Hackernews posts about Model X

1. Show HN: Apple Foundation Model in Xcode-Beta (gist.github.com)
   4 points by edgcumbe 4 days ago | discuss
2. Show HN: A GPU/VRAM filter for finding LLMs that will run on your hardware (www.whichllmmodel.com)
   2 points by mzubairtahir 13 days ago | 12 comments
3. Show HN: Run Agent Skills with mistral.rs v0.8.10: /v1/skills support and more
   20 points by ericlbuehler 21 days ago | 2 comments
4. Show HN: Jacobi–IDE for Abaqus subroutine with analytical tests and AI diagnosis (jacobee.netlify.app)
   18 points by white_tiger 17 days ago | 6 comments
5. Show HN: Bike4Mind – open-core AI workbench; any model, agents, RAG, self-host (github.com)
   3 points by erikbethke 1 day ago | 2 comments
6. One Model Won't Save You: How We Built Our AI Stack (www.xelerate.tech)
   3 points by pedrocha 20 days ago | discuss
7. China's Xiaomi MiMo Is Now 15X Faster Than ChatGPT and Claude (decrypt.co)
   3 points by gmays 28 days ago | discuss
8. Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir (github.com)
   3 points by caudena 20 days ago | 1 comments
9. Claude: Elevated errors across many models [resolved] (status.claude.com)
   189 points by forks 22 days ago | 160 comments
10. Show HN: I trained a language model that thinks the capital of Japan is Paris (hamiltonianresearch.xyz)
    15 points by farisallafi 4 days ago | 8 comments
11. Claude Sonnet 5: Anthropic's Most Agentic AI Model Arrives at a Reduced Price (2026) (lucasaguiar.xyz)
    4 points by isfttr 2 days ago | discuss
12. Meituan Trained a 1.6T-Parameter AI Model Without Nvidia GPUs (xyzlabs.substack.com)
    3 points by mgh2 4 days ago | 1 comments
13. InfiniteDiffusion: A new approach to infinite generation with diffusion models (twitter.com)
    3 points by LorenDB 13 days ago | 1 comments
14. Show HN: Skeights – Serialize sklearn models to safetensors and JSON, no pickle (github.com)
    3 points by alxhslm 2 days ago | discuss
15. I tested Gemma4 12B on my 8GB GPU, now I don't want to go back to smaller models (www.xda-developers.com)
    3 points by theanonymousone 20 days ago | discuss
16. Grok models are now available via Amazon Bedrock (x.ai)
    3 points by peterspath 20 days ago | discuss
17. Show HN: AccInt – a Work Model for AI coding agents (accint.xyz)
    3 points by maxbaluev 26 days ago | discuss
18. Probabilistic "Copies" in Generative AI Models [pdf] (download.ssrn.com)
    2 points by droidjj about 19 hours ago | 1 comments
19. Show HN: Bosun – a small model that keeps an agent's memory graph clean (huggingface.co)
    2 points by trashhalo 27 days ago | 1 comments
20. Coding and debugging will fall back to older model in Fable 5.Losing hope as Dev (x.com)
    2 points by riponcm 8 days ago | discuss
21. Show HN: Assist: an open-model-first work surface for agents (www.withassist.xyz)
    2 points by js4 14 days ago | discuss
22. Instant cut list optimizer with 3D Model and PDF Import (www.cutlistor.com)
    2 points by xiyan 14 days ago | discuss
23. Show HN: DocStreamAI – Automatic invoice/receipt collection for Quickbooks/Xero (docstreamai.com)
    2 points by alexjimenez99 28 days ago | discuss
24. Rethinking the Value of Arbitrary Order in Diffusion Models (arxiv.org)
    2 points by x312 28 days ago | discuss
25. Bringing the latest Gemini models to Apple developers (blog.google)
    2 points by xnx 30 days ago | discuss
26. Ask HN: Why not compare Fable 5 with GPT "Pro"? Why compare with GPT xhigh?
    1 points by behnamoh 27 days ago | 3 comments
27. Large language models can predict the results of social science experiments (www.nature.com)
    1 points by sbulaev about 1 hour ago | discuss
28. Ask HN: Which AI model do you use for what?
    1 points by akashwadhwani35 4 days ago | discuss
29. GLM-5.2 is the leading open weights model on the Intelligence Index v4.1 (xcancel.com)
    1 points by alecco 21 days ago | discuss
30. Launch HN: Manufact (YC S25) – MCP Cloud (manufact.com)
    111 points by pzullo 6 days ago | 70 comments