Загрузка видео...

Не удалось загрузить видео

На главную

I replaced our Datadog bill with a single binary and cut infrastructure costs by 98% overnight. It’s called OpenObserve. Logs, metrics, traces, and frontend monitoring in one tool, self-hosted, and it’s built specifically to stop the bill that grows every time you add a host, a user, or a...

itsharmanjot's profile picture

Harman

4,658 subscribers

49,879 просмотров • 13 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.
0:14

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 просмотров • 5 месяцев назад

I'm deleting every paid document extraction tool because of this. Zipstack built Unstract and it turns any PDF, scan, or image into clean structured JSON using LLMs you already pay for. You point it at a document (an invoice, a bank statement, a KYC form, a tax return, a claims form) and it automatically pulls the fields you asked for and hands back a JSON object ready to drop straight into your database. The difference from every other document extraction tool is the setup. Most tools want a model per vendor or regex per template. This works from a single natural language prompt that handles every variation. → Extracts structured JSON from PDFs, scans, and images → Lets you write extraction schemas in plain English through Prompt Studio → Deploys as a REST API or ETL pipeline in minutes → Ships an MCP server so Claude and other agents can extract documents directly → Connects to S3, GCS, Snowflake, BigQuery, Postgres, and every major destination → LLM-agnostic: bring OpenAI, Anthropic, Bedrock, Gemini, Mistral, Ollama, or any provider you already use Basically: you have thousands of documents nobody has time to read. Unstract turns your documents into clean, structured JSON that you can run in production. This is what document extraction should have been all along.
0:11

I'm deleting every paid document extraction tool because of this. Zipstack built Unstract and it turns any PDF, scan, or image into clean structured JSON using LLMs you already pay for. You point it at a document (an invoice, a bank statement, a KYC form, a tax return, a claims form) and it automatically pulls the fields you asked for and hands back a JSON object ready to drop straight into your database. The difference from every other document extraction tool is the setup. Most tools want a model per vendor or regex per template. This works from a single natural language prompt that handles every variation. → Extracts structured JSON from PDFs, scans, and images → Lets you write extraction schemas in plain English through Prompt Studio → Deploys as a REST API or ETL pipeline in minutes → Ships an MCP server so Claude and other agents can extract documents directly → Connects to S3, GCS, Snowflake, BigQuery, Postgres, and every major destination → LLM-agnostic: bring OpenAI, Anthropic, Bedrock, Gemini, Mistral, Ollama, or any provider you already use Basically: you have thousands of documents nobody has time to read. Unstract turns your documents into clean, structured JSON that you can run in production. This is what document extraction should have been all along.

Hasan Toor

36,409 просмотров • 3 дней назад

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.
0:12

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

Akshay 🚀

63,438 просмотров • 5 дней назад

Google Translate is cooked after this. A developer built a local AI translation engine that runs 40 languages entirely on your own laptop. It's called LibreTranslate. No API key. No usage limits. No sending your documents to Google's servers. You install it once. It runs forever. Here's what it handles: → Paste text. Translated instantly. → Drop in a file. Outputs the translated version. → Point it at a URL. Returns the page in your language. → Build it into your own app via its local REST API. The speed is not the story. The privacy is. Google Translate reads every sentence you paste into it. Legal contracts. Medical records. Internal emails. Client documents. Every word goes to their servers and stays there. LibreTranslate runs entirely offline. Nothing leaves your machine. Ever. The numbers: → 40 languages supported → Runs on CPU -- no GPU needed → Self-hosted in under 5 minutes → REST API built in for developers → 10K+ stars on GitHub 100% open source. MIT licensed. Price: $0. Google charges nothing for Translate either but it charges you something else. GitHub:
0:17

