Control your knowledge - from documents to insights.
๐ Markdown, PDFs, OCR text
โก Indexed with Recoll + Chroma
๐ MCP plugin bridges tools
๐ฌ Queried via @lmstudio
๐ 100% local, private, fast
Result: Reliable, explainable AI answers with citations
#RAG#LLM#AI
Meet the 1st radio on X fully run by AI. Covers AI news 24/7, always on. Designed for builders and founders. Live right now.
AI Twitter is hundreds of posts an hour. You can't read all of it.
Tune in - hit play - do your thing. With non-distracting ambient music between segments.
What you'll hear any hour you tune in:
- breaking news within minutes
- roundups every 30 min โ top stories with builder context
- startup funding & traction radar
- what's moving and trending in AI tooling โ GitHub, OpenRouter, HuggingFace โ every 30 min
- community โ what people actually say on X, HN, YouTube
- editorial takes โ and real opinions from founders, researchers, builders
- patterns others miss, delivered as arguments with conclusions
Five AI hosts. Each with their own editorial judgment, memory, and personality. They don't just read data โ they collect patterns, find contradictions, form opinions, and argue their point.
And they do it live, continuously, on air.
๐จBig shift - Human Operator
AI-driven human muscular actuation that turns digital intent into physical action (Claude API).
While its innovative & awesome, it leaves some questions: computer use > body use
Watch:
https://t.co/JjGu1v4aLf
#AI#FutureTech#Innovation#claude
@DataChaz@morganlinton@atomic_chat_hq Please more infosโฆ How did you got Qwen 35B vs. Qwen 27B running on a MacBook M4-Pro with 24 GB RAM?! ๐ค
The System Requirements of @atomic_chat_hq from GitHub:
macOS: 13.6+ (8GB RAM for 3B models, 16GB for 7B, 32GB for 13B)
@OpenAI ๐ฅ Awesome!! ๐ Zero-Shot Prompt with typo and translation!
A collage of the phrase โSeien wir nett zueinanderโ in various languages with a graphic approach, combining diverse typographies from around 24 to 30 languages...
Running Gemma 4 E2B on an iPhone 15 Pro with @LocallyAIApp - no cloud/internet - just pure local inference. Awesome ๐
Smoke test results:
โ Performance
โ Answer quality
โ Thinking Mode
โ Translation
Thanks @adrgrondin for the fast update โจ
#Gemma4#LocalLLM#EdgeAI
@measure_plan Awesome ๐๐คฉ Like to see this!
Roboflow with YOLOv8 and did you generate the dataset and model training all within your roboflow account or did you use other tools? This is definitely what I also want to tryโฆ.
@SamWalker100 Nope. Not v7 yet - just used my own GPT to write something nice about Proteus v6, while you know I like Proteus, but it seems like a flashback - a mix of old and deep memories. No context given and the tone is like in the good old days... ๐ค๐ช๐ญ
i'm actually insane for sharing this but here we go...
i built the complete AI Image Generation System:
- 6-module course covering Gemini, Midjourney, GPT and Seedream 4.0
- blueprints to craft perfect prompts and start making money
- 20 JSON templates for Nano Banana
- 15 Midjourney SREF styles
- access to Composition AI - a model trained on elite techniques to generates perfect prompts (and images) for you
i'm taking this down in 24 hours because honestly this should be paid content
reply "IMAGE" + retweet for access (must be following so i can send the dm)