TIL you can run GPT-OSS 20B on a phone! This is on Snapdragon phones with 16GB or more of GPU-accessible memory – I didn't realize they had the same unified CPU-GPU memory trick that Apple Silicon has (The largest iPhone 17 still maxes out at 12GB, so not enough RAM to run https://
x.com/nexa_ai/status
/nexa_ai/status/1975232300985291008
…
OPEN SOURCE
-
Running GPT-OSS 20B on Snapdragon Phones with GPU Memory
By
–
-
Last Chance: Context Engineering Webinar with LangChain and Manus
By
–
Last Chance to Join: Context Engineering with LangChain & @manusai This webinar brings together @RLanceMartin Martin (Founding Engineer, LangChain) and Yichao “Peak” Ji (Co-founder & Chief Scientist, Manus; MIT Innovator Under 35) to share practical best practices in
-
Flowise 3.0.8: Community Improvements and Bug Fixes
By
–
And lots of small improvements and bugfixes from community, thank you🫡 Full release note:
github.com/FlowiseAI/Flowise… [Translated from EN to English]→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
OpenAPI Toolkit Upgrades: Convert Specs to LLM-Ready Tools
By
–
5/📜 OpenAPI Toolkit upgrades
— FlowiseAI (@FlowiseAI) 10 octobre 2025
This toolkit turns any OpenAPI (Swagger/JSON) spec into a set of LLM-ready tools – kinda similar to MCP!
Simply drop an OpenAPI spec link like: https://t.co/CI2AgIW0HD and watch the magic 🪄 pic.twitter.com/kLRUN2ieY25/📜 OpenAPI Toolkit upgrades This toolkit turns any OpenAPI (Swagger/JSON) spec into a set of LLM-ready tools – kinda similar to MCP! Simply drop an OpenAPI spec link like: api.apis.guru/v2/specs/groun… and watch the magic 🪄
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Teradata MCP Connector for Natural Language Data Analysis
By
–
3/🗄️ Teradata MCP @Teradata is an open source database management system for storing, managing and analyzing large volumes of data. With the MCP connector, you can query, analyse data with natural language.
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Flowise v3.0.8 Released with TTS and Web Search Features
By
–
What a week! 😮💨 We’re still shipping regardless, v3.0.8 is live! New in this release: 🔉 TTS (OpenAI + ElevenLabs) 🌐 Built-in web search & fetch for Gemini + Anthropic 🗄️ Teradata MCP 🖥️ Oxylabs scraper 📜 OpenAPI Toolkit upgrades Let's dive in 🏄
→ View original post on X — @flowiseai, 2025-10-10 18:32 UTC
-
Controlling AI-Generated Content Distribution and Open Source Models
By
–
Puesto que no todas las formas de generar contenido con IA podrá controlarse (e.g. modelos open source), no todo el contenido podrá ser marcado criptográficamente y parte del problema seguirá existiendo. Habría que controlar el canal por donde se distribuye y quién, pero eso es
-
Neural Network Implementation in NumPy with Manual Backpropagation
By
–
Been there, done that . But how about a a neural net in NumPy with manual backprop? https://
github.com/rasbt/python-m
achine-learning-book/blob/master/code/ch12/neuralnet.py
… That was 10 years ago, makes me feel so old now -
Jamba Reasoning 3B: Tiny Open-Source Model Excels at Reasoning Tasks
By
–
@VentureBeat spotlights Jamba Reasoning 3B, our tiny open-source model that outperforms others across reasoning benchmarks and runs securely on-device. Read the feature
-
KAT-Dev-72B-Exp: Agentic Coding Model Ranks #2 SWE-Bench
By
–
HUGE a new Agentic coding model, fits on 4x RTX 3090s @ 4-bit, fully local KAT-Dev-72B-Exp by Kwaipilot – Claude Code setup guide included – ranks #2 on SWE-Bench Verified – excels at long-horizon coding + tool-use – multi-stage tuned: Mid-Training, SFT + RFT, Agentic RL