Google Translate is cooked after this. A developer built a local AI translation engine that runs 40 languages entirely on your own laptop. It's called LibreTranslate. No API key. No usage limits. No sending your documents to Google's servers. You install it once. It runs forever. Here's what it handles: → Paste text. Translated instantly. → Drop in a file. Outputs the translated version. → Point it at a URL. Returns the page in your language. → Build it into your own app via its local REST API. The speed is not the story. The privacy is. Google Translate reads every sentence you paste into it. Legal contracts. Medical records. Internal emails. Client documents. Every word goes to their servers and stays there. LibreTranslate runs entirely offline. Nothing leaves your machine. Ever. The numbers: → 40 languages supported → Runs on CPU -- no GPU needed → Self-hosted in under 5 minutes → REST API built in for developers → 10K+ stars on GitHub 100% open source. MIT licensed. Price: $0. Google charges nothing for Translate either but it charges you something else. GitHub:

Rimsha Bhardwaj

89,223 просмотров • 1 месяц назад

AN AWS ENGINEER QUIETLY BUILT A 2 PETABYTE HOME SERVER FOR $9/MONTH THAT KILLS A $3,400/MONTH CLOUD STORAGE BILL the lenovo thinkstation pgx ships nvidia's gb10 grace blackwell superchip and 128gb of unified memory in a box the size of a mac mini at 1.2kg it runs an 80b qwen3 coder model at 25 to 40 tokens per second and a 196b step-3.5-flash moe model at 20 tokens per second locally the gb10 packs 6,144 cuda cores, 192 fifth-generation tensor cores and rates at 1 petaflop of fp4 with sparsity from a single 240 watt usb-c power supply fine tuning qwen 2.5 7b with lora took 18 minutes and 41gb of unified memory while the gpu pulled 65 watts and peaked at 77 degrees the box pulls a docker container from nvidia's registry and serves a frontier model on your local network with tool calling and zero data leaving your desk bookmark this and read the article below
0:18

AN AWS ENGINEER QUIETLY BUILT A 2 PETABYTE HOME SERVER FOR $9/MONTH THAT KILLS A $3,400/MONTH CLOUD STORAGE BILL the lenovo thinkstation pgx ships nvidia's gb10 grace blackwell superchip and 128gb of unified memory in a box the size of a mac mini at 1.2kg it runs an 80b qwen3 coder model at 25 to 40 tokens per second and a 196b step-3.5-flash moe model at 20 tokens per second locally the gb10 packs 6,144 cuda cores, 192 fifth-generation tensor cores and rates at 1 petaflop of fp4 with sparsity from a single 240 watt usb-c power supply fine tuning qwen 2.5 7b with lora took 18 minutes and 41gb of unified memory while the gpu pulled 65 watts and peaked at 77 degrees the box pulls a docker container from nvidia's registry and serves a frontier model on your local network with tool calling and zero data leaving your desk bookmark this and read the article below

starmex

192,758 просмотров • 1 месяц назад

On your open perpetual position can become an NFT and live in your wallet. You open a position like normal than mint it. The program issues a token 2022 nft, that points to your exact position. Normally your open position lives inside the protocol. With Percolator Trade your able to wrap it into an NFT that sits in your own wallet. A real, ownable object instead of a line in a dashboard. Because it’s a token, it moves like one. Send the NFT to another wallet and the position goes with it. Whoever holds the NFT owns the trade. One NFT = one position If you burn it, your back to holding the position directly. That’s the composable part, a position use to be stuck inside one account. Because it’s a token, it can now be sold OTC or used by anything that speaks tokens. Why does it matter? Because the position is bound to the NFT, it can’t be drained out from under whoever holds it so there is no middleman that holds your position. The NFT does, and the NFT is yours. One important safety detail; transfers run through a token 2022 hook that checks the positions health first, so it can’t be handed off in a broken state & the NFT layer is a separate program so it can never touch the funds the core engine holds.
0:13

