CodeDemo (@codedemo) profile picture

CodeDemo pastes code snippets into your favorite IDE without getting in your way.

U.S.A.
Joined October 2013
CodeDemo retweeted
⚡ Meet Qwen3.6-35B-A3B:Now Open-Source!🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception and reasoning ability 🧠 Multimodal thinking + non-thinking modes Efficient. Powerful. Versatile. Try it now👇 Blog:qwen.ai/blog?id=qwen3.6-35b-… Qwen Studio:chat.qwen.ai HuggingFace:huggingface.co/Qwen/Qwen3.6-… ModelScope:modelscope.cn/models/Qwen/Qw… API(‘Qwen3.6-Flash’ on Model Studio):Coming soon~ Stay tuned
432
1,577
619
11,302
2,721,659
CodeDemo retweeted
You can now train Gemma 4 with RL in our free notebook! You just need 9GB VRAM to RL Gemma 4 locally! Gemma 4 will learn to solve sodoku autonomously via GRPO. RL Guide: unsloth.ai/docs/get-started/… GitHub: github.com/unslothai/unsloth Gemma 4 Colab: colab.research.google.com/gi…
20
221
12
1,370
66,327
Excited to launch the accompanying free RLHF Course for my book. To kick it off, I've released: - Welcome video - Lecture 1: Overview of RLHF & Post-training - Lecture 2: IFT, Reward Models, Rejection Sampling - Lecture 3: RL Math - Lecture 4: RL Implementation I'm going to add question & answer videos throughout the lecture to go deeper on topics that need it, and potentially cover some topics that are too recent and in flux to go in print. I expect 10-15 videos in total over the next few months. At the same time, development around the code for the book is picking up. It's a great time to build the foundation for post-training methods. YT playlist and course landing page below.
51
240
23
1,737
195,168
😱 HOLY SHIT... Someone just dropped a fully liberated Gemma 4 E4B! and the guardrail removal process appears to have left coherence fully intact AND improved coding abilities! 🤯 huggingface.co/OBLITERATUS/g… OBLITERATED Gemma: ✅ 97.5% compliance rate, 2.1% refusal rate, 0.4% degenerate outputs (499/512 prompts answered on OBLITERATUS bench) ORIGINAL Gemma 4 E4B: ❌ 1.2% compliance rate, 98.8% refusal rate (506/512 prompts refused) Coherence: fully intact Factual: same Reasoning: same Code: +20% 📈 Creative writing: same But the REAL story here isn't the model itself, it's how it was made... 🧵 THREAD 👇
127
454
60
4,715
434,426
CodeDemo retweeted
No.1. Again! 🎉 Thanks for all OSS developers! MiniMax M2.7 has only 230B parameters with 10B activated, yet delivers excellent results and outstanding performance. @MiniMax_AI It is particularly well-suited for open-source agents such as @openclaw , hermes @NousResearch , and @opencode etc. Moreover, it is totally free for individual developers. We will continue to provide better models and updates to the community. @huggingface
74
87
7
1,316
99,890
CodeDemo retweeted
🦞👾 LM Studio is now an official @openclaw provider! Run: openclaw onboard --auth-choice lmstudio Use your local models with your OpenClaw - it's private and free. Works on Mac, Windows, and Linux. Let's Claw 🦞🦀
77
297
48
2,459
160,178
Neural Computers arxiv.org/abs/2604.06425
44
256
46
1,703
303,989
CodeDemo retweeted
We're bringing the advisor strategy to the Claude Platform. Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.
1,014
2,687
1,202
37,828
4,789,810
CodeDemo retweeted
This quarter I am teaching a new course titled Large Language Models. The focus is on interpretability, alignment, and agents. All the course materials are public: uchicago-llm-course.github.i…. I have been procrastinating for three weeks for this post, but hope that the materials are useful!
13
135
5
898
42,897
hours, not days 🐼
4
39
3
195
Looks like the "hashrate will drop weeks before the merge due to miners rushing to sell ahead of everyone else" thesis has been proven completely false. I'm a bit surprised! I argued against a 50% drop but definitely expected like 5-10%.
799
1,169
132
9,135
The merge is still expected to happen around Sep 13-15. What's happening today is the Bellatrix hard fork, which *prepares* the chain for the merge. Still important though - make sure to update your clients!
1,477
3,782
601
20,593