Donnie

I'm clearly not an influencer but here's my Build Small Hackathon submission anyway - Orion's Cottage 🌌 on @huggingface Skyfield, starplot, 3 small models MiniCPM (EN), Aya (FR), Nemotron (expert brief). Parallel polish on Modal. Off Grid + red-light for the field. @Gradio @cohere @modal @nvidia @OpenBMB #BuildSmallHackathon

@cursor_ai @SpaceX Huzzah, reset tokens?

We're excited to join forces with @SpaceX to advance the frontier of useful AI. Expect significant improvements to Cursor soon.

@swyx @TomasReimers @cursor_ai Didn't you say git was on the way out?

Cursor/Graphite’s @TomasReimers just announced Origin @cursor_ai’s long awaited Git competitor, scalable for agent workloads, extensible with api and mcp, and built in merge conflicts and co failure agent resolution

@UvA_Amsterdam @TheyCallMeMr_ @johnamqdang @mgalle @mziizm @ahmetustun89 @beyzaermis Announcing new research on cultural representation across LLM training data. 🌪️🏷️🕵️🗺️ Led by @ananya__sahu, @mhrnz_m, @mrdanieldsouza, @rsrchvslstrytlr, Julia Kreutzer, and @mziizm 📜Read the paper: arxiv.org/abs/2606.13808

@jxnlco Not for previous subscribers though.

wow hit 100k so, one of the biggest requests is about resetting rate limits, so heres a tip. Codex now has referrals that give you the ability to reset your rate limit on your time

@joshwoodward @GeminiApp Gave it a shot!

Want unreleased @GeminiApp features before anyone else? Love breaking, testing, and shaping new tech? We're opening a limited number of slots for power users to join the Gemini Trusted Tester program. Sign up here: goo.gle/4onCRHq

@tokifyi Japan has @SakanaAILabs

🇺🇸 USA → OpenAI + Anthropic 🇨🇦Canada → Cohere 🇫🇷 France → Mistral 🇨🇳 China → DeepSeek + Qwen Your country?

does switching models always start a new session? @skcd42

@japan_nobunaga Pretty much yes.

I bumped into someone online and they apologized three times before I could type "sorry" back. They had a Canadian flag in bio 🇨🇦 Is "sorry" a Canadian reflex? What's the most Canadian thing you've done without realizing it?

@DanielSmidstrup How do I get there?

6.2k followers on day 76 🥳 Consistency is key!

For those using oauth for openclaw and or Hermes. Does @grok or @OpenAI regular plan last a month?

@HermesAgentTips Will they remember when they do get feelings...

got over 5K followers but I need to know who’s not a bot… answer this.. do bots have feelings?

@benln I'm building LingoShadow on @huggingface & @Gradio , a tool that generates audio clips of useful sentences for a learner's typically use cases in their target language. The strategy is called language shadowing, which is how toddlers learn to speak: huggingface.co/spaces/build-s…

Built MatchWise 🃏 An AI-powered memory game with infinite emoji levels, lives, leaderboard, and a Performance Meter that unlocks Challenge levels. Powered by MiniCPM5 + Gradio + llama.cpp HF Space: huggingface.co/spaces/build-s… @Gradio @huggingface @OpenBMB #llamacpp #buildSmall

@HuggingModels This is intriguing

Gemma 4 12B Coder is here and it's a game changer for local code generation. This GGUF model packs Google's latest gemma-4 architecture into a compact 12B size, perfect for running on consumer hardware. It's optimized for reasoning and thinking, making it ideal for developers who want fast, private coding assistance without the cloud.

Sovereign AI capabilities in more than one democracy is essential to the democratic project. Come contribute to Cohere’s mission.

@thsottiaux What about decent amateur work?

I have a new kind of big button that I can press for Codex. Over the next 100 days, we will select one person per day who does impressive or incredibly useful work with Codex and give them 10X usage limits for a month to see what they can do with it. First one tomorrow.

thank you @cursor_ai "Power user grant" 🙏

@skcd42 sub-agent animation is awesome!

got cooked so hard its beyond "well done"

@GoogleAIStudio @huggingface build small hackathon with @codex @grok and @antigravity

What are you vibe coding this weekend?