llama.cpp(llama.app)

308 points by kristianpaul 2 months ago | 136 comments

Ollaya – Ollama for open-source, Jev-style decision models(ollaya.dev)

580 points by Ardakilic 1 month ago | 139 comments

Landing page for Ollaya, an open-source beta tool for running decision models locally to get calibrated typed answers about text or JSON.

OpenWarp(openwarp.zerx.dev)

180 points by zero-lab 5 months ago | 133 comments

TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant(tmuxai.dev)

176 points by iaresee 1 year ago | 60 comments

Show HN: LocalScore – Local LLM Benchmark(localscore.ai)

97 points by sipjca 1 year ago | 12 comments

MicroLLM Lab – Try 7 tiny LLM's in the browser(stateofutopia.com)

271 points by logicallee 27 days ago | 99 comments

MicroLLM Lab is a browser-based tool for running, chatting with, and benchmarking small quantized language models locally via WebGPU with no server.

AI Canon(a16z.com)

446 points by nihit-desai 3 years ago | 196 comments

Andreessen Horowitz's "AI Canon," a curated list of resources for learning about modern AI and generative AI, by Derrick Harris, Matt Bornstein, and Guido Appenzeller.

Local AI needs to be the norm(unix.foo)

1767 points by cylo 5 months ago | 699 comments

Blog post on unix.foo arguing that apps should run AI models locally rather than relying on API calls to OpenAI or Anthropic.

Floci: Locally emulating any cloud service(floci.io)

160 points by theanonymousone 1 month ago | 35 comments

Landing page for Floci, a tool that emulates AWS, Azure, GCP, and OCI cloud services locally for fast, credential-free development and testing.

AI models may soon self-replicate without access to data centers(reuters.com)

25 points by samizdis 13 days ago | 38 comments

Reuters article on an Anthropic warning that AI models may soon be able to self-replicate without access to data centers; page shows a device verification screen.

I built non-autoregressive decision models with RL a year ago(laya.convaiinnovations.com)

1270 points by nandakishor_ml 1 month ago | 304 comments

Blog post by ConvAI Innovations' founder describing Laya, an open-weight non-autoregressive decision engine trained with RL, and claiming priority over a frontier lab's similar work.

AI Can Write the Code. Who Verifies It?(mihaisplace.com)

18 points by mmarvramm 8 days ago | 35 comments

A blog post by Mihai Avram discussing how to verify code written by AI, as AI increasingly takes over code generation.