Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇

Florian S

4,948 subscribers

54,319 views • 1 year ago •via X (Twitter)

Education Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

introducing Krea API. turn your workflows or trainings into endpoints and access any of the models we serve in Krea through our new API platform. learn how to get started 👇

introducing Krea API. turn your workflows or trainings into endpoints and access any of the models we serve in Krea through our new API platform. learn how to get started 👇

KREA AI

113,132 views • 7 months ago

We are introducing v0-1.5-md and v0-1.5-lg, our newest models for UI generation and web development. Available today on Coming to the API next week.

We are introducing v0-1.5-md and v0-1.5-lg, our newest models for UI generation and web development. Available today on Coming to the API next week.

v0

131,019 views • 1 year ago

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks AI in the US.

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks AI in the US.

Warp

14,154 views • 1 year ago

OpenClaw is replacing entire workflows and most people can't even set one up. 1.5M+ API keys leaked on GitHub this year. Self-hosting OpenClaw? Exposed IPs. Leaked keys. Config nightmares. Hours wasted. Introducing Spawnr. no API keys. No setup. No servers. Instant model switching. One click. Built-in UI. Telegram. Secure. Spawn your AI agent in seconds → spawnr.io Start for free → Soon supporting nanobot by Xubin Ren 👀

OpenClaw is replacing entire workflows and most people can't even set one up. 1.5M+ API keys leaked on GitHub this year. Self-hosting OpenClaw? Exposed IPs. Leaked keys. Config nightmares. Hours wasted. Introducing Spawnr. no API keys. No setup. No servers. Instant model switching. One click. Built-in UI. Telegram. Secure. Spawn your AI agent in seconds → spawnr.io Start for free → Soon supporting nanobot by Xubin Ren 👀

Potato

18,110 views • 5 months ago

Introducing 3 UNLIMITED models available now on Freepik💥 Seedream 4.5, Reve, and Z-image Like, comment + RT in the next hour. One winner gets 100K credits Details on each model in thread 🧵👇

Introducing 3 UNLIMITED models available now on Freepik💥 Seedream 4.5, Reve, and Z-image Like, comment + RT in the next hour. One winner gets 100K credits Details on each model in thread 🧵👇

Magnific

24,567 views • 7 months ago

Chain Free Web3: The Future of Multi-Chain Apps I am thrilled to announce the OneBalance API Early Access and to be working with MetaMask, OpenSea, and Wintermute to make a Chain Free Web3 a reality. Eliminate the complexity of chains, gas fees, and bridges for your users. Try out chain abstraction today. Be one of the first building on the OneBalance API.

Chain Free Web3: The Future of Multi-Chain Apps I am thrilled to announce the OneBalance API Early Access and to be working with MetaMask, OpenSea, and Wintermute to make a Chain Free Web3 a reality. Eliminate the complexity of chains, gas fees, and bridges for your users. Try out chain abstraction today. Be one of the first building on the OneBalance API.

Stephane

42,780 views • 1 year ago

BIG one for devs today. Introducing the Notion Developer Platform: - Notion CLI, ntn (Notion in your terminal) - Workers (run code on Notion's infra) - Database sync (any data source into Notion) - Agent tools (build any workflow) - Webhook triggers (trigger Notion from any app) - External Agents API (bring any agent into Notion) - Notion Agents SDK (use Notion Agents anywhere) - …and a bunch more API improvements And soon, you won't need to be a developer to build on Notion. Your agent will be one for you.

BIG one for devs today. Introducing the Notion Developer Platform: - Notion CLI, ntn (Notion in your terminal) - Workers (run code on Notion's infra) - Database sync (any data source into Notion) - Agent tools (build any workflow) - Webhook triggers (trigger Notion from any app) - External Agents API (bring any agent into Notion) - Notion Agents SDK (use Notion Agents anywhere) - …and a bunch more API improvements And soon, you won't need to be a developer to build on Notion. Your agent will be one for you.

Notion

973,462 views • 2 months ago

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇

YanXbt

29,127 views • 24 days ago

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

alphaXiv

52,395 views • 8 months ago

Introducing the Branding format 🎨 You can now extract complete brand DNA from any website including color schemes, logos, frameworks and more in one API call Perfect for coding agents to clone or match existing site aesthetics. Try it out now on the playground or API today 👇

Firecrawl

111,093 views • 8 months ago

Introducing Replit ModelFarm, the fastest and safest way to build your next Generative AI app. Available for free on Hacker and Pro plans till October 15th. It requires zero setup, zero configuration, and zero API keys. With Replit ModelFarm, you can build a working Gen AI app in as little as 3 lines of code. Get started by installing the Replit AI library in any Python, JavaScript, or TypeScript Repl. The library implements an API for text completion, chat completion, and text embeddings. It supports streaming so your users can see model responses in real-time rather than waiting on a single output. All Hacker and Pro builders will have free access to a selection of Gen AI models offered by Google Cloud Vertex AI through Replit ModelFarm. All models are accessible from the development environment and any deployed app.

