Elye

I'm on Mastodon too #Mastodon @elye" target="_blank" rel="nofollow noopener">androiddev.social/@elye

What If Every Mass Layoff Required the CEO to Quit? 🤔 medium.com/tech-ai-chat/w… #SocialResponsibility #Workforce #AI #Trend

Dev Phobia Words Evolution... #Programmer #Coding #ProgrammerHumour

Writing Code Might No Longer Free... medium.com/tech-ai-chat/c… #CodingJourney #Programming #Coding

Avoid MCP When Possible medium.com/tech-ai-chat/a… #Coding #AgenticCoding #MCP

Generating a $0.10 customised tutorial programming lessons content! Customised knowledge is cheaper than ever! medium.com/tech-ai-chat/w… #ArtificialIntelligence #Coding #Programming

Multiply your agentic coding potential even with just a single prompt. medium.com/tech-ai-chat/s… #AgenticAI #Coding #AI #AgenticCoding

Expanding Your AI Coding Skills by Understanding How VS Code Copilot Works Under the Hood and How Its Context Window Is Structured medium.com/tech-ai-chat/m… #Copilot #VSCode

Custom Agent: Beyond VS Code Copilot Agent, Ask and Plan Mode medium.com/tech-ai-chat/b… #VScode #Copilot

Plan mode: A Faster And Cost Efficient Path Than Just Vibe Coding Your Way Forward medium.com/tech-ai-chat/f… #aicoding #Claude #vscode

Claude Agent Skills - the Lazy Loading of AI Prompting medium.com/tech-ai-chat/l… #VSCode #AgentSkills

Why did we build Antigravity? Our Head of Product Engineering @kevinhou22 breaks this down in his keynote from @aiDotEngineer

Stop Using Groups in Xcode! Seven Reasons Folders Are Better — Especially for Legacy Projects medium.com/mobile-app-dev… #iOSDevelopment #Elye

The reception to @antigravity has been absolutely incredible. We've filled with gratitude. Let's do a little show and tell with what the community has been building! 👇

Google just dropped "Attention is all you need (V2)" This paper could solve AI's biggest problem: Catastrophic forgetting. When AI models learn something new, they tend to forget what they previously learned. Humans don't work this way, and now Google Research has a solution. Nested Learning. This is a new machine learning paradigm that treats models as a system of interconnected optimization problems running at different speeds - just like how our brain processes information. Here's why this matters: LLMs don't learn from experiences; they remain limited to what they learned during training. They can't learn or improve over time without losing previous knowledge. Nested Learning changes this by viewing the model's architecture and training algorithm as the same thing - just different "levels" of optimization. The paper introduces Hope, a proof-of-concept architecture that demonstrates this approach: ↳ Hope outperforms modern recurrent models on language modeling tasks ↳ It handles long-context memory better than state-of-the-art models ↳ It achieves this through "continuum memory systems" that update at different frequencies This is similar to how our brain manages short-term and long-term memory simultaneously. We might finally be closing the gap between AI and the human brain's ability to continually learn. I've shared link to the paper in the next tweet!

@OfficialLoganK Thank goodness for AI note-taking and summarization, or we’d never sleep!

You went 🍌🍌 for Nano Banana. Now, meet Nano Banana Pro.  It’s SOTA for image generation + editing with more advanced world knowledge, text rendering, precision + controls. Built on Gemini 3, it’s really good at complex infographics - much like how engineers see the world:)

My notes on Google's new Antigravity IDE - at first glance it looks like yet another VS Code fork but there are some interesting new ideas in there simonwillison.net/2025/Nov/18/go…

Claude code is good Codex is good Cursor is good Windsurf is good Cline is good Roo Code is good Kilo is good Amp is good OpenCode is good Aider is good

Computer Science is not science, and it's not about computers. Got reminded about this gem from MIT the other day

@rqobela COBOL

Programming language you learnd but never used again is...?