Vlado Ivanković

An early beta of Grok Build, an agentic CLI for coding, building apps, and automating workflows is now available for SuperGrok Heavy subscribers. Through this early beta, we will improve the model and product based on your feedback. Try it at x.ai/cli

Introducing Shark Rating ift.tt/UDZkrKn #PHP #Projects

@Anaya_sharma876 Next step delete Meta AI 😂

I just deleted Claude and installed Meta AI, now tell me the next steps.

@neerajjj6785 Pascal 🧮

Programming Languages and their AI Replacement Risk •🧊 HTML/CSS — 🔴 Highest •🟣 Visual Basic — 🔴 Highest •🐘 PHP — 🔴 High •🐫 Perl — 🔴 High •🎵 Groovy — 🔴 High •🟨 JavaScript — 🟠 Medium •🐍 Python — 🟠 Medium •💎 Ruby — 🟠 Medium •🎯 Dart — 🟠 Medium •🐦 Swift — 🟠 Medium •🌙 Lua — 🟠 Medium •☕ Java — 🟡 Low •🟣 C# — 🟡 Low • 🅺 Kotlin — 🟡 Low •🔺 Scala — 🟡 Low •🧬 Julia — 🟡 Low •💧 Elixir — 🟡 Low •🐹 Go — 🔵 Very Low •🔧 C — 🔵 Very Low •🚀 C++ — 🔵 Very Low •🦀 Rust — 🔵 Very Low •⚡ Zig — 🔵 Very Low •⚙️ Assembly — 🔵 Very Low •🧮 Fortran — 🔵 Very Low

What’s next after AI?

Come to the Duck side. #Maythe4thBeWithYou 👀

Only 4 questions without editing code 🙈 #Opus #Claude #AI

@Its_Nova1012 GLM

Which open source AI model are you using? - Qwen 3.5 - DeepSeek v4 - Llama 4 Maverick - Kimi K2.6 And what's main the reason behind it?

@psomkar1 For frontend GPT with codex In-app browser

As a dev , which model do you prefer for the frontend ?

@Surendar__05 GBT Plus + Claude Pro + GLM pro

Be honest guys, if you’re building an app from scratch, which subscription is worth it right now?

@0xPrajwal_ hype 🦆

Is it hype, or are people really moving from Claude to Codex?

GPT-5.5 VS OPUS 4.7 🤖#ai

@arena @OpenAI It's not realistic.

GPT-5.5 by @OpenAI is now live in the Arena, landing across multiple leaderboards. Here’s how it ranks by modality: - Code Arena (agentic web dev): #9, a strong +50pt jump over GPT-5.4 - Document Arena (analysis & long-content reasoning): #6, on par with Sonnet 4.6 - Text Arena: #7, Math #3, Instruction Following: #8 - Expert Arena: #5 - Search Arena: #2 - Vision Arena: #5 Strong, well-rounded performance, especially in Code (+50 pts vs GPT-5.4). Congrats to @OpenAI on the release. Full category breakdowns by modality in the thread.

Saturday isn’t a Break, it’s a Build.

🎉 Codeep v1.3.34 is out! Now available: 🚀 DeepSeek V4 Pro & Flash (1M context, 384k output) 🔥 OpenAI GPT-5.5 (new default) + GPT-5.4 variants Bug fix: GPT-5+ models now work correctly (temperature parameter handling) #AI #CLI #Developers #DeepSeek #OpenAI

The AI Coding Agent Built for the Terminal 🚀 codeep.dev 🧮 #ai #dev #cli #Artificialintelligence #Opensource

Codeep VS Code Extension v0.1.4 is out 🚀 New: interrupt & reply — type while the agent is working, press Enter to cancel and send your reply instantly. No more stopping the agent just to answer a question. Install: marketplace.visualstudio.com/items?itemName… #VSCode #AIcoding #DevTools #CodingAgent #OpenSource

Codeep v1.3.0 — now works with Ollama 🦙 Run AI coding sessions fully local. No API key, no cloud, no cost. codeep.dev/docs/providers Pick any installed model with /model Works local or remote (custom IP/port) Agent mode — use 7B+ models for best results #Ollama #LocalAI #CodingAssistant #OpenSource

🚀 Codeep v1.2.152 is out! A lot happened in this release: 🔒 Security — rate limiting on all API endpoints + auth fix for task fetching ⚠️ Token budget warnings — know when your agent is approaching the context limit (per-model accurate) 🔄 /sync command — sync your learning preferences & profiles across machines 📝 Debug logging — CODEEP_DEBUG=1 now writes to ~/.codeep/logs/ without breaking the UI ⚡ Retry logic — cloud sync now retries on network errors with exponential backoff Plus TypeScript 6.0, updated model pricing & context windows for all providers. codeep.dev

Codeep v1.2.135 is out! 🚀 GPT-5.4 support just dropped, plus we unlocked 8-hour agent runs, 10k iterations & 32k tokens. Let your CLI bots cook! #CLI #DevTools #OpenSource 💾 ift.tt/2mAIbBW