پن کیا گیا ٹویٹ
Mateusz Mirkowski
3.8K posts
Mateusz Mirkowski
@llmdevguy
Autonomous agents, agentic engineering Building & testing agentic systems Exploring local LLMs
Remote work evangelist شامل ہوئے Mart 2013
149 فالونگ1.8K فالوورز
@redmonkeyAI I am testing it. It's tier below them unfortunately.
English
🔥GLM 5.2 vs Kimi K2.7.
Which one is better?
Will test it soon.
What's your thoughts?
English
@arunoda True. I use 5.5 mostly. Kimi and glm are good enough in most cases but not in very complex tasks.
English
@llmdevguy I tried some really hard tasks yesterday with both. Still they are not Opus or GPT 5.5 level. Working with complex tasks involving backend, client & UI stuff they are not there yet. But for surgical tasks, it’s good. Both are better than their previous versions.
English
@llmdevguy I've only tried kimi so far for code review and it worked pretty well!
English
I hate that I am starting to like AI generated music better than other modern music.
There are some telltale signs music is AI generated, but it's subtle. My sister is big into making AI music also, so I've been forced to listen to quite a bunch this year.
Make it on a 3090.
English
K2.6 was the best Chinese model until today.
Now K2.7 is even better.
Amazing work.
Kimi.ai@Kimi_Moonshot
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6. 🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates. ⚡️ 6x High-Speed Mode coming soon! 🔌 Available today via Kimi API and Kimi Code. 🔗 Kimi Code: kimi.com/code 🔗 API: platform.moonshot.ai
English
Google releases DiffusionGemma.✨
The new 26B-A4B diffusion text model runs locally on 18GB RAM.
It supports high-speed text generation, thinking, image, video and 256K context.
Run and train via Unsloth Studio.
GGUF: huggingface.co/unsloth/diffus…
Guide: unsloth.ai/docs/models/di…
Google Gemma@googlegemma
Meet DiffusionGemma! An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license. Moving beyond sequential, token-by-token processes to generate entire blocks of text simultaneously. Here’s what’s new with DiffusionGemma: 👇
English
@llmdevguy I'm finding Medium is really the sweet spot, anything higher and it takes about a week to do anything. i'm using high for planning and medium to implement
English
So Fable 5 is more expensive than 5.5 xhigh, but at the same level.
Terp@OnlyTerp
Tldr Fable 5 low is solving in the least steps and is a great cost per task
English
😞Yesterday I realized that 5.3 codex is removed.
This is very sad.
5.3 was great for fixing bugs or small features.
And it was very cheap.
I hope we will get something in return.
English
@llmdevguy Few weeks ago you compare Chinese models and k2.6 was winner . How’s M3 compares now ?
English
Second iteration much better, but still issues with animations.
Mateusz Mirkowski@llmdevguy
🚀First try MiniMax 3. Not bad. Animations are a bit clunky, but overall it proposed me interesting design. Although I prefer what Kimi K2.6 proposed.
English
🇨🇳After testing Chinese models over the last few weeks, my coding ranking currently looks like this:
1. Kimi K2.6
2. GLM-5.1
3. MiMo V2.5 Pro
4. MiniMax 2.7
5. DeepSeek V4 Pro
👉But each of them has its own superpowers.
Frontend/Design: K2.6
Backend: K2.6 / GLM-5.1
Code review: MiMo
All-rounder: M2.7
Reasoning: DeepSeek
Now I'm waiting for MiniMax 3.0, which I hope will take the number 1 spot!
English
🚀First try MiniMax 3.
Not bad. Animations are a bit clunky, but overall it proposed me interesting design.
Although I prefer what Kimi K2.6 proposed.
English
We have it!
Looks fantastic.
MiniMax (official)@MiniMax_AI
Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days
English