Shruti Codes's banner

Shruti Codes

@Shruti_0810 • 107,070 subscribers

Regular Tech & AI Updates 💻 | Sharing Free Resources 🌐 | Collabs: [email protected] | Daily Tech news

Shorts

Okay, this is a VERY different way to think about AI video. Instead of generating a clip and waiting for the result, Visko’s Orbis lets the world stream live. And the crazy part? You can change the prompt while it’s still running and watch the world respond. AI video is getting interctive now.

Okay, this is a VERY different way to think about AI video. Instead of generating a clip and waiting for the result, Visko’s Orbis lets the world stream live. And the crazy part? You can change the prompt while it’s still running and watch the world respond. AI video is getting interctive now.

32,409 görüntüleme

GOODBYE TO CYBERSECURITY! Someone just open-sourced an arsenal of AI hacking tools. Not one. Not ten. Hundreds. Inside the repository: • Jailbreak frameworks for LLMs • Prompt injection testing tools • AI red team agents • Model extraction utilities • Supply chain attack demos • Automated AI pentesting frameworks These are the same categories of tools security researchers use to find vulnerabilities before attackers do. Now anyone can study them. That's both exciting... and terrifying. The biggest threat to AI isn't smarter models. It's insecure ones. If you're building with LLMs and you're not actively testing your prompts, agents, and infrastructure— You're probably shipping vulnerabilities you don't even know exist. Open source is accelerating AI. It's also accelerating AI attacks. Repository link in the comments ↓

GOODBYE TO CYBERSECURITY! Someone just open-sourced an arsenal of AI hacking tools. Not one. Not ten. Hundreds. Inside the repository: • Jailbreak frameworks for LLMs • Prompt injection testing tools • AI red team agents • Model extraction utilities • Supply chain attack demos • Automated AI pentesting frameworks These are the same categories of tools security researchers use to find vulnerabilities before attackers do. Now anyone can study them. That's both exciting... and terrifying. The biggest threat to AI isn't smarter models. It's insecure ones. If you're building with LLMs and you're not actively testing your prompts, agents, and infrastructure— You're probably shipping vulnerabilities you don't even know exist. Open source is accelerating AI. It's also accelerating AI attacks. Repository link in the comments ↓

125,899 görüntüleme

One thing I think AI developers underestimate: Your model isn't always your biggest risk. Your infrastructure is. A lot of AI apps work great in development… Until the provider you're relying on has an outage, rate limits your requests, or a model suddenly becomes unavailable. If your entire product depends on one AI provider, you've created a single point of failure. That's why I like the approach CometAPI is taking. Instead of locking your app to one vendor, it gives you access to 500+ AI models through a single OpenAI-compatible endpoint. That means you can: → switch models without rewriting your integration → build fallback routes for better reliability → compare models as new ones launch → avoid getting locked into a single provider For teams building with Claude Code, Cursor, AI agents, SaaS products, or automation tools, that flexibility matters a lot once you're in production. They're also shipping new models quickly. Recent additions include: • GPT-5.6 • Happy Horse 1.1 • Kling Video Plus recently released: • Gemini 3.1 Flash Lite Image • Claude Sonnet 5 Worth checking out if you're building AI products that need to stay reliable as the ecosystem moves fast. Try it here: #AI #LLM #Developers #OpenAI #Claude #Cursor #ClaudeCode #BuildInPublic

