I actually looked for them but didn't find the open weights. I only found their ASR models, which are different? https://
huggingface.co/XiaomiMiMo/MiM
o-V2.5-ASR
…
LLMS
-
Xiaomi MiMo V2.5 ASR Models Open Weights Search
By
–
-
Higher Resolution LLM Architecture Gallery and Summaries
By
–
Higher res figures (and summaries) in the LLM architecture gallery:
-
Dense Gemma 4 and Qwen 3.6 Models vs MoE Trade-offs
By
–
Not necessarily everyone, since MoE can also add a lot of headache. There are dense Gemma 4 and Qwen3.6 variants
-
Claude Skills: AI Community’s Favorite Feature This Year
By
–
Skills are easily my favorite Claude feature this year
-
Monthly AI Model Releases Demand Frequent Evaluation Cycles
By
–
Monthly model releases means we're going to need monthly evals haha
-
Discussion on Claude Code API implementation and compatibility
By
–
Le projet est open source e si certain se chauffe… . Après vu que je passe par l’api codex server app pas sûr que Claude code est la même.
-
AutoReason: Advancing AI Reasoning Research and Model Discovery
By
–
Paper: https://
github.com/NousResearch/a
utoreason/blob/main/paper/autoreason.pdf
… Check out http://
AlphaSignal.ai to get a daily summary of top models, repos, and papers in AI. Read by 280,000+ devs. -
Self-refinement loops in AI: Problems and solutions
By
–
Karpathy-inspired paper proves self-refinement destroys your AI's own output. Most AI self-refinement loops make outputs worse. Models hallucinate flaws to satisfy critique prompts. They expand scope every pass. They never stop editing. Autoreason is a new paper that fixes
-
AI Model Evaluation Benchmarks Limited Testing Scope Critique
By
–
Same energy as "we only tested on MMLU" a year ago haha
-
Beyond Model Size: Smart Scaffolding for LLM Agents
By
–
Think building an AI agent is just a better brain? What if the real secret is what you add outside the model? A team from Shanghai Jiao Tong University, OPPO, and others argues that the future of LLM agents isn't about bigger weights, but smarter scaffolding. They introduce a