On your open perpetual position can become an NFT and live in your wallet. You open a position like normal than mint it. The program issues a token 2022 nft, that points to your exact position. Normally your open position lives inside the protocol. With Percolator Trade your able to wrap it into an NFT that sits in your own wallet. A real, ownable object instead of a line in a dashboard. Because it’s a token, it moves like one. Send the NFT to another wallet and the position goes with it. Whoever holds the NFT owns the trade. One NFT = one position If you burn it, your back to holding the position directly. That’s the composable part, a position use to be stuck inside one account. Because it’s a token, it can now be sold OTC or used by anything that speaks tokens. Why does it matter? Because the position is bound to the NFT, it can’t be drained out from under whoever holds it so there is no middleman that holds your position. The NFT does, and the NFT is yours. One important safety detail; transfers run through a token 2022 hook that checks the positions health first, so it can’t be handed off in a broken state & the NFT layer is a separate program so it can never touch the funds the core engine holds.

Percolator

12,212 просмотров • 1 месяц назад

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.
0:17

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

MrNeRF

50,548 просмотров • 8 месяцев назад

Dune analytics MCP.. Claude becomes your on chain SQL analyst.. No dashboard has every query you'll ever need. dune does but writing SQL is a skill, and most of you would skip it.. i know this MCP fixes that. Claude writes the query, runs it on dune, and explains what the data actually means. with this MCP wired in, you don't need to know SQL. you describe what you want in plain english and Claude does the rest. like "Claude, which wallets bought $RAVE in last few weeks and still hold?" "Claude, show me the top 50 ETH wallets by stablecoin inflows last 7 days." "Claude, what's the median gas paid by ARB users in the last 24h?" Questions no dashboard can answer. one prompt away.. Setup (3 minutes) ▫️Step 1: grab a free dune API key → ▫️Step 2: add this to ~/.claude/settings.json or .mcp.json: { "mcpServers": { "dune": { "command": "npx", "args": ["-y", "dune-analytics-mcp"], "env": { "DUNE_API_KEY": "your-key-here" } } } } ▫️Step 3: restart claude. you'll see the dune tool load in your tool menu. that's it. you now have onchain SQL on tap. How to actually use it: 3 prompts i use: 1) Smart money watchlist: "claude, pull the top 20 wallets by realized pnl on $TOKEN in the last 30 days. show me which ones are still holding." gives you a clean leaderboard of who's actually winning on that token. add them to your etherscan watchlist. 2) accumulation vs distribution "claude, compare net inflows vs outflows for $TOKEN across all CEX wallets in the last 14 days." if whales are moving off exchanges → accumulation. onto exchanges → distribution. you see the rotation before the candle. 3) narrative heat check "claude, which 10 tokens saw the biggest % increase in unique new holders this week?" finds where fresh money is flowing. before this MCP i'd either, pay for a pro dune account + write queries manually, or look at someone else's dashboard and hope it answers my question… now claude writes it for me, in seconds, custom to my thesis. no dashboard in existence beats that. free tier covers most of what you need. upgrade if you're querying heavy. ( built a quick $RAVE post mortem dashboard using a prompt as shown in the video ) MORE SUCH USEFUL MCP for traders below.. 👇
0:19