One thing I think AI developers underestimate: Your model isn't always your biggest risk. Your infrastructure is. A lot of AI apps work great in development… Until the provider you're relying on has an outage, rate limits your requests, or a model suddenly becomes unavailable. If your entire product depends on one AI provider, you've created a single point of failure. That's why I like the approach CometAPI is taking. Instead of locking your app to one vendor, it gives you access to 500+ AI models through a single OpenAI-compatible endpoint. That means you can: → switch models without rewriting your integration → build fallback routes for better reliability → compare models as new ones launch → avoid getting locked into a single provider For teams building with Claude Code, Cursor, AI agents, SaaS products, or automation tools, that flexibility matters a lot once you're in production. They're also shipping new models quickly. Recent additions include: • GPT-5.6 • Happy Horse 1.1 • Kling Video Plus recently released: • Gemini 3.1 Flash Lite Image • Claude Sonnet 5 Worth checking out if you're building AI products that need to stay reliable as the ecosystem moves fast. Try it here: #AI #LLM #Developers #OpenAI #Claude #Cursor #ClaudeCode #BuildInPublic

56,822 görüntüleme

I didn't realize how much time I was wasting until I stopped having to type the same instructions every single time. Every prompt looked something like: – Use our colors – Match the existing UI – Keep it responsive – Follow accessibility best practices Now I just save it as a Skill in. From then on, it remembers the context for me. It's one of those features you don't think you need... until you use it once.

I didn't realize how much time I was wasting until I stopped having to type the same instructions every single time. Every prompt looked something like: – Use our colors – Match the existing UI – Keep it responsive – Follow accessibility best practices Now I just save it as a Skill in. From then on, it remembers the context for me. It's one of those features you don't think you need... until you use it once.

25,698 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

non aesthetic things Dads embarrassing their daughter on the beach

non aesthetic things Dads embarrassing their daughter on the beach

290,140 görüntüleme • 1 yıl önce

Your website doesn't need a redesign. It needs an honest audit. Most founders spend weeks changing headlines, tweaking CTAs, or redesigning pages... without knowing what's actually stopping people from converting. That's why I like what the team at Kite AI built. At you can get a free Growth Grader that audits your website across messaging, conversions, SEO, AI visibility, pricing, and technical health. It doesn't just tell you what's wrong it prioritizes the fixes that will have the biggest impact and even shows a before/after version of your homepage. The best part? No signup required. Just reply to Kite AI with your website URL, and it'll send back your Growth Grader in about 5 minutes. If you're building a startup, this is probably the easiest way to find out why your website isn't pulling its weight. Check out here:

Your website doesn't need a redesign. It needs an honest audit. Most founders spend weeks changing headlines, tweaking CTAs, or redesigning pages... without knowing what's actually stopping people from converting. That's why I like what the team at Kite AI built. At you can get a free Growth Grader that audits your website across messaging, conversions, SEO, AI visibility, pricing, and technical health. It doesn't just tell you what's wrong it prioritizes the fixes that will have the biggest impact and even shows a before/after version of your homepage. The best part? No signup required. Just reply to Kite AI with your website URL, and it'll send back your Growth Grader in about 5 minutes. If you're building a startup, this is probably the easiest way to find out why your website isn't pulling its weight. Check out here:

50,380 görüntüleme • 2 ay önce

A 300ms search doesn't sound slow... Until your agent makes 40-50 searches for a single task. Then it suddenly becomes the thing you're waiting on. Octen is taking a different approach by rebuilding search specifically for AI agents. Their published benchmarks show 62ms latency and $1 per 1,000 calls. Definitely worth checking out if you're building AI products.

A 300ms search doesn't sound slow... Until your agent makes 40-50 searches for a single task. Then it suddenly becomes the thing you're waiting on. Octen is taking a different approach by rebuilding search specifically for AI agents. Their published benchmarks show 62ms latency and $1 per 1,000 calls. Definitely worth checking out if you're building AI products.

