AI Coding Live News

On Oct 30, SenseTime released SenseNova-Loop-9B-Preview (Apache 2.0) on its official X account and Hugging Face. It runs layers 4 to 27 of a 32-layer decoder twice with the same weights, so each forward pass executes 56 layer computations while storing about 9B parameters, about 14.6B at inference, and it uses two-stream mHC (manifold-constrained hyper-connections) to manage the residual streams. It takes text and images, with training sequences up to 262,144 tokens. SenseTime charts show it beating Qwen3.5 and Qwen3.6 peers on BIRD-Dev, WorkBuddy Bench, and other agent and data tasks, while it still trails on Terminal Bench 2.1; the technical report is not out yet. The official launch post drew about 910 likes.

Zoom

Microsoft Research, Microsoft Security and UC Berkeley open-sourced TokenEconomizer on GitHub (Apache 2.0, v0.1.0 released October 26), a plugin for Claude Code, Codex, GitHub Copilot CLI and Pi, with experimental opencode support. It learns from earlier sessions in the same repository: micro-skills remember repo facts, tool pruning drops tool definitions that go unused, and a loop guard nudges an agent that is stuck. The paper reports 18.4–30.9% lower mean cost across five agent and model combinations on 277 SWE-Bench tasks (paper figures).

Zoom

LM Studio posted on X at 15:32 UTC on Oct 29 that users can now download a new oMLX engine inside LM Studio and run it with MLX models they already have. The official changelog lists it in Bionic 1.1.10, alongside speculative decoding for MLX models and an in-app terminal. oMLX is an open-source Apple Silicon inference server maintained by developer jundot (Apache 2.0, about 23,000 GitHub stars) built around continuous batching and a two-tier RAM and SSD KV cache. LM Studio has not published speed comparisons for the engine.

Zoom

On Oct 27 OpenBMB (ModelBest) open-sourced the MiniCPM-OCR suite with two models: MiniCPM-OCR 1.0, a 1.3B-parameter document parser that scores 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2 (vendor-reported), and MiniCPM-OCR Jev, a 2B OCR quality judge that scores any parser's output region by region from 0 to 1 and flags content that needs human review. Code and weights are Apache 2.0, with day-one support for vLLM, SGLang, llama.cpp, Ollama and multiple chip platforms.

Zoom

On Oct 28 DiffuSpace, whose members come from the HKU NLP group behind Dream 7B, released its first model, Clover-35B-A3B-Preview: a mixture-of-experts diffusion language model initialized from Qwen3.6-35B-A3B, with 35B total and about 3B active parameters, a 128K context window and block-parallel denoising. Vendor-reported results include 73.6 on SWE-bench Verified, 51.7 on Terminal-Bench 2.1 and 83.8 on GPQA Diamond, with 680 tokens/s on a single GB300 in agent workloads. Weights are Apache 2.0 on Hugging Face, ModelScope and GitHub, with SGLang and llama.cpp support.

Zoom

The Google AI Studio team released an experimental preview of the Gemini API CLI (command name gemini-api). It is a stateless, zero-dependency Go binary for macOS, Linux and Windows, open source under Apache 2.0. Any coding agent with shell access and a GEMINI_API_KEY can call text reasoning, image, video, music and speech generation, file and YouTube analysis, audio and video transcription, and managed agents such as Deep Research with one command. Media is written straight to disk and only the file path goes to stdout, so base64 payloads never land in the context window. Google labels it experimental and not a supported Google product.

Zoom

Recursive, founded by Richard Socher, has officially open-sourced Flint (RecursiveSI/flint), a 39.8B Mixture-of-Experts (MoE) coding agent model under Apache 2.0 with day-zero Ollama support (ollama run flint). Activating just 2.5B parameters per token across 47 MoE layers with a 262K context window, Flint hits 125+ tokens/sec on an M4 Pro MacBook Pro. It sets new benchmarks for sub-50B local models, scoring 74.2% on SWE-bench Verified and 89.7% on SWE-bench Pro v2.

Zoom

On Oct 21, Recursive, the startup founded by Richard Socher, released its first model, Flint: a 39.8B-total MoE coding model with about 2.5B active parameters per token, with weights on Hugging Face under Apache 2.0. Recursive says it leads sub-50B MoE models on SWE-Bench Pro v2, Terminal-Bench 2.1 and SWE-Bench Verified, runs at 125+ tok/s on an M4 Pro MacBook Pro, and was built from scratch in under four months with its automated research system, the Eureka Machine, contributing to nearly every part of the stack.

Zoom

At GTC Berlin on Oct 21, NVIDIA announced the OpenShell Reference Architecture: building on the open-source OpenShell secure runtime, it pairs Vera Rubin for inference, Vera CPUs for agent harnesses, and BlueField-4 DPUs running NVIDIA Sentry for in-silicon policy enforcement, so enterprises can build, contain, observe and govern agents on-prem and at the edge. NVIDIA says it is available now; partners named include Anthropic, OpenAI, Meta, Microsoft and ServiceNow. The software is Apache 2.0.

Zoom

Krafton AI, the research division of global gaming giant Krafton, officially announced the open-weights release of Raon-1 mini under Apache 2.0. Pretrained from scratch, Raon-1 mini features a sparse Mixture-of-Experts (MoE) architecture with 30 billion total parameters and only 4 billion active parameters per token. The release is accompanied by a dedicated DFlash speculative drafting model and a live interactive playground. Internal evaluations reveal that Raon-1 mini matches Meta's Muse Glimmer across agentic tool-use and coding benchmarks while requiring substantially lower VRAM and sustaining lower generation latency.

Zoom

On Oct 21 the vLLM community and Ant Group open-sourced Humming (Apache 2.0), a quantized-inference library that JIT-compiles GEMM kernels on demand. It supports every NVIDIA architecture from Turing on plus T-Head's Zhenwu 810E, and covers weight and activation combinations from INT1-INT8 and FP4-FP8 for dense and MoE workloads. In vLLM's microbenchmarks it runs 2-5x faster than vLLM Marlin, FlashInfer or DeepGEMM in some cases; on 8 H20 GPUs, switching DeepSeek-V4.1-Flash MoE from Marlin W4A16 to Humming W4A8 raised throughput 14-43%. vLLM 0.29.0 ships it built in.

Zoom

On Oct 20, Vercel released durable-harness, an open-source package (Apache 2.0, npm 0.0.1-beta.6, marked experimental). It adds durability from the outside to existing coding-agent harnesses such as Pi, OpenCode, Codex and Claude Code: every model and tool call is logged before and after it runs in a Workflow SDK World, and if a function times out or crashes, a queue hands the turn to a new function that resumes from the log, so finished model calls are not billed twice. It runs on Vercel, on local files, or on self-hosted Postgres and other backends.

Zoom

On Oct 20, French voice AI company Gradium open-sourced Phonon, a family of on-device text-to-speech models: the English Phonon 31m (64 MB q8 weights, Apache 2.0) and Phonon 40m (single-language English, French, German, Spanish and Portuguese variants plus a five-language model, CC BY-NC non-commercial). Built on Kyutai's Pocket TTS and the Mimi codec, it ships its own runtime for CPU, Metal, CUDA, Vulkan, WebGPU, Core ML and Snapdragon, running offline on phones, browsers and a Raspberry Pi. Gradium reports 7 ms to first audio on a MacBook Air M5 CPU versus 517 ms for Kokoro.

Zoom