Fetching from the wire…
01
02
03
04
05
06
07
08
Models2026-09-19 · source-backed
@madiator's Bespoke Nimble uses contrastive data curation to lift the base model from 66% to 90% against Jev's 93% on the same task. Latent Space That's the most informative data point in the whole clone wave, because it suggests most of the accuracy is reachable with a public base model plus curated data, and the remaining three points plus the pricing come from the architecture and serving stack. A self-hosted decision model is a weekend of data work.
Each link below shares sources, entities, or timing with this story.
PortLLM claimed training-free, data-free transfer of LoRA patches onto updated base models, but only over short horizons and without theoretical grounding. This study runs 10 continual-pretraining steps on Mistral, Gemma, and Qwen and finds portability persists long-run, meani...
Moonshot AI dropped Kimi K2.6 today and the numbers are hard to ignore. One trillion parameters total, 32 billion active per token across 384 experts, 256K context window, and native multimodal input. It scores 58.6 on SWE-Bench Pro versus GPT-5.4's 57.7 and Claude Opus 4.6's...
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...
Staged on ModelScope for 23:00 Beijing time August 26, it's roughly 125B parameters plus a separate N-gram embedding table of about 51B, activating 6B per token, with GDN gated-delta hybrid layers and Qwen Sparse Attention. Alibaba frames it as a technology preview of the Qwen...
Hugging Face published its Summer 2026 State of Open Models report on August 14, and one statistic in it went almost entirely unremarked in the coverage. By July 2026, agents rather than humans became the Hub's primary users. Claude Code alone accounted for 44.4% of all agent...
Three points behind GLM-5.3 at 60, tying GPT-5.6 Terra and Muse Spark 1.2, at $0.09 per task against $0.68 for GLM-5.3 max (Latent Space). It burned 149M output tokens to run the index, of which 134M were reasoning tokens, more than Kimi K3 at 133M or Qwen3.8 2.4T A95B at 136M...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.