Perplexity

Planet AI Developer Filter September 03, 2026 06:57

Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon

Perplexity open sourced Lily, a Rust and Metal inference engine running Qwen3.6-35B-A3B on Apple silicon, 1.35x faster decode.

Entities: Perplexity

Planet AI Developer Filter September 02, 2026 05:12

Perplexity Releases Hybrid Compute on Mac: Cloud Agents Orchestrate Down to a Local Model, Gated On Device

Perplexity hybrid compute splits a Mac task across cloud and local models, gated by an open-sourced on-device classifier.

Entities: Perplexity

The New Stack AI Coding Filter August 25, 2026 15:34

Perplexity’s Computer agent can now run locally — if you can afford it

Perplexity’s Portable Computer runs locally on Nvidia RTX GPUs and the DGX Spark.

Entities: NVIDIA Perplexity Nvidia RTX

Planet AI Developer Filter August 21, 2026 14:08

Release langchain-perplexity==1.4.1 · langchain-ai/langchain

The agent engineering platform. Contribute to langchain-ai/langchain development by creating an account on GitHub.

Entities: Perplexity

Mitchell Bryson AI Builder Articles April 17, 2026 00:00

The desktop just became the new front line - Mitchell Bryson

In a single 24-hour window, Google gave away a native Gemini Mac app, Perplexity began charging $200/month for an always-on desktop agent, and Mozilla dropped an open-source alternative for enterprises who refuse vendor lock-in. Three radically different...

Entities: Google Gemini Perplexity

Mitchell Bryson AI Builder Articles March 14, 2026 00:00

The always-on agent needs its own computer - Mitchell Bryson

In a single week, the AI industry acknowledged that agents are a fundamentally different computing paradigm. Perplexity shipped a $200/month always-on agent running on dedicated Mac mini hardware. Microsoft built Copilot Cowork as a persistent cloud agent...

Entities: NVIDIA Microsoft Perplexity