GitHub – yuanchenyang/smalldiffusion: Simple and readable code for training and sampling from diffusion models https://
buff.ly/WDuy3yN
#AI #MachineLearning #DeepLearning #LLMs #DataScience
CODE
-
Simple readable code for diffusion model training sampling
By
–
-
Grok 3 Integration in CodeLLM Editor Coming Soon
By
–
Grok 3 is very good when it is embedded in code editors Will be in CodeLLM before end of day
-
Multimodal Agents with Voice Support Now Easier to Build
By
–
Multimodal agents are now easier to build with the Agents SDK—voice included! Check out this new sample app from @dkundel and @seratch showing how to quickly integrate real-time audio into your agents.
-
Share Your Fine-Tuned Model on Hugging Face
By
–
very cool! you should share the fine-tuned model on http://
hf.co/models! -
Google Gemini Now Supports MCP Protocol for AI Agents
By
–
MCP is a good protocol and it's rapidly becoming an open standard for the AI agentic era. We're excited to announce that we'll be supporting it for our Gemini models and SDK. Look forward to developing it further with the MCP team and others in the industry
-
Found Notion MCP Server OpenAPI Specification
By
–
Found the spec here: https://
raw.githubusercontent.com/makenotion/not
ion-mcp-server/refs/heads/main/scripts/notion-openapi.json
… -
OpenAPI Specs with Response Schemas for Better AI Agents
By
–
I think this is really nice for 2 reasons: (1) Using an OpenAPI spec as a way to specify the endpoints is genius. (2) The spec contain response schemas!!! We really need this for agents to work well. Nice job!
-
Cerebras Delivers 19x Faster Code Generation with Llama 4
By
–
Subsecond code generation in action. 👀
— Cerebras (@cerebras) 9 avril 2025
Same prompt. Same output. Just 19x faster. Cerebras powers the fastest @AIatMeta Llama 4.
Get Access now: https://t.co/isthZ2Xau4 pic.twitter.com/7xzU7Tevf8Subsecond code generation in action. Same prompt. Same output. Just 19x faster. Cerebras powers the fastest @AIatMeta Llama 4. Get Access now: https://
cerebras.ai/build-with-us -
Models optimizing their own implementations automatically
By
–
Noted! Maybe the models can start optimizing their own implementations
-
Remote MCP Server Release Request for Integration
By
–
Would you release a remote MCP server too? We’d love to integrate with that