Great perspective and tips from @ClementDelangue on the early days of gpt-oss. Building strong foundations take time, and we’re excited to be working with inference providers and @huggingface to help these models perform at their best. Please keep your feedback coming!
LLMS
-
Small Edge Models Versus Large Language Models Comparison
By
–
It's a very small edge model. Grok on the other hand is a huge model.
-
Qwen3 235B Instruct Model Now Available on Replicate
By
–
Need more Qwen? Qwen3 235b Instruct surpasses many SOTA models in reasoning, comprehension, mathematics, and coding across multiple languages. Extremely useful for agents and MCP. http://
replicate.com/qwen/qwen3-235
b-a22b-instruct-2507
… -
LangChain Introduces Open SWE: Open-Source Asynchronous Coding Agent
By
–
Try out Open SWE: http://
swe.langchain.com Watch the announcement video: https://
youtu.be/TaYVvXbOs8c Or read the announcement blog: https://
blog.langchain.com/introducing-op
en-swe-an-open-source-asynchronous-coding-agent/
… See the GitHub repo: http://
github.com/langchain-ai/o
pen-swe
… Read the docs: http://
docs.langchain.com/labs/swe -
Qwen Releases Two New AI Models on Huggingface
By
–
Qwen released 2 new models on Huggingface: – Qwen3-4B-Instruct-2507
– Qwen3-4B-Thinking-2507 New models every week -
Claude Code Adds AI-Powered Security Review Feature
By
–
Claude Code can now perform a security review! This feature is also supported in Github Actions, so you can check every new PR.
— 🚨 AI News | TestingCatalog (@testingcatalog) 6 août 2025
Best timing 👀 https://t.co/CI8NhrpMp4 pic.twitter.com/uOzAE7RLRFClaude Code can now perform a security review! This feature is also supported in Github Actions, so you can check every new PR. Best timing
-
Qwen3-4B-Thinking-2507 Model Release on Hugging Face
By
–
HF: https://
huggingface.co/Qwen/Qwen3-4B-
Thinking-2507
… HF:
