
LM Studio's Bionic Agent App Finally Runs on Linux for Free
LM Studio's agentic app Bionic now runs on Linux, giving penguin users repo-aware coding, document work, and voice transcription with local open models.
20 stories

LM Studio's agentic app Bionic now runs on Linux, giving penguin users repo-aware coding, document work, and voice transcription with local open models.

Google's new 330M-parameter time series foundation model handles multivariate forecasting zero-shot in a single forward pass, topping Gift-Eval, FEV-Bench and Time.

A dependency-free Node tool turns any repo into a live zoomable map showing exactly what Claude Code, Codex, and Cursor are doing.
Seven practical shifts for securing agents that can find any crack

Runway's Solaris skips the code layer entirely, generating live app interfaces frame by frame and beating top LLMs on visual reconstruction tests.
A one-line change to LoRA's initialization closes the gradient gap with full fine-tuning, boosting speed and stability with zero extra parameters.
A double-refined abliteration of Qwen3.8-27B cuts refusals to near zero while shrinking behavioral damage roughly sixfold versus its upstream.
A community-built IQ2_XXS quantization squeezes Qwen3.8-Flash-Next's 177B parameters into a 75GB GGUF that runs on ~42GB of memory.

DeepSeek gives its Flash model eyes with an experimental multimodal release that matches Claude Opus 4.8 on agent tasks at a fraction of the cost.

Z.ai shipped a frontier coding model without touching the base weights, matching GPT-5.6 Sol and Claude Fable 5 on agentic tasks through scaled post-training alone.

A new Gaussian splatting framework reconstructs volumetric videos with thousands of frames of complex motion, extending prior methods by roughly 70x in temporal coverage.

Apodex 1.1 lands with an Elo of 1348 on GDPval-AA v2, beating DeepSeek V4 Pro and Kimi K2.6 on real-world agentic work.
Broad Institute researchers unveil a framework that separates score-chasing from real scientific reasoning, exposing where Claude, GPT, and Gemini break down.
McGill NLP's post-trained AfriqueQwen3.5-4B covers 50 African languages and beats larger open models on the AfroBench-Lite suite.

A humanoid robot jumps onto monkey bars, swings across at half a meter per second, and drops safely, guided by raw lidar and a reinforcement-learned policy.
A community LoRA trained on 924 curated martial arts clips brings specific wushu technique names into MiniMax H3 video generation, with ComfyUI drop-in support.
GitHub ships a batch of quality-of-life fixes for Issues: pinned views, reaction avatars, denser dashboards, hidden closed sub-issues, and scoped dependency APIs.
A 21 GB single-file build of MiniMax-H3 renders 10-second clips with synchronized stereo audio in about 76 seconds at 4 steps.
A confusingly worded policy change swaps a temporary 50% boost for a permanent 25% one, leaving Claude Code users with 17% less weekly capacity than they have now.
A community quant of Qwen3.8-Flash-Next shrinks the 177B MoE to 84 GiB with a per-layer mixed-precision recipe that beats standard IQ4_XS on both size and quality.