33,333 görüntüleme • 1 ay önce

Tested DeepSeek V4 Flash on ZenMux today Tried a more practical approach instead of just chatting. → Asked it to build a SaaS landing page → Generated full HTML, CSS, JS → Ran the code → got a working UI It handled layout, components, and styling pretty smoothly. Iteration was simple too — just refine the prompt and improve the output. Also liked how easy it is to switch between models in the same place and test things side by side without changing setups. What stood out is how quickly you can go from idea → working frontend without jumping between tools. From a cost perspective, this kind of output is more than enough for a lot of routine dev tasks. Feels less like a “Claude killer” More like a “Claude bill killer.” If you want to try it yourself, I’ve added the link below 👇 Try it here: ZenMux

Tested DeepSeek V4 Flash on ZenMux today Tried a more practical approach instead of just chatting. → Asked it to build a SaaS landing page → Generated full HTML, CSS, JS → Ran the code → got a working UI It handled layout, components, and styling pretty smoothly. Iteration was simple too — just refine the prompt and improve the output. Also liked how easy it is to switch between models in the same place and test things side by side without changing setups. What stood out is how quickly you can go from idea → working frontend without jumping between tools. From a cost perspective, this kind of output is more than enough for a lot of routine dev tasks. Feels less like a “Claude killer” More like a “Claude bill killer.” If you want to try it yourself, I’ve added the link below 👇 Try it here: ZenMux

69,532 görüntüleme • 4 ay önce

AI agents have a memory problem. You create the perfect workflow, debugging process, or project setup... A few days later, you're teaching the same lessons all over again. Most AI workflows disappear the moment the chat ends. That's why EvoMap caught my attention. Instead of letting successful AI workflows vanish, it turns them into reusable assets that agents can learn from again and again. Check it out: 🧵

AI agents have a memory problem. You create the perfect workflow, debugging process, or project setup... A few days later, you're teaching the same lessons all over again. Most AI workflows disappear the moment the chat ends. That's why EvoMap caught my attention. Instead of letting successful AI workflows vanish, it turns them into reusable assets that agents can learn from again and again. Check it out: 🧵

34,376 görüntüleme • 3 ay önce

I stopped prompting AI today… And trained my own AI agent instead. I tested Panofy — The Best AI Agent for Expert-Level Tasks Here’s what happened 👇 Instead of repeating prompts again & again… You can train an agent once and it keeps working your way. Try it:

I stopped prompting AI today… And trained my own AI agent instead. I tested Panofy — The Best AI Agent for Expert-Level Tasks Here’s what happened 👇 Instead of repeating prompts again & again… You can train an agent once and it keeps working your way. Try it:

39,080 görüntüleme • 4 ay önce

🚨 Claude Code just got REPLACED overnight… for $0 An open-source project is now running a 122B model locally on your MacBook 🤯 No API fees. No cloud. No limits. Just raw power on your own machine. 1 command install. Double-click to launch. If this works at scale… it’s game over for paid AI tools. GitHub ↓

🚨 Claude Code just got REPLACED overnight… for $0 An open-source project is now running a 122B model locally on your MacBook 🤯 No API fees. No cloud. No limits. Just raw power on your own machine. 1 command install. Double-click to launch. If this works at scale… it’s game over for paid AI tools. GitHub ↓

40,749 görüntüleme • 4 ay önce

Most AI world models impress you for 20 seconds. The harder problem is making them stay coherent. That's what stood out to me in Robbyant's LingBot-World-Infinity. Instead of chasing another resolution headline, the paper focuses on reducing autoregressive drift the issue where small prediction errors compound until the world slowly falls apart. Their stress test is a single uninterrupted 60-minute rollout across 20 different scenarios with no visible quality decay. If you want to see the interactive system yourself, it's live on Reactor: 🎮 I also like that they don't pretend it's perfect. The paper openly says it doesn't have true long-term memory. Leave an area and come back later, and it regenerates something plausible instead of recalling the exact same place. That's a refreshingly honest limitation. Open weights make it even more interesting to dig into. Robbyant For anyone who wants to explore the research: 💻 GitHub: 🤗 Model Weights:

