feels like ages since a new truly paradigm shifting model released on open weights side? or am I missing something? the closest on proprietary side is gpt-5-codex
@reach_vb
-
Hugging Face Hub Launches Custom Apps, GGUF Editing, Xet Integration
By
–
The Hugging Face Hub team is on a tear recently: > You can create custom apps with domains on spaces
> Edit GGUF metadata on the Fly
> 100% of the Hub is powered by Xet – faster, efficient
> Responses API support for ALL Inference Providers
> MCP-UI support for HF MCP Server
> -
GPT-Realtime and E2E Models in Production Projects
By
–
little survey: are you using gpt-realtime/ mini or any other E2E model in projects? if yes, what for?
-
Hugging Face Transformers: Managing 1M Lines Python Code
By
–
With 1,000,000+ lines of Python and 400+ models How do we keep @huggingface Transformers sane? > Our design tenets: one-model-one-file, modular shards, minimal API, no breakage Peek under the hood on one of the biggest and most-used open ML codebases out there
-
Voice Input Privacy Concerns in Social Environments
By
–
it's one of the biggest deterrents for me to use voice input – it's a bit weird to speak in an environment where you know there's atleast one person listening to you
-
SDK and LLM UI Code Reorganization
By
–
Also reorganised the code to be a bit more focused on SDK and the LLM UI aspect:
-
Inference Provider App Now Supports Responses API for Open Models
By
–
Inference Provider starter app now supports the Responses API Best part: you can run any open weights model with the Responses API – even if the official provider doesn’t support it. Starter app in the next tweet – check it out!
-
JavaScript Ecosystem Superior for Building AI Applications
By
–
Recently realised that the JS ecosystem for building AI apps is so much superior than Python Using @nextjs and OpenAI client makes it a breeze to rapidly prototype apps Some cool recipes incoming..
-
Qwen 235B Vision Language Model Released Under Apache 2.0
By
–
NEW: Qwen 235B A22B Vision Language Model is OUTT! Apache 2.0 licensed and upto 1 Million context length
-
GPT-5-Codex Becomes Second Responses API Only Model
By
–
After gpt-oss, the latest gpt-5-codex is the second model to be Responses API only! Makes sense, since Responses is objectively a better choice than Chat Completions for Agentic use-cases