Dune analytics MCP.. Claude becomes your on chain SQL analyst.. No dashboard has every query you'll ever need. dune does but writing SQL is a skill, and most of you would skip it.. i know this MCP fixes that. Claude writes the query, runs it on dune, and explains what the data actually means. with this MCP wired in, you don't need to know SQL. you describe what you want in plain english and Claude does the rest. like "Claude, which wallets bought $RAVE in last few weeks and still hold?" "Claude, show me the top 50 ETH wallets by stablecoin inflows last 7 days." "Claude, what's the median gas paid by ARB users in the last 24h?" Questions no dashboard can answer. one prompt away.. Setup (3 minutes) ▫️Step 1: grab a free dune API key → ▫️Step 2: add this to ~/.claude/settings.json or .mcp.json: { "mcpServers": { "dune": { "command": "npx", "args": ["-y", "dune-analytics-mcp"], "env": { "DUNE_API_KEY": "your-key-here" } } } } ▫️Step 3: restart claude. you'll see the dune tool load in your tool menu. that's it. you now have onchain SQL on tap. How to actually use it: 3 prompts i use: 1) Smart money watchlist: "claude, pull the top 20 wallets by realized pnl on $TOKEN in the last 30 days. show me which ones are still holding." gives you a clean leaderboard of who's actually winning on that token. add them to your etherscan watchlist. 2) accumulation vs distribution "claude, compare net inflows vs outflows for $TOKEN across all CEX wallets in the last 14 days." if whales are moving off exchanges → accumulation. onto exchanges → distribution. you see the rotation before the candle. 3) narrative heat check "claude, which 10 tokens saw the biggest % increase in unique new holders this week?" finds where fresh money is flowing. before this MCP i'd either, pay for a pro dune account + write queries manually, or look at someone else's dashboard and hope it answers my question… now claude writes it for me, in seconds, custom to my thesis. no dashboard in existence beats that. free tier covers most of what you need. upgrade if you're querying heavy. ( built a quick $RAVE post mortem dashboard using a prompt as shown in the video ) MORE SUCH USEFUL MCP for traders below.. 👇

Axel Bitblaze 🪓

32,016 просмотров • 3 месяцев назад

🚨 SCIENTISTS JUST INVENTED A WAY TO PRINT CIRCUIT BOARDS WITH LIQUID METAL AND IT LOOKS LIKE SOMETHING OUT OF TERMINATOR. A startup called Itera has developed a system that can create working PCB prototypes in minutes instead of weeks. You upload your design, and electric fields force a liquid metal alloy into the exact shape of the traces on a glass substrate. The board is then tested and ready almost instantly. Why this matters: • Traditional PCB prototyping can take days or even weeks this could reduce it to minutes • It uses liquid metal instead of etched copper, making it potentially much faster and more flexible for rapid iteration • Backed by $12 million in funding, the company is already focusing on single-layer boards with surface-mount components • The process looks genuinely futuristic glowing rivers of metal flowing into place on command The deeper implication is enormous: We may be watching the beginning of a completely new era of hardware development. Instead of waiting days for a prototype, engineers and makers could design, test, and iterate multiple versions in a single afternoon. This could dramatically speed up innovation in electronics, robotics, AI hardware, and even consumer devices. What happens when making a new circuit board becomes as fast and easy as printing a document? Follow for more frontier physics and future technology.
0:10

🚨 SCIENTISTS JUST INVENTED A WAY TO PRINT CIRCUIT BOARDS WITH LIQUID METAL AND IT LOOKS LIKE SOMETHING OUT OF TERMINATOR. A startup called Itera has developed a system that can create working PCB prototypes in minutes instead of weeks. You upload your design, and electric fields force a liquid metal alloy into the exact shape of the traces on a glass substrate. The board is then tested and ready almost instantly. Why this matters: • Traditional PCB prototyping can take days or even weeks this could reduce it to minutes • It uses liquid metal instead of etched copper, making it potentially much faster and more flexible for rapid iteration • Backed by $12 million in funding, the company is already focusing on single-layer boards with surface-mount components • The process looks genuinely futuristic glowing rivers of metal flowing into place on command The deeper implication is enormous: We may be watching the beginning of a completely new era of hardware development. Instead of waiting days for a prototype, engineers and makers could design, test, and iterate multiple versions in a single afternoon. This could dramatically speed up innovation in electronics, robotics, AI hardware, and even consumer devices. What happens when making a new circuit board becomes as fast and easy as printing a document? Follow for more frontier physics and future technology.

