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!
OPEN SOURCE
-
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
… -
Open SWE: Autonomous Cloud-Based Coding Agent for GitHub
By
–
Introducing Open SWE: An Open-Source Asynchronous Coding Agent Open SWE is a fully autonomous, cloud-based coding agent that acts like a true teammate. Integrate it with your GitHub account, and put it to work fixing bugs or implementing features. Try it out the demo today
-
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 -
Qwen3-4B-Thinking-2507 Model Release on Hugging Face
By
–
HF: https://
huggingface.co/Qwen/Qwen3-4B-
Thinking-2507
… HF: -
OpenAI Open Weights Models: Provider Differences Impact
By
–
For the open weights models from OpenAI your provider seems to matter a lot. I expect this will be sorted, but there are pretty big differences right now.
-
Qwen Releases Qwen3-4B-Instruct and Qwen3-4B-Thinking Models
By
–
Qwen just dropped Qwen3-4B-Instruct-2507 and Qwen3-4B-Thinking-2507