Hello. I'm Emir from France. I'm looking for a collaborator based on EU or North America. No technical skills, just only need smooth communication skill. Let's get in touch with me via telegram. Telegram : @softluna517 Thank you.

I canceled my Gamma subscription today haha Anthropic just launched Claude Design, a research preview tool where you collaborate with Claude to create polished visual assets like prototypes, slides, and one-pagers, then refine everything through chat. - Powered by Claude Opus 4.7 vision model, so it can actually “see” and work with visual layout - Starts from prompts, uploads (DOCX, PPTX, XLSX), images, or even your codebase, more paths from idea to output - Builds or applies your design system during onboarding by reading code and design files, consistent branding without manual cleanup - Inline comments, direct edits, and adjustment sliders, tighter feedback loops and less back and forth - Turns static mockups into interactive prototypes without code review/PRs, faster validation before engineering time - Exports to Canva, PDF, PPTX, HTML, easier handoff to the rest of the stack - One-step handoff bundle to Claude Code, hinting at a real design to build automation pipeline - Organization-scoped sharing and group collaboration, teams can iterate live in the same doc Read the full article here: https://www.anthropic.com/news/claude-design-anthropic-labs

Recently worked on an AI system for a music industry website redesign. There were two parts to it: 1. A public-facing AI chat widget for general queries + lead capture 2. A private, full-screen AI assistant inside the client portal. The second one was more interesting. The client didn’t just want “AI support” — they were concerned about users overusing it and burning unnecessary tokens. So instead of a typical chatbot, I designed a session-based interaction system: - Each user gets a 5-minute active window - At minute 4 → a warning is triggered (“1 minute left”) - At minute 5 → session ends + redirects to an external GPT - Then a 5-minute cooldown kicks in - After cooldown → user can start again It basically runs in a loop. What’s interesting is how this changes behavior: Users become more intentional with their questions instead of treating it like an endless chat. Also ended up optimizing one of their internal workflows in the process: A task that used to take ~6 hours manually is now done in under 10 minutes. No fancy theory here—just structuring AI usage in a way that actually makes sense operationally. Still experimenting with how far this “controlled AI interaction” approach can go.

Anthropic just dropped Claude Opus 4.7 and it is a massive win for anyone into automation. This new update is a major leap forward that focuses on turning Claude into a reliable agent that can handle complex projects from start to finish with way less babysitting. - Hand off the hardest coding tasks with total confidence because it now double checks its own work before reporting back. - Vision capabilities have tripled to support high resolution images up to 2576 pixels for reading dense screenshots or diagrams. - New adaptive thinking lets the model spend more time on hard problems while staying fast on the easy stuff. - Professional taste is built in to help you create higher quality slide decks and user interfaces that actually look good. - Advanced memory helps it remember important notes across long sessions so you don't have to repeat yourself. - The xhigh effort level gives us finer control over the tradeoff between deep reasoning and response speed. - $5/million base input tokens and $25/million output tokens Read more: https://www.anthropic.com/news/claude-opus-4-7

Google is reportedly testing a Gemini app for macOS, and the big upgrade is that it can use on-screen and in-app context to answer you more helpfully. - Gemini getting a standalone Mac app, not just web - "Desktop Intelligence" pulling context from open apps and your desktop, only when Gemini is in use - Similar screen-context features already in ChatGPT and Claude Mac apps, so the desktop AI race is heating up - Potential path toward AI that not only reads context, but eventually takes actions inside apps - Apple and Google partnership means Gemini tech is likely to show up in future Apple Intelligence experiences on macOS anyway If Gemini can see what we see on desktop, what would you guys actually trust it to do: summarize docs, write emails, debug code, run automations, or something bigger? Read the full article here: https://www.engadget.com/ai/google-is-reportedly-testing-a-gemini-app-for-mac-203703372.html