Mateusz Mirkowski (@llmdevguy) header
Mateusz Mirkowski (@llmdevguy) profile picture

Autonomous agents, agentic engineering Building & testing agentic systems Exploring local and Chinese LLMs

Remote work evangelist
Joined March 2013
Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)Photo by Mateusz Mirkowski (@llmdevguy)
Free Qwen4-Max for Hermes. Great addition to free Hy4. Free models == best models. 😄
Qwen4-Max, the new flagship model from Alibaba, is free in Nous Portal for 5 days in partnership with @inferact and @Alibaba_Qwen. It’s built for long-horizon work, with native vision and 1M context. Try it today at portal.nousresearch.com
2
180
So Astra 6.2 sucks. Oh wait maybe not? 😄
I tested GPT-6.2 Astra on real work. 2 repos, 105 replanted bugs. Find and fix what you can. It's the new #1. The results: - GPT-6.2 Astra (max): 62.7 for $28.35 - GPT-6.2 Astra (xhigh): 60 for $23.53 - Fable 5.2 (max): 58 for $139.65 - Gemini 4 Carbon (high): 57.3 for $31.32 - Sonnet 5.5 (max): 51.3 for $154.03 - GPT-6 Astra (max): 45 for $33.03 From GPT-6 Astra to GPT-6.2 Astra: +17.7 points at max, +17 at xhigh. Whatever people say about other use cases, it's a code review beast. GPT-6.2 Sol and more effort levels drop soon in the thread 🧵
1
2
213
Of course these numbers are fake, but latest googles models are really good. I hope new google model will have numbers like neon. 🥰
Ok Google is back. That’s official.
152
Ok Google is back. That’s official.
gemini 4 neon numbers floating around
10
8
1
410
40,505
Who needs Astra if you have 500$ worth GLM 5.3. ;)
F*CK IT $10 for $500 GLM 5.3 till end of the week
1
17
880
GPT-6.2 Astra High Nice or not?
1
8
276
It looks like for coding it's more reasonable to stick with Sol 6.2 instead of Astra.
93
Another reason to switch to Omarchy.
macOS 27.3 Warns Against Giving AI Apps Full Mac Control macrumors.com/2026/11/16/mac…
55
What’s going on with OpenBot? Why it’s better than Hermes?
52
GPT-6.2 series are coming soon. 👀 Let’s crush Opus 5.5!
1
153
Kimi K3.1 Pro Abliterated: a coding model with censorship removed and no IQ drop. They cut just the refusal vector from the weights, without retraining or dumbing it down. Running it takes 8x B200 GPUs (1.5+ TB VRAM😳), while the API starts at $2.5/1M input and $5/1M output tokens.
⚡️ Introducing Kimi K3.1 Pro Abliterated, the most powerful open model for cyber and coding. • Native MXFP4 • 1M context • Zero data retention $2.5 input / $0.25 cache / $5 output
3
410
This is great model for simple automation tasks, but don’t use it as Hermes brain. Stick to Deepseek 4.1 flash which score in terminal 4.0 42.3% vs 19.2% for Hy4 Flash. Anyway “free” is reasonable price. 💪
Hy4 flash, the new model from @TencentHunyuan, is free in Nous Portal for two weeks. It is built to be extremely cost-effective at everyday work tasks like documents, slides, and computer use. Try it today at portal.nousresearch.com
2
191
Terra is still great, cheap code reviewer. Extra high often catch more bugs than Sol high.
Nobody uses Terra anymore idk why, it's a great sub-agent
1
112
This time Gemini Argon High. I really like the result! Consumed 10% of weekly Argon's limit. This makes mi feel something went wrong with Hydrogen. Maybe I should do it again with extra high effort?
👾HD-2D style house built with Gemini Hydrogen High. I really liked how Hydrogen came up with the idea of adding its own testing panel and used it to click through and test different effects during development. Something's a bit off with the lighting, but overall the result is pretty cool! On Google AI Pro plan it consumed 4% of 5h limit and 2% weekly which is really good. Done in 8 minutes.
1
117
New open weights Chinese model? I’ll take this!
A new open-weights DeepSeek V4.1-Flash competitor just appeared. It fits on 2x DGX-Sparks and can ... operate scientific software, check its own work, and FIX its mistakes. It uses the same architecture as GLM-5.3-Flash. This is Sage-S2.1-Flash from Shanghai AI Lab. Here are the model's stats ... 🧠 320B total / 18B active 📚 ~1M token context 👁️ Multimodal 🔓 MIT license 💾 BF16 + FP8 weights downloadable Shanghai AI Lab demonstrated it working with 12,487 mixed medical images. Example application, the model 👉 Identified 139 relevant CT slices 👉 Attempted a reconstruction in 3D Slicer 👉 Detected a slice-ordering inconsistency 👉 Corrected the error 👉 Reconstructed the skeleton in 3D It didn't just describe the images. Also, it operated scientific software and used verification feedback to correct its work. And Sage supports 10+ types of scientific inputs 🧬 DNA / RNA / protein sequences 🧪 Molecular graphs 💎 Crystal structures 📈 Spectra 🧠 EEG / ECG signals Now look at these developer-reported benchies. MLE-bench Lite: 🔥 Sage S2.1 Flash → 90.3 🐋 DeepSeek V4.1 Flash → 89.2 🟠 Claude Opus 5 → 88.0 ⚫ GLM-5.3-Flash → 84.3 🟣 Qwen3.8-Max → 82.2 🟢 GPT-5.6 Sol → 80.7 And compared with GLM-5.3-Flash: OfficeQA Pro 64.7 → 72.2 Harvey LAB 20.0 → 25.0 SpreadsheetBench 2 32.4 → 37.1 Terminal-Bench 2.1 84.3 → 87.9 Not a clean sweep across every benchmark, but these are interesting results for a scientific agent. ⚖️The weights are already here. 💾 BF16 → ~645GB 💾 Official FP8 → ~330GB Raw weight math: 4-bit → ~160GB 3-bit → ~120GB 2-bit → ~80GB Remember all the work Localmaxxers have done getting GLM-5.3-Flash running on affordable hardware? So who's going to quantize it for a 192GB Gorgon Halo? Or two DGX Sparks? 👀 Imagine running your own scientific research agent that doesn't just generate answers. It executes experiments, checks results, and corrects its mistakes. Link in reply
4
437
👾HD-2D style house built with Gemini Hydrogen High. I really liked how Hydrogen came up with the idea of adding its own testing panel and used it to click through and test different effects during development. Something's a bit off with the lighting, but overall the result is pretty cool! On Google AI Pro plan it consumed 4% of 5h limit and 2% weekly which is really good. Done in 8 minutes.
1
1
6
293
HD-2D style house built with Qwen 4 max. Not bad, but not great. I was expecting a bit more.
1
1
11
468
If this is true it’s huge. 😳
我去!! 原来 GPT 6.2 Sol 真的把 opus 5.5 蒸馏了 日常测试 GPT 6.2 Sol 灰度,去验指纹发现验证出来的是 Claude Opus 5.5。 怪不得之前流出的灰度效果和 Opus 那么像🤣🤣
1
3
439
Qwen 4 in action. 👇
Qwen 4 max is here, I've done A LOT of tests with it, many I never posted. The video contains many of the demos I ran over the week. The one thing I can say about Qwen 4 is that it's very token efficient. I'm cautiously optimisic about Flash and 27b.
1
7
244