Aurelia Vance (@CodeByAurelia) header
Aurelia Vance (@CodeByAurelia) profile picture

Helping ambitious Founders and CEOs create meaningful Personal Brands on Twitter | Al & Web Dev Enthusiast |🔗 DM For Paid Promotion📩. [email protected]

New York, USA
Joined June 2011
Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)Photo by Aurelia Vance (@CodeByAurelia)
Aurelia Vance retweeted
A new development worth following in AI-assisted programming. Qoder is Alibaba's coding agent and agent harness from the same company behind Qwen. It has launched Qoduck, a stealth model that individual users can try free for a limited time. qoder.com/
A stealth model just landed on Qoder. Meet Qoduck. Don't ask where it came from. Free every day for all individual users. Limited-time.
10
18
46
8,732
Aurelia Vance retweeted
The interesting part about these Magnific experiments isn’t just the animation quality. It’s the workflow behind them. Create the visuals in Magnific One, animate them with Move, then refine individual elements without rebuilding everything.
6 motion experiments made with Magnific One + Move Stills created with Magnific One, then animated with Move to explore collage, texture and cinematic styles The examples and prompts behind each look 👇
10
20
38
8,617
Aurelia Vance retweeted
If I were making a skincare ad, I'd rather show the actual product texture than just talk about how good it is. CapCut PC's Black Friday promotion ends October 30: 60% off Pro and 40% off Ultra. Edit Pilot can help optimize the original audio from the product demonstration. Then I'd use color adjustment tools to keep the skin and product looking natural, and fine-tune the close-up shots on the timeline. The goal is to make the experience feel genuine, not overly edited. tinyurl.com/2v23rn22 #capcutpc #capcutmarketing #capcutblackfriday #capcutsale
22
25
109
51,636
Aurelia Vance retweeted
Watch this for a second. Notice how the different elements work together? That’s the sort of detail that makes motion graphics feel polished. Magnific Move is taking a pretty interesting approach to creating this stuff. You describe it. An AI agent builds it. #MagnificMove
20
20
95
48,618
Aurelia Vance retweeted
The interesting part isn’t just generating motion graphics. It’s being able to go back, change one detail, and keep everything else intact. That’s where Magnific Move gets interesting.
Meet Magnific Move: motion graphics you can talk to Animated charts, launch videos, logo reveals. Type what you want, say what to change, and make it move with agentic video editing Every layer stays editable, see it in action
7
10
45
9,474
Aurelia Vance retweeted
A woman is on her phone, the product is beside the bed, and a ghost is waiting outside the window. 👻 Dreamina’s first month is just $0.29, and CapCut Desktop separately offers 60% OFF Pro or 40% OFF Ultra through Oct 30. These are separate subscriptions. The phone call, scare, and window entrance all need their own timing, and lining them up can get messy. CapCut PC Multi-Track Editing helps arrange the clips and sound cues into a clearer sequence. Dreamina: tinyurl.com/5xbtv4x6 CapCut Desktop: tinyurl.com/2v23rn22 #CapCutDidThat #Dreamina #Smallbusinessmarketing #CapCutSale
23
21
114
53,031
Aurelia Vance retweeted
What makes an AI agent useful? Its ability to understand context, use tools, execute tasks, and verify what it produces. Qoder is built around this workflow. DeepSeek-Flash is available at zero Credits within the daily free allowance through Oct 31. qoder.com/qoder
DeepSeek-V4.1-Flash-1017 is FREE in Qoder through Oct 31. Free and paid individual accounts included. No claim needed. Daily free uses cost 0 Credits, even with a zero balance. How to start is in the reply 👇
12
8
41
30,747
Aurelia Vance retweeted
Your concert footage is piling up, but the fan edit is still just an idea in your head. 😭🎤 The CapCut plugin is coming soon to ChatGPT! At CapCut World, leading creators and OpenAI came together to explore new AI-powered creative workflows. Describe the edit you want, let ChatGPT control CapCut Web through the plugin to help organize your footage and build a rough cut with AI Smart Editing, then jump into the timeline to polish those iconic stage moments. From scattered fancams to a fan edit taking shape, the workflow feels more connected. Currently in early access on ChatGPT desktop for PC. Mobile and web support is expected in mid-November. #CapCutWeb #CapCutDidThat #ChatGPT #CapCutWorld
23
14
110
54,647
Aurelia Vance retweeted
Keep the UGC feel. Give the product ad a cleaner finish. The CapCut Web plugin is coming soon to ChatGPT. Describe your style to guide captions, transitions, and filters around your raw footage. Leading creators and OpenAI explored AI-powered video workflows at CapCut World. Early access is available on ChatGPT desktop, with mobile and web support expected in mid-November. #CapCutDidThat #CapCutWeb #ChatGPT #CapCutWorld
25
19
97
56,026
Aurelia Vance retweeted
A little change to your content routine can make a big difference. 🎥 Use Dreamina to generate fresh assets for just $0.29 in the first month, then bring them into CapCut PC for editing. From Oct 20–30, CapCut Pro is 60% off and Ultra is 40% off. Each service is billed separately. Browse the CapCut Black Friday sale: tinyurl.com/2v23rn22 Check out the Dreamina + CapCut offer: tinyurl.com/5xbtv4x6 #CapCutDidThat #Dreamina #Smallbusinessmarketing #CapCutSale
25
9
85
59,856
Aurelia Vance retweeted
CapCut’s exclusive Black Friday offer has gone live on Desktop: enjoy 60% off Pro and 40% off Ultra, October 20–30. A Halloween launch video needs to guide attention toward the collection and its key message. With Edit Pilot in CapCut PC, you can describe editing changes in natural language and review them in the timeline. Continue developing the sequence as you assess where the campaign feels clear and where it needs another pass. Give the edit a direction that serves the launch. #capcutpc #capcutmarketing #capcutsale #capcutblackfriday
23
7
99
63,462
Aurelia Vance retweeted
I launched the first image and video generation models at Google, and kept asking why all AI designs look the same. AI has brought us the WORST era of design. It made content creation effortless, but it also made 90% of it look painfully generic. My co-founder and I spent 2 years building in stealth to change that. Meet Vyb, the first AI design model that understands your taste like a designer would. RT + comment your website URL and we’ll make your first design.
