agree, would love to see more datasets & training scripts releases!
CODE
-
Toon Team Releases Token Efficiency and Retrieval Accuracy Benchmarks
By
–
Here are the benchmarks for token efficiency and retrieval accuracy as provided by the Toon team. You can find the same information in their GitHub repo: https://
github.com/toon-format/to
on
… -
Moonshot AI Unveils Kimi K2 Thinking 1T-Parameter Model
By
–
Beijing-based Moonshot AI has unveiled Kimi K2 Thinking — a 1T-parameter Mixture-of-Experts model built for deep reasoning, coding, and web search. Performance Highlights: SOTA on HLE (44.9%), BrowseComp (60.2%), SWE-Bench Verified (71.3%) Matches or surpasses GPT-5
-
MCP One Year Anniversary Hackathon with Anthropic and Gradio
By
–
MCP might have been one of the biggest most recent new developments in AI. We're celebrating its one year anniversary with @AnthropicAI @gradio hosting a legendary virtual hackathon in a week. Gonna be fun!
-
Deepnote: Collaborative AI and Data Science Platform Solution
By
–
Linking you with those guys @DeepnoteHQ they will be able to help you 🙂
-
LangChain Tools Successfully Running in Production Environments
By
–
Interesting! But there are also many examples of tools which are working greatly in production with @langchain
, right? -
Multi-head Attention in Large Language Models Visual Explanation
By
–
Multi-head attention in LLMs, visually explained: pic.twitter.com/kN5epKVTJx
— Akshay 🚀 (@akshay_pachaar) 7 novembre 2025Multi-head attention in LLMs, visually explained:
-
Cambrian-S: Advanced Spatial Video Understanding Model Released
By
–
Cambrian-S: Towards Spatial Supersensing in Paper: https://
arxiv.org/abs/2511.04670
v1
…
Website: https://
cambrian-mllm.github.io
Code: https://
github.com/cambrian-mllm/
cambrian-s
…
Cambrian-S Models: https://
hf.co/collections/ny
u-visionx/cambrian-s
…
VSI-590K: https://
hf.co/datasets/nyu-v
isionx/vsi-590k
…
VSI-SUPER: https://
hf.co/collections/ny
u-visionx/vsi-super
… -
ReAct Framework in CrewAI: LLM Problem-Solving with Tools
By
–
ReAct is really popular. Here's an example from CrewAI, which uses ReAct to let LLM think through problems and use tools to act on the world.
-
Codex Team Makes Rapid Incremental Progress
By
–
Codex team continues making rapid incremental progress