Autonomous agents, agentic engineering Building & testing agentic systems Exploring local LLMs
Remote work evangelist
Joined March 2013
- Tweets3.8K
- Following149
- Followers1.8K
- Likes4.5K
It happened much later than I expected, but it was obvious that it would happen sooner or later.
Minimax is still one of the most cost-effective plans.
🔥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.
🚀You end the day with 19% of your limit left.
You wake up in the morning, and the limit has reset.
Thanks @thsottiaux ! 😇
🌓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.
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.
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!
🙏Please release a model that’s at least half as good as this meme.
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
K2.6 was the best Chinese model until today.
Now K2.7 is even better.
Amazing work.
🌘 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
