AI coding wasn't up to par 2-years ago. It is now.
LLMS
-
AI Model Excels at Creative Writing and Metafictional Storytelling
By
–
we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story
-
AI-Generated Code Won’t Reach 90% Adoption Soon, Expert Says
By
–
I think it is more realistic to look at what happened with human-written text. ChatGPT (in 2022) is making a huge difference in how we write. But I wouldn't say that 90% of text is AI-generated (yet). Similarly, I don't think that 90% of code is going to be AI generated in 3-6
-
Code Interpreter Coming to Responses API as Built-in Tool
By
–
We’re working to add Code Interpreter to the Responses API as our next built-in tool!
-
Web Search Tool Integration with Structured Outputs JSON Schema
By
–
You can use the web search tool together with Structured Outputs—just set your own JSON schema, and the model will return results directly in JSON!
-
OpenAI Refreshes Agents Platform APIs and SDKs Suite
By
–
The new OpenAI Agents Platform https://
latent.space/p/openai-agent
s-platform
… @OpenAIDevs are refreshing the entire suite of APIs, Tools, and SDKs for the year of Agents. We grab an exclusive interview with @romainhuet and @nikunjhanda to ask your burning questions on the Responses API, Web -
Coding Attention Mechanisms: Understanding the Engine of LLMs
By
–
Just uploaded my "Coding Attention Mechanisms" tutorial. A 2h15m session on coding attention mechanisms to understand how the engine of LLMs works: self-attention → parameterized self-attention → causal self-attention → multi-head self-attention
-
Cerebras Inference delivers 70x faster token processing for Llama
By
–
Cerebras Inference runs the industry’s most popular models at more than 2,000 tokens/s – 70x faster than leading GPU solutions. Cerebras Inference models including Llama 3.3 70B, will be available to HuggingFace developers, enabling seamless API access to Cerebras CS-3 powered AI
-
Cerebras Delivers 10x Speedup for AI Inference Applications
By
–
Cerebras Inference 🤝 @huggingface
— Cerebras (@cerebras) 11 mars 2025
Experience an instant 10x speedup for AI chat, reasoning, and agentic apps.
Ready to try the fastest inference in the world? It’s just one click. Watch the demo below.
We can't wait to see what you will build! pic.twitter.com/sSbRE4lDZuCerebras Inference @huggingface Experience an instant 10x speedup for AI chat, reasoning, and agentic apps. Ready to try the fastest inference in the world? It’s just one click. Watch the demo below. We can't wait to see what you will build!