Prompt
@engineerrprompt
Building http://whryte.com, Creator of localGPT | AI Educator
Yesterday I released the 'preview' of LocalGPT v2, and its already trending on Github Its an opinionated implementation of private RAG powered by local models via @ollama and @huggingface. Give it a ⭐️ on @github (🙏🙏) Watch the video in next post to learn how it was built...
Nano Banana Pro is here! It's a significant step in professional grade image generation and editing with text. It can do everything that the original Nano Banana could but with some new exciting capabilities. - built on Gemini 3, it can reason and iterate on images during its…
We just dropped Nano Banana Pro, built on Gemini 3. 🍌 With state-of-the-art text rendering, vast world knowledge and studio-quality creative controls, Gemini 3 Pro Image can create and edit more complex visuals, infographics and more. Here’s what’s under the hood. 🧵
This is big, go try it out!
🎉 Crawl4AI 0.7.7 is live, Self Hosting is the KING and QUEEN 🤴 🫅 Self hosting just leveled up. This release turns @crawl4ai into a real platform, not a library. You get a monitoring dashboard baked into Docker, open slash dashboard and you see the entire system breathing in…
Its launch Day! @Google Gemini 3 Pro is here! I had early access to the model and a gravity defying agent :) . Its a really good model with great vibes! SOTA in almost all regards. Here are some of my thoughts after extensively testing the model youtu.be/MPjOQIQO8eQ
youtube.com
YouTube
Gemini 3 - The Next Era!
Its not only a doc that you sign! Its trust
vibe hacking!
We disrupted a highly sophisticated AI-led espionage campaign. The attack targeted large tech companies, financial institutions, chemical manufacturing companies, and government agencies. We assess with high confidence that the threat actor was a Chinese state-sponsored group.
New features dropping soon in Whryte: the fastest local & private voice-to-text for MacBooks. Works in every app already. Soon you'll be able to transcribe local files too, and speaker diarization is coming soon. Check it out: whryte.com
A true legend!
Leaving Meta and PyTorch I'm stepping down from PyTorch and leaving Meta on November 17th. tl;dr: Didn't want to be doing PyTorch forever, seemed like the perfect time to transition right after I got back from a long leave and the project built itself around me. Eleven years…
Does money even matter at this level?
BREAKING: Elon Musk's $1T compensation package is approved with over 75% of the vote.
Another huge release from @Kimi_Moonshot - Kimi K2 The gap between open and proprietary models is closing. Apart from impressive benchmarks, here are a few things I personally found interesting. - They used Quantization-Aware Training (QAT) during the post-training phase. All…
🚀 Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here. 🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%) 🔹 Executes up to 200 – 300 sequential tool calls without human interference 🔹 Excels in reasoning, agentic search, and coding 🔹 256K context window Built…
This looks really nice. Need to try this out
Voice is the New Keyboard I am building a new local and private voice to text app that let's you type 4x faster with your voice! Macbooks are powerful enough to run SOTA transcription models and LLMs. You don't need yet another subscription! Try it: whryte.com…
whryte.com
Whryte - Private, Blazing-Fast Transcription for Mac
Turn speech into text anywhere you can type, completely offline. 100% private, optimized for Apple Silicon.
Anthropic is offering a limited-time 1 month free pro plan to new subscribers with company email address. You get to test the new Memory, Skill and Projects features. After the free month, subscriptions auto-renew (users can cancel anytime - set a reminder :) ). Offer ends…
.@nvidia just released Nemotron-Nano-12B-v2-VL-FP8: - 12 B vision-language params, FP8 quant, 128 K context - single-image VQA, OCR, chart/doc QA, 10-language caption - scores 87.6 % on AI2D, 94.3 % on DocVQA, 89.4 % on ChartQA - vLLM-ready, Apache-2.0 Pretty neat Nvidia is…
Seems like a really competent open weight model!
We’re open-sourcing MiniMax M2 — Agent & Code Native, at 8% Claude Sonnet price, ~2x faster ⚡ Global FREE for a limited time via MiniMax Agent & API - Advanced Coding Capability: Engineered for end-to-end developer workflows. Strong capability on a wide-range of applications…
United States Trends
- 1. $ENLV 4,815 posts
- 2. #IDontWantToOverreactBUT N/A
- 3. Jimmy Cliff 13.8K posts
- 4. #GEAT_NEWS N/A
- 5. Good Monday 43.2K posts
- 6. #MondayMotivation 10.8K posts
- 7. Thanksgiving 131K posts
- 8. Victory Monday 2,694 posts
- 9. TOP CALL 4,351 posts
- 10. DOGE 209K posts
- 11. #VenezuelaVictoriaTotal 2,016 posts
- 12. The Harder They Come 1,709 posts
- 13. AI Alert 2,250 posts
- 14. #MondayVibes 2,882 posts
- 15. Shane Bowen 6,668 posts
- 16. Monad 148K posts
- 17. $NVO 2,791 posts
- 18. $OSCR 2,644 posts
- 19. Check Analyze N/A
- 20. Token Signal 2,736 posts
Something went wrong.
Something went wrong.