274
236
199
1,658
3,675,375
Aurelia Vance retweeted
From a Tesla Roadster concept to a complete marketing video, the workflow can be surprisingly straightforward. Start by explaining what you want the video to communicate, then use Codex with CapCut Web to turn those instructions into creative execution. Instead of manually figuring out every step before you begin, you can guide the process with natural language. It’s the combination of an AI that understands your intent and an editing tool that helps bring the vision together. #capcutweb #capcutmarketing #capcutcodex #capcutchatgptplugin
26
5
101
63,969
Aurelia Vance retweeted
Me watching an AI response appear one token at a time: 🧍 Me discovering people are still finding ways to accelerate decoding: 👀 EAGLE-4 is another interesting addition to that rabbit hole.
EAGLE-4 is here. From EAGLE-1 to EAGLE-3, we’ve kept making inference faster. EAGLE-4 is our fastest yet. 961.6 tokens/s on @Alibaba_Qwen’s Qwen3.8-27B with TokenSpeed (BF16, 4× @NVIDIA B300, TP4, one request, T=0). Github: github.com/eagle-hq/EAGLE-4
10
4
39
18,722
Aurelia Vance retweeted
Document parsing benchmark update. OXR (1.3B, open source) currently leads olmOCR-Bench. Also OmniDocBench. And DocParsingBench. Against GLM-OCR: • OmniDocBench 97.18 vs 95.22 • DocParsingBench 87.76 vs 80.34 • 100 pages, lone RTX PRO 6000: 101.0 s vs 308.0 s Complex formulas are where I'd stress-test it. Architecture: exchangeable layout model, concurrent recognition and ordering, RSI post-training. github.com/SoMarkAI/OXR
Beyond OCR. Meet OXR. Only 1.3B. Open source. #1 on olmOCR-Bench, OmniDocBench & DocParsingBench🏆 #1 in parsing speed among open-source models⚡ RSI-powered. A first in document parsing. Turn documents into Agent-Friendly data. If OXR helps, give us a star on GitHub! 🌟
10
2
29
9,326
Aurelia Vance retweeted
Developers who enjoy testing different AI models should check this out. DeepSeek V4.1-Flash-1017 is currently available on Qoder with zero credit consumption through October 24. qoder.com/qoder
DeepSeek dropped V4.1-Flash-1017 on Saturday. It's been in Qoder since day one. Now it's FREE through Oct 24. 0.0x credits for free and paid users. Just select it and go.
13
1
36
33,913
Aurelia Vance retweeted
Interesting to see an open-source model this size claiming strong performance while running on a single DGX card. The efficiency angle stands out more than the raw scores.
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!! Open weights under the MIT license. Coding ✅SWE-bench Verified: 0.845 ✅TB2.1: 0.813 ✅CyberGym: 0.800 ✅NL2Repo: 0.512 Agentic ✅HLE: 0.446 ✅BrowseComp: 0.785 ✅MCP-Atlas: 0.746 ✅Toolathlon: 0.708 🤗Hugging Face: huggingface.co/ornith-ai/Orn… We can’t wait to see what you build with Ornith-1.5-122B.
11
2
32
13,881
Aurelia Vance retweeted
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!! Open weights under the MIT license. Coding ✅SWE-bench Verified: 0.845 ✅TB2.1: 0.813 ✅CyberGym: 0.800 ✅NL2Repo: 0.512 Agentic ✅HLE: 0.446 ✅BrowseComp: 0.785 ✅MCP-Atlas: 0.746 ✅Toolathlon: 0.708 🤗Hugging Face: huggingface.co/ornith-ai/Orn… We can’t wait to see what you build with Ornith-1.5-122B.
220
506
461
2,760
1,512,158
Aurelia Vance retweeted
With Tesla Roadster back in the conversation, it’s tempting to put every cool car shot into one video. But a stronger promo usually has one clear focus. Use CapCut Web + Codex to help organize your footage around a single message, whether it’s design, performance-inspired visuals, or a futuristic mood. Cut anything that distracts from that idea, then polish the pacing in CapCut. #capcutweb #capcutchatgptplugin #capcutcodex #capcutmarketing
23
14
156
64,877
Aurelia Vance retweeted
From the streets to the skies. The future of car commercials is here. ⚡ Bring your boldest ideas to life with CapCut Desktop. Save 60% on Pro or 40% on Ultra, Oct 20–30. Desktop only. #capcutpc #capcutsale #capcutmarketing]
22
7
134
64,183