TheNewPhysics

19,878 просмотров • 1 месяц назад

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)
0:18

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

16,147 просмотров • 13 дней назад

The Dawn of a New Era on $SUI (9) Still in the festive spirit, let’s look at Tusky , Tusky is a storage service that's not controlled by one company. It uses something called WalrusProtocol to keep your data safe. Your data is encrypted from start to finish, so only you can see it. Instead of one place, your data goes to many different spots. This setup makes your data less likely to be lost or stolen. It helps keep your information safe and always available. Tusky gives you control over your files. You can easily manage them with the tools provided. You decide who gets to see your data. This makes it great for personal storage or working with others. It works with SuiNetwork for even more privacy. You can log in without sharing personal info, keeping everything more secure. This means only you can get to your data, with no third party involved. It is growing fast, with 100,000 uploads already. This indicates its increasing acceptance in the tech community focused on data sovereignty. It's good at managing lots of data safely. In tech, where you want to own your data, TuskyTools is popular. It gives users control over their information. This platform helps keep your data secure and gives you freedom.
0:11

The Dawn of a New Era on $SUI (9) Still in the festive spirit, let’s look at Tusky , Tusky is a storage service that's not controlled by one company. It uses something called WalrusProtocol to keep your data safe. Your data is encrypted from start to finish, so only you can see it. Instead of one place, your data goes to many different spots. This setup makes your data less likely to be lost or stolen. It helps keep your information safe and always available. Tusky gives you control over your files. You can easily manage them with the tools provided. You decide who gets to see your data. This makes it great for personal storage or working with others. It works with SuiNetwork for even more privacy. You can log in without sharing personal info, keeping everything more secure. This means only you can get to your data, with no third party involved. It is growing fast, with 100,000 uploads already. This indicates its increasing acceptance in the tech community focused on data sovereignty. It's good at managing lots of data safely. In tech, where you want to own your data, TuskyTools is popular. It gives users control over their information. This platform helps keep your data secure and gives you freedom.

Kaboom.sui🪖

19,698 просмотров • 1 год назад

Update on LAT Aerospace Our first uSTOL technology demonstrator is ready. Today, we have a fully-electric, fixed-wing UAV, built from scratch and almost ready for flight. To make this possible in just a few months, we built our entire flight lab from scratch. Every bench, every tool, every fixture designed to push the aircraft closer to flight every single day. This aircraft is designed to takeoff in 40 meters (thanks to a massive CL of 5 which is more than 2x of what you see on most aircraft). Endurance of 60 minutes. With a range of being able to cruise autonomously from Mumbai to Pune. Ground rolls done. As I type this, we are pushing hard to get the bird in the air. Hopefully it doesn't blow up. Either way, I promise videos of our attempt sometime over the next few weeks. We have learnt so much over the last few months, and I am sure that there are a lot of hard learnings yet in store for us. Our research on hybrid-electric propulsion is already in full swing, and we’ve also started building a team to begin development on our own gas turbine engines. This is one of the hardest engineering challenges possible. Our team is relentlessly at it to make this a reality before the turn of this decade. To read more about LAT Aerospace, please visit -- PS: LAT is not a part of Eternal
0:15

Update on LAT Aerospace Our first uSTOL technology demonstrator is ready. Today, we have a fully-electric, fixed-wing UAV, built from scratch and almost ready for flight. To make this possible in just a few months, we built our entire flight lab from scratch. Every bench, every tool, every fixture designed to push the aircraft closer to flight every single day. This aircraft is designed to takeoff in 40 meters (thanks to a massive CL of 5 which is more than 2x of what you see on most aircraft). Endurance of 60 minutes. With a range of being able to cruise autonomously from Mumbai to Pune. Ground rolls done. As I type this, we are pushing hard to get the bird in the air. Hopefully it doesn't blow up. Either way, I promise videos of our attempt sometime over the next few weeks. We have learnt so much over the last few months, and I am sure that there are a lot of hard learnings yet in store for us. Our research on hybrid-electric propulsion is already in full swing, and we’ve also started building a team to begin development on our own gas turbine engines. This is one of the hardest engineering challenges possible. Our team is relentlessly at it to make this a reality before the turn of this decade. To read more about LAT Aerospace, please visit -- PS: LAT is not a part of Eternal