Introducing Replit ModelFarm, the fastest and safest way to build your next Generative AI app. Available for free on Hacker and Pro plans till October 15th. It requires zero setup, zero configuration, and zero API keys. With Replit ModelFarm, you can build a working Gen AI app in as little as 3 lines of code. Get started by installing the Replit AI library in any Python, JavaScript, or TypeScript Repl. The library implements an API for text completion, chat completion, and text embeddings. It supports streaming so your users can see model responses in real-time rather than waiting on a single output. All Hacker and Pro builders will have free access to a selection of Gen AI models offered by Google Cloud Vertex AI through Replit ModelFarm. All models are accessible from the development environment and any deployed app.

Replit ⠕

229,285 views • 2 years ago

Unveiling the DFlow Prediction Markets API Today, we give builders a direct, programmatic way to access real tokenized Kalshi markets natively on Solana The DFlow API is the first and only API to offer: • 100% market coverage • Full composability expected from onchain assets • Flexible redemptions of correct predictions in multiple stablecoins • Deepest liquidity onchain Build with DFlow

Unveiling the DFlow Prediction Markets API Today, we give builders a direct, programmatic way to access real tokenized Kalshi markets natively on Solana The DFlow API is the first and only API to offer: • 100% market coverage • Full composability expected from onchain assets • Flexible redemptions of correct predictions in multiple stablecoins • Deepest liquidity onchain Build with DFlow

DFlow

189,652 views • 7 months ago

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺

LM Studio

40,796 views • 5 months ago

The binoculars model, animations and UI have all been updated this month to feel more modern. 🔎☢️🎯 Right click to peer through the binoculars and left click to cycle the three zoom levels. And it pairs nicely with the new mortar! Read more on our DevBlog:

The binoculars model, animations and UI have all been updated this month to feel more modern. 🔎☢️🎯 Right click to peer through the binoculars and left click to cycle the three zoom levels. And it pairs nicely with the new mortar! Read more on our DevBlog:

Rust

51,628 views • 1 month ago

Native iOS split view is coming to React Navigation 🔜 Powered by React Native Screens 🫶 Let us know your use cases so we can test and ensure that the API is suitable for a wide range of usage 👇

Native iOS split view is coming to React Navigation 🔜 Powered by React Native Screens 🫶 Let us know your use cases so we can test and ensure that the API is suitable for a wide range of usage 👇

React Navigation

12,374 views • 3 months ago

ESMFold2 and the ESM-C family, now available for use! We’ve partnered with biohub (the ESM team’s new home), to provide day 1 access to their newly open-sourced series of models. The family of models show best-in-class results for structure prediction, de novo design, and protein-language model tasks.

ESMFold2 and the ESM-C family, now available for use! We’ve partnered with biohub (the ESM team’s new home), to provide day 1 access to their newly open-sourced series of models. The family of models show best-in-class results for structure prediction, de novo design, and protein-language model tasks.

Deniz Kavi

15,633 views • 1 month ago

Went too far… for real? The ImagineArt Black Friday Sale is LIVE. Get up to 66% OFF, invite up to 40 people, and access all top models for FREE - costing as low as $2.1 per person. 🔁 Retweet + Comment “ImagineArt Black Friday” to get 250 FREE credits in your DMs.

Went too far… for real? The ImagineArt Black Friday Sale is LIVE. Get up to 66% OFF, invite up to 40 people, and access all top models for FREE - costing as low as $2.1 per person. 🔁 Retweet + Comment “ImagineArt Black Friday” to get 250 FREE credits in your DMs.

ImagineArt

1,051,082 views • 7 months ago

You can now connect your OpenRouter URL directly to the Warp Agent. OpenRouter unlocks a world of models including Anthropic, OpenAI, Gemini, DeepSeek, Kimi, and more, all with better prices and uptime. Set your URL, model, and an alias to easily switch using /model.

You can now connect your OpenRouter URL directly to the Warp Agent. OpenRouter unlocks a world of models including Anthropic, OpenAI, Gemini, DeepSeek, Kimi, and more, all with better prices and uptime. Set your URL, model, and an alias to easily switch using /model.

Warp

15,097 views • 1 month ago

Lovable will be free to use for everyone on International Women's Day this Sunday in partnership with Anthropic. Over 120 in-person events are being hosted across the globe by the Lovable SheBuilds community, and we're live-streaming from the Lovable office. See more details:

Lovable will be free to use for everyone on International Women's Day this Sunday in partnership with Anthropic. Over 120 in-person events are being hosted across the globe by the Lovable SheBuilds community, and we're live-streaming from the Lovable office. See more details:

Lovable

151,070 views • 4 months ago

Excited to announce Claude 3.7 Trend Finder 🔦 Use Anthropic's new model to monitor & extract trends on blogs and socials with and the X API. It collects posts from key influencers and sites, tracks the latest trends, and then pings you on Slack or Discord.

Excited to announce Claude 3.7 Trend Finder 🔦 Use Anthropic's new model to monitor & extract trends on blogs and socials with and the X API. It collects posts from key influencers and sites, tracks the latest trends, and then pings you on Slack or Discord.

Caleb Peffer (Hiring!)

67,931 views • 1 year ago