Most AI world models impress you for 20 seconds. The harder problem is making them stay coherent. That's what stood out to me in Robbyant's LingBot-World-Infinity. Instead of chasing another resolution headline, the paper focuses on reducing autoregressive drift the issue where small prediction errors compound until the world slowly falls apart. Their stress test is a single uninterrupted 60-minute rollout across 20 different scenarios with no visible quality decay. If you want to see the interactive system yourself, it's live on Reactor: 🎮 I also like that they don't pretend it's perfect. The paper openly says it doesn't have true long-term memory. Leave an area and come back later, and it regenerates something plausible instead of recalling the exact same place. That's a refreshingly honest limitation. Open weights make it even more interesting to dig into. Robbyant For anyone who wants to explore the research: 💻 GitHub: 🤗 Model Weights:

15,066 görüntüleme • 2 ay önce

No laptop. No tech background. Just… your voice. I opened Replit ⠕ on my phone, hit the mic, and said a simple 10-second prompt: “Build a landing page for a handmade coffee subscription brand.” And boom. Replit converted the voice note, understood the concept, and spun up an entire website in one go — clean layout, human-sounding headline, colors that matched the vibe… everything. The best part? I didn’t jump between apps. I didn’t Google templates. I just talked, tweaked a few things, and Replit filled in the rest automatically. And yes, this works right from your mobile too — perfect for those “random idea at 2 AM” moments. If you’ve been sitting on an idea or a brand concept, this is literally how fast you can turn it into something real. Give it a shot →

49,831 görüntüleme • 9 ay önce

The SaaS stack is breaking. Marketing. CRM. Sales. Support. Every new problem = another subscription. This Product Hunt launch is betting on a different future. One AI. Every department. Instead of adding AI to your tools... replace the tools with AI. Feels like we're moving from AI copilots... to AI operating businesses. If this works, "software stack" might become an outdated concept.

The SaaS stack is breaking. Marketing. CRM. Sales. Support. Every new problem = another subscription. This Product Hunt launch is betting on a different future. One AI. Every department. Instead of adding AI to your tools... replace the tools with AI. Feels like we're moving from AI copilots... to AI operating businesses. If this works, "software stack" might become an outdated concept.

16,074 görüntüleme • 2 ay önce

Developers won’t like this…😭 But 90% of “AI agents” we’ve been hyping are basically unstable interns with amnesia. They hallucinate. They loop. They forget instructions. A tiny 11-person team from Sweden just fixed ALL of it. Meet the first AI agent engine that actually works: Link : AI agents just entered their real era.

Developers won’t like this…😭 But 90% of “AI agents” we’ve been hyping are basically unstable interns with amnesia. They hallucinate. They loop. They forget instructions. A tiny 11-person team from Sweden just fixed ALL of it. Meet the first AI agent engine that actually works: Link : AI agents just entered their real era.

41,182 görüntüleme • 9 ay önce

Top 10 Insane Amazon Gadgets That Will Blow You Away 1. Water blaster amazon link :

Top 10 Insane Amazon Gadgets That Will Blow You Away 1. Water blaster amazon link :

50,544 görüntüleme • 1 yıl önce

TinyFish just made web search + fetch FREE for every AI agent. No credit card. No hacks. Just plug and go. Works everywhere I actually build: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • Claude Code + OpenClaw skills • LangChain / CrewAI And the best part? Full-browser fetch → clean markdown/JSON = no junk HTML = lower token costs = faster agents This is what agent stacks were missing. Try it:

TinyFish just made web search + fetch FREE for every AI agent. No credit card. No hacks. Just plug and go. Works everywhere I actually build: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • Claude Code + OpenClaw skills • LangChain / CrewAI And the best part? Full-browser fetch → clean markdown/JSON = no junk HTML = lower token costs = faster agents This is what agent stacks were missing. Try it:

