Sabitlenmiş Tweet
Mateusz Mirkowski
3.8K posts
Mateusz Mirkowski
@llmdevguy
Autonomous agents, agentic engineering Building & testing agentic systems Exploring local LLMs
Remote work evangelist Katılım Mart 2013
150 Takip Edilen1.8K Takipçiler
English
Planning (at least) three weeks in China in September with my wife and young daughter that speaks Chinese! ✈️
I hope to be able to visit at least @MiniMax_AI and @Zai_org labs while there 🙏
English
5h limits temporary gone in GPT.
Please stay this forever. 🙏
English
🔥First impressions of GPT-5.6:
Sol:
- Eats limits way too fast
- Much better for security checking than 5.5
- Way better for design
Terra:
- Slightly better 5.5
- Good balance between results and costs
Luna:
- Cheap and fast for easy tasks.
English
Cant make this up CLAUDE RESET USAGE after GPT 5.6 SOL dropped LOL
GIF
English
Fugu is not a new model. It’s more like proxy to many different models like GPT 5.5 or Opus 4.8.
Mateusz Mirkowski@llmdevguy
Remember, Fugu is a dangerous fish. 😄
English
@loktar00 I was expecting 12-15 t/s. At least 25 would be good I think.
English
🚀You end the day with 19% of your limit left.
You wake up in the morning, and the limit has reset.
Thanks @thsottiaux ! 😇
English
@llmdevguy Recently I developed an invoice generator MVP using glm 5.2 and the results are insane. I have recorded a complete session while testing all the things which is available at my profile.
English
🌓I was supposed to write a post today about how great Kimi K2.7-Coder is, but then I started testing GLM 5.2. I've changed my mind.
The difference between GLM 5.2 and the previous 5.1 feels bigger than the difference between K2.6 and K2.7.
Which one is better? For now, it seems like GLM has a slight edge, but I need to run more tests.
English
Cool, Codex.
But please do not use my limits if this occurs...
English
I would add just one thing.
Try to buy motherboard with 2 x8 pcie express ports. Cheap ones can give you one x16 and other x4 which will reduce speed greatly with two GPUs.
Lotto@LottoLabs
Keep it simple if you want to learn local ai 1) Build the cheapest rig that can house 1 used 3090 2) Who cares about ram, cpu, etc, buy ddr4 32gb, get a decent mid range ryzen/intel 3) download qwen 3.6 27b You’ll be into the rig like $1500 at most You won’t be able to upgrade much (maybe another 3090) but it’s a great starting point You don’t feel locked into learning about big rigs and upgrade paths If you like it then you can still keep and run the 3090 rig (trust me it’s useful) And you can build a new separate rig if you need more vram, on any platform after you have some experience and know what type of hardware you actually need, not what people recommend online!
English
🙏Please release a model that’s at least half as good as this meme.
Alexander Knigge@AlexanderKnigge
oh my god its happening @MistralAI has officially confirmed the upcoming release of Le Chaton Fat - 30T MoE with 256 experts - 1M context window - multimodal and multilingual - outperforms Fable 5 on every benchmark
English
Fine-tuned Super-Chaton Fat :
- 500T with 1B MoE
- 1B context
- 104.2% on SWE bench
- 98.2% on cute cat bench
Alexander Knigge@AlexanderKnigge
oh my god its happening @MistralAI has officially confirmed the upcoming release of Le Chaton Fat - 30T MoE with 256 experts - 1M context window - multimodal and multilingual - outperforms Fable 5 on every benchmark
English