud.

Cognition

10,129,242 次观看 • 1 个月前

Claude Opus 4.7 vs Kimi K2.6 It's not even close. 3 months ago nobody believed open-source could beat Claude. Today it did. Full guide with Prompt 👇

Claude Opus 4.7 vs Kimi K2.6 It's not even close. 3 months ago nobody believed open-source could beat Claude. Today it did. Full guide with Prompt 👇

Poonam Soni

32,242 次观看 • 1 个月前

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

Dan Shipper 📧

350,783 次观看 • 20 天前

I built a pull up tracker for my livestream. When someone likes the stream it adds a pull up. It automatically subtracts when I do them. Coded this with opus 4.7 in 30 minutes. The future is now.

I built a pull up tracker for my livestream. When someone likes the stream it adds a pull up. It automatically subtracts when I do them. Coded this with opus 4.7 in 30 minutes. The future is now.

Max Blade

30,149 次观看 • 1 个月前

An OpenAI engineer stopped me at a hackathon in Hayes Valley I had my terminal open on a table. Three panels. Live trades scrolling. He was walking past and froze. "That's not a demo. That's a live scoring engine. What model is that" I told him. Claude Opus 4.7. Four repos. $25 a month. He pulled up a chair without asking. "We benchmarked Opus 4.7 internally. It beat o3 on structured reasoning across every eval we ran. And you're telling me you're using it to trade" I told him it does more than trade. It reads 86 million trades and finds who wins and why. No fine-tuning. No prompting chains. Just raw context. He leaned back. "Show me the data source" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You point Opus 4.7 at this and it reverse-engineers the strategy. It finds the wallets that win. Then it finds why they win. Then it copies the pattern" His team spent 14 months building something similar. 10 engineers. Custom infra. Still in staging. "The part that killed us was exit timing. Every model we trained nailed entries. But the best traders exit before the crowd. We never figured out the threshold" I told him my bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever comes first. He stopped talking. "How did you find that" Opus 4.7 found it in poly_data. Top wallets exit before resolution 86% of the time. Losers hold to 58%. Exits are the entire game. I opened another tab. "Three commands. 500 markets. Opus scores them in 20 minutes" "That's our internal eval pipeline. Except it took us a year and you did it in a weekend with our competitor's model" My setup: Claude Opus 4.7 - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400 in 19 days. Copytrade here: I showed him the article where I broke down every repo and every command. He read it twice. Then looked up. "You just published what we've been trying to ship for six months. Using the other team's model" He texted me the next day. "My manager found your thread. Delete it" Too late.

An OpenAI engineer stopped me at a hackathon in Hayes Valley I had my terminal open on a table. Three panels. Live trades scrolling. He was walking past and froze. "That's not a demo. That's a live scoring engine. What model is that" I told him. Claude Opus 4.7. Four repos. $25 a month. He pulled up a chair without asking. "We benchmarked Opus 4.7 internally. It beat o3 on structured reasoning across every eval we ran. And you're telling me you're using it to trade" I told him it does more than trade. It reads 86 million trades and finds who wins and why. No fine-tuning. No prompting chains. Just raw context. He leaned back. "Show me the data source" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You point Opus 4.7 at this and it reverse-engineers the strategy. It finds the wallets that win. Then it finds why they win. Then it copies the pattern" His team spent 14 months building something similar. 10 engineers. Custom infra. Still in staging. "The part that killed us was exit timing. Every model we trained nailed entries. But the best traders exit before the crowd. We never figured out the threshold" I told him my bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever comes first. He stopped talking. "How did you find that" Opus 4.7 found it in poly_data. Top wallets exit before resolution 86% of the time. Losers hold to 58%. Exits are the entire game. I opened another tab. "Three commands. 500 markets. Opus scores them in 20 minutes" "That's our internal eval pipeline. Except it took us a year and you did it in a weekend with our competitor's model" My setup: Claude Opus 4.7 - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400 in 19 days. Copytrade here: I showed him the article where I broke down every repo and every command. He read it twice. Then looked up. "You just published what we've been trying to ship for six months. Using the other team's model" He texted me the next day. "My manager found your thread. Delete it" Too late.

Lunar

136,409 次观看 • 2 个月前

Holy FUCK. Claude 4 Opus just ONE-SHOTTED a WORKING browser agent — API and frontend. One prompt. I've never seen anything like this. Genuinely can't believe it.

Holy FUCK. Claude 4 Opus just ONE-SHOTTED a WORKING browser agent — API and frontend. One prompt. I've never seen anything like this. Genuinely can't believe it.

Matt Shumer

807,039 次观看 • 1 年前

Сlaude Design + Claude Opus 4.7 is so cracked at Scroll-based Animated landing pages. 🤯 and anyone can achieve the same results. Here's the prompt ↓

Сlaude Design + Claude Opus 4.7 is so cracked at Scroll-based Animated landing pages. 🤯 and anyone can achieve the same results. Here's the prompt ↓

Viktor Oddy

50,933 次观看 • 1 个月前

Opus 4.7 can build Lottie Animations. One prompt via Lottie Creator MCP → 500 particles, each with its own path, easing, and arrival frame. I didn't touch a keyframe. What should I ask it to build next? Best reply, I'll make it.

Opus 4.7 can build Lottie Animations. One prompt via Lottie Creator MCP → 500 particles, each with its own path, easing, and arrival frame. I didn't touch a keyframe. What should I ask it to build next? Best reply, I'll make it.

Nattu

186,374 次观看 • 2 个月前

the real reason why SF is 6 months ahead on AI is just physics: shipping a SOTA model from the bay area to NYC is a logistical nightmare imagine what it took to bring Opus 4.7 to Europe (we don't have trains here) 😢

the real reason why SF is 6 months ahead on AI is just physics: shipping a SOTA model from the bay area to NYC is a logistical nightmare imagine what it took to bring Opus 4.7 to Europe (we don't have trains here) 😢

fabian

1,850,389 次观看 • 1 个月前

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.

GMI Cloud

75,785 次观看 • 27 天前