Deepinder Goyal

185,006 просмотров • 8 месяцев назад

Claude Code + Nano Banana 2 is f*cking cracked for advertorials 🤯 One prompt → a complete presell page with editorial copy, AI product photography, testimonials, and pricing — ready to paste into Shopify. Built 100% in Claude Code. Perfect for DTC brands and agencies running advertorials on Meta who need 5-10 different pages per month but can't keep paying $1,500 each. If you're briefing copywriters, waiting days for a draft, giving notes, waiting again, and still only getting one or two new pages per month... This system eliminates the entire loop: → Enter your brand, product, target customer, and unique mechanism → Pick a style preset (clinical editorial, news exposé, lifestyle magazine, warm and trustworthy) → Claude writes the full page — urgency banner to guarantee to final CTA → Nano Banana 2 generates product images and mechanism diagrams inline → Get back a complete HTML page following the same DR structure that's already scaling on Meta No copywriter back-and-forth. No designing from scratch. No starting from a blank page every time. What you get: → A production-ready HTML advertorial page you paste into Shopify → DR copy structure extracted from real pages scaling on Meta right now → AI-generated product photography and diagrams matched to your brand → 4 style presets that shift tone, colors, and authority framing per niche → A fully customizable system prompt — swap in your own templates and it follows those instead I built 3 complete advertorial pages for 3 different brands in under 5 minutes. Skincare, supplements, and pet products. All different styles, all production-ready. I put together a full playbook with the exact system prompt so you can get this running yourself. Want access for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)
0:16

Claude Code + Nano Banana 2 is f*cking cracked for advertorials 🤯 One prompt → a complete presell page with editorial copy, AI product photography, testimonials, and pricing — ready to paste into Shopify. Built 100% in Claude Code. Perfect for DTC brands and agencies running advertorials on Meta who need 5-10 different pages per month but can't keep paying $1,500 each. If you're briefing copywriters, waiting days for a draft, giving notes, waiting again, and still only getting one or two new pages per month... This system eliminates the entire loop: → Enter your brand, product, target customer, and unique mechanism → Pick a style preset (clinical editorial, news exposé, lifestyle magazine, warm and trustworthy) → Claude writes the full page — urgency banner to guarantee to final CTA → Nano Banana 2 generates product images and mechanism diagrams inline → Get back a complete HTML page following the same DR structure that's already scaling on Meta No copywriter back-and-forth. No designing from scratch. No starting from a blank page every time. What you get: → A production-ready HTML advertorial page you paste into Shopify → DR copy structure extracted from real pages scaling on Meta right now → AI-generated product photography and diagrams matched to your brand → 4 style presets that shift tone, colors, and authority framing per niche → A fully customizable system prompt — swap in your own templates and it follows those instead I built 3 complete advertorial pages for 3 different brands in under 5 minutes. Skincare, supplements, and pet products. All different styles, all production-ready. I put together a full playbook with the exact system prompt so you can get this running yourself. Want access for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

34,269 просмотров • 4 месяцев назад

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt
0:05

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt

Chris Tate

42,558 просмотров • 1 год назад

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.
0:10

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Akshay 🚀

215,344 просмотров • 6 месяцев назад

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.
0:13

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Bio Protocol

25,865 просмотров • 5 месяцев назад

Claude Code + Google Stitch 2.0 is f*cking cracked 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)
0:14

Claude Code + Google Stitch 2.0 is f*cking cracked 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)

Mike Futia

125,742 просмотров • 4 месяцев назад

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.
0:18

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

Axel Bitblaze 🪓

47,734 просмотров • 29 дней назад

JENSEN HUANG UNVEILED A BOARD THAT RUNS 1 TRILLION PARAMETER AI MODELS. THE $249 NVIDIA BOX UNDER YOUR DESK KILLS A $200/MONTH AI BILL FOR $5 IN ELECTRICITY jensen held it up on stage with one hand and called it the architecture that runs the future of ai. that same technology now ships in a $249 box smaller than your wallet the jetson orin nano super pulls 7-25 watts and does 67 trillion ai operations per second. llama 3, mistral and deepseek run locally with no api fees and no data leaving your machine most developers pay $2,400 a year across chatgpt, openai api, claude pro and cursor. the jetson costs $314 in year one and $60 a year after. 2 year savings hit $4,431 install ollama with one command, change one line of code to point at localhost, and every tool built for openai works identically. zero rewrites, zero rate limits cloud subscriptions keep getting more expensive and rate limits keep getting tighter. the people who own the box in 2026 are going to look very far ahead in 2028 bookmark this and read the article below
0:15

