Manish Kumar Shah ✓

The small tweaks are usually the most annoying part of building an app. “Make this button bigger… no, the other one.” With @boltdotnew Visual Edits, just click the element, edit it directly, and save multiple changes in one batch. AI builds it. You handle the finishing 21.6K views · 44 likes · 10 reposts · 16 replies Open on X →

The annoying part of scheduling a meeting was never finding a calendar slot. It was all the back-and-forth just to get there. Lindy’s new CC scheduling fixes that without making the other person change anything. Just CC Lindy on the thread, and it reads the conversation, 16.7K views · 22 likes · 7 reposts · 6 replies Open on X →

AI is pushing creativity into new territory, but the bigger question is still deeply human. Why do we feel the need to create? Spectrum explores that question through the lens of AI filmmaking. A fascinating reminder that sometimes, the technology matters less than the 9.1K views · 30 likes · 5 reposts · 14 replies Open on X →

Most AI gateways make it easy to connect to cloud models. But what happens when your model is running on your laptop? That’s where https://t.co/YJ4xwoiJ03 gets interesting. You can connect local + cloud models through one AI gateway. 15.8K views · 55 likes · 29 reposts · 12 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev2 Sep

One thing I like about the Realtime TTS-2 launch is that voice control doesn’t stop at choosing a voice. You can describe the delivery in plain language and steer how the line should sound. TTS-2 also brings sub-100ms TTFB, while the new Flash model gets that below 25ms. It’s 9K views · 39 likes · 13 reposts · 4 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev2 Sep

Most AI assistants tell you what to do. Catch actually does it. It can schedule meetings, handle emails, book travel, make calls + take care of the admin work that keeps piling up. $99/mo vs ~$4,500/mo for a human assistant. This is the kind of AI agent I actually want to htt 17.5K views · 71 likes · 45 reposts · 12 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev1 Sep

Most AI video tools give you a finished clip and stop there. What caught my attention with Orbis is that the world keeps running. You can change the prompt while it’s happening and actually see the world respond without stopping. You’re not just waiting for a result. You can 61K views · 225 likes · 32 reposts · 48 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev1 Sep

The faster we ship, the faster our test coverage can fall behind. QA Wolf’s approach to continuously mapping the product and spotting coverage gaps makes a lot of sense for modern development. 11.7K views · 62 likes · 15 reposts · 17 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev1 Sep

Your test suite is out of date the moment you ship a new feature. 📉 Before AI coding tools, a focused team *might* have kept up. Now it’s impossible. Our product-mapping AI explores your app, spots coverage gaps, and outlines new tests as you ship. https://t.co/cAtETXpqw5 htt 23.8K views · 60 likes · 1.2K reposts · 30 replies Open on X →

Manish Kumar Shah ✓@manishkumar_dev27 Aug

Running complex, long-running AI jobs with Claude quickly eats up all my credits. Save your Claude credits or extend them by offloading those jobs to Neo MCP. Instead of making Claude handle everything, Neo takes over the heavy AI/ML work while your coding assistant stays https 51.5K views · 159 likes · 40 reposts · 34 replies Open on X →

@manishkumar_dev Definitely worth experimenting with. The multilingual lip sync + multi-shot features caught my attention. 31 views · 2 likes · 0 reposts · 0 replies Open on X →

You can also use Wan 3.0 inside the Magnific Suite. You can experiment with text-to-video acting, Spanish accents, kids’ content + 3D animation with singing/speaking characters. 40% OFF until September 30 ⚡ If you’re creating with AI video, it’s definitely worth trying. Try 3.4K views · 16 likes · 0 reposts · 0 replies Open on X →

The multi-shot generation is another feature I really liked. You can direct multiple shots in one generation, with movements like crash zooms and 180° camera orbits. It feels less like generating separate clips and more like directing a scene. 1.2K views · 15 likes · 0 reposts · 1 replies Open on X →

Character consistency is another thing I noticed. You can work with the same characters across different shots while keeping their appearance much more consistent. And with the Magnific Suite, you can bring these generations together and build out the scene you have in mind. ht 2.3K views · 15 likes · 0 reposts · 1 replies Open on X →

The multilingual lip sync is one of the features I’m most interested in. Wan 3.0 can keep characters in sync while they speak, even when the language changes mid-scene. That opens up some interesting possibilities for storytelling, ads + localized content. I used these https:/ 2.4K views · 15 likes · 0 reposts · 1 replies Open on X →

🚨 AI video just took another step forward. I’ve been testing Wan 3.0 on Magnific, and what stood out to me is how much control you can get from a single generation. 30s video + sound, multilingual lip sync, consistent characters + multi-shot scenes. And right now, it’s 40% htt 88.5K views · 232 likes · 34 reposts · 36 replies Open on X →

@manishkumar_dev @manishkumar_dev dreamina sounds intriguing. i've been messing around with AI video tools lately too. curious how it stacks up against the big names. gonna dive in, thanks for the heads-up! 47 views · 1 likes · 0 reposts · 0 replies Open on X →

@manishkumar_dev The queue-free part alone would make me give Seedance 2.5 a try. 134 views · 1 likes · 0 reposts · 0 replies Open on X →

@manishkumar_dev The $0.097/sec pricing is impressive. Excited to try Dreamina 100 views · 1 likes · 0 reposts · 0 replies Open on X →