Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint(prismml.com)

551 points by JonSchneider 1 month ago | 176 comments

PrismML blog post announcing Bonsai 2 27B, a compressed language model claiming near-lossless quality at a 9x smaller footprint.

Ternary Bonsai: Top Intelligence at 1.58 Bits(prismml.com)

202 points by nnx 6 months ago | 54 comments

1-Bit Bonsai Image 4B Image Generation for Local Devices(prismml.com)

438 points by modinfo 4 months ago | 186 comments

PrismML blog post announcing Bonsai Image 4B, a 1-bit and ternary quantized image generation model designed to run on local devices.

Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs(prismml.com)

385 points by PrismML 6 months ago | 144 comments

Homepage of PrismML, a startup building ultra-dense, compact AI models such as its 1-bit Bonsai LLMs for smartphones and efficient datacenters.

CEO: Raspberry Pi stock to hit 1M units monthly, starting in July(arstechnica.com)

27 points by sohkamyung 3 years ago | 30 comments

Waymo One is now open to everyone in San Francisco(waymo.com)

435 points by ra7 2 years ago | 525 comments

Waymo blog post from June 25, 2024 announcing that its Waymo One robotaxi service is now open to everyone in San Francisco.

Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint(prismml.com)

551 points by JonSchneider 1 month ago | 176 comments

PrismML blog post announcing Bonsai 2 27B, a compressed language model claiming near-lossless quality at a 9x smaller footprint.

Plan mode is dead(aymannadeem.com)

537 points by jmvldz 1 month ago | 468 comments

Blog post by Ayman Nadeem arguing that plan mode in AI coding tools is obsolete, reflecting on building the Nuanced desktop coding app around planning.

AI agent opens a PR write a blogpost to shames the maintainer who closes it(github.com)

747 points by wrxd 8 months ago | 581 comments

A closed GitHub pull request to matplotlib by user crabby-rathbun proposing to replace np.column_stack with np.vstack().T for performance.

What AI-Native Looks Like(fagnerbrack.com)

14 points by fagnerbrack 1 month ago | 7 comments

A blog post by Fagner Brack on Medium describing what an AI-native approach to software development with stable infrastructure looks like.

Gemini 2.0: our new AI model for the agentic era(blog.google)

961 points by meetpateltech 1 year ago | 469 comments

Google blog post by Sundar Pichai, Demis Hassabis and Koray Kavukcuoglu announcing Gemini 2.0, a new AI model aimed at agentic use cases.

Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning(techcommunity.microsoft.com)

399 points by lappa 1 year ago | 136 comments

Microsoft AI Platform Blog post announcing Phi-4, a small language model specializing in complex reasoning.