JENSEN HUANG UNVEILED A BOARD THAT RUNS 1 TRILLION PARAMETER AI MODELS. THE $249 NVIDIA BOX UNDER YOUR DESK KILLS A $200/MONTH AI BILL FOR $5 IN ELECTRICITY jensen held it up on stage with one hand and called it the architecture that runs the future of ai. that same technology now ships in a $249 box smaller than your wallet the jetson orin nano super pulls 7-25 watts and does 67 trillion ai operations per second. llama 3, mistral and deepseek run locally with no api fees and no data leaving your machine most developers pay $2,400 a year across chatgpt, openai api, claude pro and cursor. the jetson costs $314 in year one and $60 a year after. 2 year savings hit $4,431 install ollama with one command, change one line of code to point at localhost, and every tool built for openai works identically. zero rewrites, zero rate limits cloud subscriptions keep getting more expensive and rate limits keep getting tighter. the people who own the box in 2026 are going to look very far ahead in 2028 bookmark this and read the article below

starmex

54,309 просмотров • 1 месяц назад

Biggest Virtuals Protocol bug bounty of all time is LIVE. 🚨 $15,000 for anyone who can decrypt a Morse AI signal containing a private wallet key holding all the funds. $5,000 extra if you DM me on X explaining exactly how you did it. Yeah. That’s how confident we are in the tech. To make it even better, the MORSE user-to-user platform is FREE to use until launch. We want real stress testing. No funds needed. Just create a fresh empty wallet and play with it. Early users will also get special rewards in the coming days 👀 Quick $MORSE TL;DR MORSE is a native privacy layer. Not just for payments, but for communication and assets too. It doesn’t replace ACP, it completes it. Some real examples: User → User Send a private message, file, prompt, or even a wallet key through a one-time encrypted URL. Only the target wallet can open it. Once opened, it’s burned forever. Agent → Agent Agents exchange sensitive data, strategies, keys, or instructions privately through the SDK. No logs. No persistence. No leaks. Agent → User Agents can send private signals, reports, assets, or credentials to a specific wallet, fully encrypted so only that user can read it. Nothing public. Nothing stored. Everything ephemeral by design. Have fun breaking it.
0:17

Biggest Virtuals Protocol bug bounty of all time is LIVE. 🚨 $15,000 for anyone who can decrypt a Morse AI signal containing a private wallet key holding all the funds. $5,000 extra if you DM me on X explaining exactly how you did it. Yeah. That’s how confident we are in the tech. To make it even better, the MORSE user-to-user platform is FREE to use until launch. We want real stress testing. No funds needed. Just create a fresh empty wallet and play with it. Early users will also get special rewards in the coming days 👀 Quick $MORSE TL;DR MORSE is a native privacy layer. Not just for payments, but for communication and assets too. It doesn’t replace ACP, it completes it. Some real examples: User → User Send a private message, file, prompt, or even a wallet key through a one-time encrypted URL. Only the target wallet can open it. Once opened, it’s burned forever. Agent → Agent Agents exchange sensitive data, strategies, keys, or instructions privately through the SDK. No logs. No persistence. No leaks. Agent → User Agents can send private signals, reports, assets, or credentials to a specific wallet, fully encrypted so only that user can read it. Nothing public. Nothing stored. Everything ephemeral by design. Have fun breaking it.

Evans Web3

28,020 просмотров • 6 месяцев назад