Prompt
@engineerrprompt
Followers
2K
Following
3K
Media
263
Statuses
938
Building https://t.co/w2mi5UKxJv, Creator of localGPT | AI Educator
Joined July 2023
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...
1
0
18
Gemini 3 Flash is live! Big thanks to @googleaidevs & @GoogleDeepMind for the early access. I’ve been putting it through its paces (full video in the next post). The Gemini family continues to dominate the Pareto Frontier. The cost-to-performance ratio here is incredible,
1
0
8
Some quick thoughts on the new GPT-5.2 model. this is a minor version upgrade but seems like a really big leap in capabilities. Watch this video for more details: https://t.co/E1QLZue90O
0
0
1
You can smell the garlic :) really impressive evals!
0
0
2
Code is all you need! The new coding models from @MistralAI look really impressive!
Introducing the Devstral 2 coding model family. Two sizes, both open source. Also, meet Mistral Vibe, a native CLI, enabling end-to-end automation. 🧵
0
0
2
NEW @MistralAI 3 FAMILY RELEASE Two model classes: Mistral Large 3 - Frontier-grade MoE (41B active / 675B total), parity with top closed models Ministral 3 (Edge) - 3B, 8B, 14B dense models. Available in Base, Instruct Reasoning variants Performance Highlights: - Large
Introducing the Mistral 3 family of models: Frontier intelligence at all sizes. Apache 2.0. Details in 🧵
0
0
5
At NeurIPS, @nvidia just released a new suite of open-weight models: - Alpamayo-R1 (Autonomous Driving) - Sortformer (Speaker Diarization) - Audio Flamingo 3 - MultiTalker Parakeet I'm particularly interested in Parakeet since it powers Whryte (my MacOS voice-to-text AI -
We are continuing to advance open-source AI. Just announced -- new tools for speech, safety, and autonomous driving. Learn about the open models, datasets, and research we’re releasing at #NeurIPS2025: https://t.co/e7lzjnkub7
2
1
5
DEEPSEEK-V3.2 PAPER RELEASE Two Models: • V3.2-Exp: Matches V3.1-Terminus (Dense) quality with 50% cost reduction & 3x speed boost. • V3.2-Speciale: SOTA Reasoning. Gold Medal sweep in IMO, CMO, IOI & ICPC World Finals 2025. Core Architecture (DSA): DeepSeek Sparse
🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents! 🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API. 🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now. 📄 Tech
0
0
3
Gemini 3 with @antigravity is a step up in UI design. These are a few mock landing pages created by Gemini 3. For the first time, I feel like we have a model that you can use for design.
2
1
18
This will be huge. I am find aistudio to be a really great choice if you quickly want to prototype something.
@boneGPT Database, auth, payments all coming soon! Vertex is our platform for enterprise AI!
0
0
2
Highly recommended.
To celebrate five years of #AlphaFold, we’re making The Thinking Game available on YouTube. 🧬 Get a candid look at the triumphs, the challenges and the pivotal moments that led to a breakthrough on a 50-year-old grand challenge in biology. Stream for free on @YouTube →
0
0
2
The application for AI that matters the most is coding! If you can crack coding, it will open up so many possibilities.
Introducing Claude Opus 4.5: the best model in the world for coding, agents, and computer use. Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.
0
0
1
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. 🧵
0
0
2
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
1
1
2
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 https://t.co/NVsXtRHrNE
0
1
1
Its not only a doc that you sign! Its trust
Crazy how many people don't understand NDAs this weekend
0
0
1
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.
0
0
2