Diadems Tech

Claude Code can design Animated social media posts now. Prompt below 👇

@melvynx j'ai l'impression d'avoir perdu un pote...

Day 3 with OpenClaw: In all my tests, GPT 5.4 is consistently the worst model for agentic tasks. Lazy, stupid, never follows anything, feels like you are a baby sitter. I don't know how OpenAI manages to make such a shitty model but this feels terrible. I miss Opus.

glad they banned openclaw, the servers are finally reliable again

13,500 GitHub ⭐ in just a few days for a newly open-sourced project. 🤯 And for good reason. Paperclip by @dotta isn't just another AI wrapper, it's a powerful Node.js backend and React dashboard designed to tame the wild west of AI agents. You need Paperclip if you: 🧠 Have 20 Claude tabs open and can't remember who is doing what. 🤖 Rely on different types of agents (Codex, OpenClaw) and need them to collaborate. 📈 Want agents working for you 24/7 with fully auditable work and costs. 🚀 Want to build an autonomous business, not spend your days managing pull requests. Here is why the entire dev timeline is obsessed with it right now: → It forces structure: Budgets, org charts, and goal alignments are built right in. → Deep integration: It coordinates tasks atomically with models like OpenClaw. → Removes the mental load: You manage the vision, the agents handle the execution. Any agent, any runtime, with seamless coordination and zero lock-in. 🔥 Also an MIT-licensed, fully open-source project that's moving incredibly fast with a great Discord community. Link to the repo in 🧵↓

Stop drowning in the 847-page Clawbot / @OpenClaw docs. This one-page cheat sheet condenses EVERYTHING you need 👇

⚠️ #Clawdbot / #MoltBot : ne faites confiance à AUCUNE skill ClawdHub sans avoir lu le code source en entier. Des milliers de DL sur des skills malveillantes ces derniers jours (prompt injection, backdoors, etc.) Never trust. Always verify. cc @sdrzn

Introducing GLM-4.7-Flash: Your local coding and agentic assistant. Setting a new standard for the 30B class, GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight deployment option. Beyond coding, it is also recommended for creative writing, translation, long-context tasks, and roleplay. Weights: huggingface.co/zai-org/GLM-4.… API: docs.z.ai/guides/overvie… - GLM-4.7-Flash: Free (1 concurrency) - GLM-4.7-FlashX: High-Speed and Affordable

Stanford published the exact lectures used to train some of the world’s best AI engineers. Here are 7 outstanding AI lecture series you can watch for free right now. Covers AI fundamentals through modern LLMs 🧵 ↓

Bonne année 2026 à tous ! 🎉 Je vous souhaite une année remplie de petits bonheurs, de grandes réussites et surtout une santé de fer. Prenez soin de vous et de vos proches ! ❤️

Project page: apple.github.io/ml-sharp/ Discuss on HuggingFace: huggingface.co/apple/Sharp

Yess! @Vercel just dropped their open-source visual agent and workflow builder! 🔥 ▪️ Built on useworkflow.dev ▪️ Outputs “use workflow” code ▪️ AI text→workflow ▪️ AI SDK + Elements ▪️ Integrations: Resend, Linear, Slack Demo + free template in 🧵↓

how do Adaline and Apple make these crazy 3d zooming effects as you scroll? it's easier than you think - let me show you how prompts and code in thread:

Pauvre France 🥀… Quand donc nos politiques auront-ils l’audace de briser les chaînes de cette mascarade funeste ? Quand allons-nous retrouver la bonne voie ? Est-ce encore possible, ou sommes-nous définitivement perdus… youtube.com/watch?v=pncXDm… Merci @EricLarch 🙏

@LayerAddition x.com/Fluxora_Design…

You do not want to miss the MCP updates & announcements from Windows, Gradio, Caucus, Anthropic, Firecrawl, Postman, Perplexity, Cline, and more this week!  I summarized everything you need to know below.  (save for later)

Every memory → a vector. Your life → a dataset. Run a LLM on it. You get an AI that thinks like you. Talks like you. But without your bugs. #Neuralink #AI #AGI #MindUpload

ELEVENLABS WHO? This voice AI is open-source, ultra-expressive, and actually beats ElevenLabs in quality. No paywalls. No weird licensing. Just pure, controllable speech synthesis — built for creators and devs. Here’s the model everyone’s switching to: 👇

GPT-4o images can now talk. You can create a human that doesn’t exist Make it speak exactly what you want Add emotion, tone, perfect delivery Reality is OVER... Here’s how to pull it off in 30 seconds 👇

trackers v2.0.0 is out combo object detectors from top model libraries with multi-object tracker of your choice for now we support SORT and DeepSORT; more trackers coming soon link: github.com/roboflow/track…