19,860 görüntüleme • 4 ay önce

Stop using AI like a chatbot. It can literally run your research for you. They don’t work. They just… talk. Until now. I tested a setup that actually executes tasks: → Claude Code plans → XCrawl fetches real-time data → AI analyzes + delivers insights No fluff. Just output. I gave it a real task: “Analyze top candle brands, pricing & trends” What happened next was wild 👇 Instead of guessing: XCrawl: → searched competitors → crawled real product pages → returned structured data Claude: → compared pricing → spotted trends → delivered insights Result (in minutes): - actual price ranges - best-selling product types - real positioning strategies No tabs. No copy-paste. No manual research. This is the real shift: Old AI: “Here’s an answer.” New AI: “I’ve already done the work.” If you’re still using AI like Google… you’re already behind. Try it yourself (free 1,000 credits): Docs:

Stop using AI like a chatbot. It can literally run your research for you. They don’t work. They just… talk. Until now. I tested a setup that actually executes tasks: → Claude Code plans → XCrawl fetches real-time data → AI analyzes + delivers insights No fluff. Just output. I gave it a real task: “Analyze top candle brands, pricing & trends” What happened next was wild 👇 Instead of guessing: XCrawl: → searched competitors → crawled real product pages → returned structured data Claude: → compared pricing → spotted trends → delivered insights Result (in minutes): - actual price ranges - best-selling product types - real positioning strategies No tabs. No copy-paste. No manual research. This is the real shift: Old AI: “Here’s an answer.” New AI: “I’ve already done the work.” If you’re still using AI like Google… you’re already behind. Try it yourself (free 1,000 credits): Docs:

20,473 görüntüleme • 5 ay önce

WiFi Spy Camera A wireless camera you can hide in plain sight. With real-time monitoring via a connected device, it keeps you informed anywhere.

WiFi Spy Camera A wireless camera you can hide in plain sight. With real-time monitoring via a connected device, it keeps you informed anywhere.

22,450 görüntüleme • 1 yıl önce

Trojan Watch This advanced spy software tracks activities like keystrokes, screenshots, and active apps. The ultimate digital surveillance tool.

Trojan Watch This advanced spy software tracks activities like keystrokes, screenshots, and active apps. The ultimate digital surveillance tool.

20,249 görüntüleme • 1 yıl önce

Tired of AI app builders that lock you into subscriptions and limit your model choices? 🤔 Meet : The free, local, open-source vibe coding tool that actually sets you free. 💻 Runs on your computer (Mac/Windows) 🗝️Model freedom: Use any AI model (Gemini 2.5 Flash or Pro? Free OpenRouter ones? it’s your choice!) 🦋Zero lock-in: Integrates smoothly with editors like Cursor, VS Code, etc. ♾️Truly free: Build unlimited apps without restrictions It’s not just theory. 1000+ builders are already using it, 12+ releases shipped. Dyad is dropping updates weekly based on amazing community feedback. Stop renting your tools. Start owning them. 👉 Download Dyad free: (P.S. 👀Check out the momentum on Product Hunt too →) #opensource #developers #programmers #dsa #100daysofcode #letsconnect

Tired of AI app builders that lock you into subscriptions and limit your model choices? 🤔 Meet : The free, local, open-source vibe coding tool that actually sets you free. 💻 Runs on your computer (Mac/Windows) 🗝️Model freedom: Use any AI model (Gemini 2.5 Flash or Pro? Free OpenRouter ones? it’s your choice!) 🦋Zero lock-in: Integrates smoothly with editors like Cursor, VS Code, etc. ♾️Truly free: Build unlimited apps without restrictions It’s not just theory. 1000+ builders are already using it, 12+ releases shipped. Dyad is dropping updates weekly based on amazing community feedback. Stop renting your tools. Start owning them. 👉 Download Dyad free: (P.S. 👀Check out the momentum on Product Hunt too →) #opensource #developers #programmers #dsa #100daysofcode #letsconnect

18,154 görüntüleme • 1 yıl önce

5/ Keychain Camera Disguised as a car keychain, this compact device captures photos and videos. Perfect for on-the-go surveillance.

5/ Keychain Camera Disguised as a car keychain, this compact device captures photos and videos. Perfect for on-the-go surveillance.

15,716 görüntüleme • 1 yıl önce