Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-09-10 · source-backed
arXiv 2609.09134 evolved a harness with a weak model, watched a stronger expert use that harness better, then tried the obvious fix. It cost 4 to 30 points on Qwen3-Coder and Gemma 4, even though the same procedure helps under the unevolved harness. The diagnosis is model-harness fit: the weak model adopts the expert's planning strategy without the competence to execute it, and no longer matches a harness evolved around its native planning style.
Each link below shares sources, entities, or timing with this story.
The models are good. The license is the real story. Google released Gemma 4 on April 2 with four variants: E2B, E4B, 26B MoE, and 31B Dense. All built on the Gemini 3 architecture. The 31B Dense variant claimed #3 on Arena AI's text leaderboard, beating models 20x its size. Th...
Google DeepMind shipped Quantization-Aware Training checkpoints for every Gemma 4 size, and the headline number is genuinely useful: the smallest model goes from 11.4GB to 1.1GB. That's 0.84GB if you go text-only. Up to ~72% lower VRAM and 2x faster inference on mobile NPUs, w...
Google DeepMind released Gemma 4 on April 2 with four model sizes (E2B, E4B, 26B MoE, 31B Dense) under Apache 2.0. Multimodal (text, vision, audio). 256K context. Native thinking and tool-calling optimized for agentic workflows. Day-zero ecosystem support across vLLM, llama.cp...
Google released open-source Multi-Token Prediction (MTP) drafters for the Gemma 4 model family. The concept: pair a heavy target model (Gemma 4 31B) with a lightweight drafter that predicts several future tokens in parallel. The target model verifies the predictions in a singl...
Google's HF org lists diffusiongemma-26B-A4B-it (~4B active), an image-text-to-text Gemma member that's diffusion-style rather than purely autoregressive (Hugging Face). No detailed announcement yet, which is why I'm flagging it low. But a diffusion approach inside the Gemma o...
The leaderboard says first place. The methodology says you should check your own bill. Qwen3.8 Max now ranks first on Artificial Analysis' agentic index, scoring 86.1 on OSWorld-Verified ahead of GPT-5.6 Sol Max at 83.2 and Fable 5 at 85.0, priced at $2.00/M input and $6.00/M...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.