Skip to main content

Perplexity Will Open Source Its Faster Lily AI Engine For Apple Silicon

BrianFagioli writes: Perplexity has built a local artificial intelligence engine designed specifically for Apple silicon and the Qwen3.6-35B-A3B model. Called Lily, the engine uses a Rust runtime and custom Metal kernels, with neither PyTorch nor MLX in its execution path. Perplexity says Lily averaged 23 percent faster prompt processing and 35 percent faster token generation than MLX-LM on an M5…

entertainment.slashdot.org ·1h ago

We haven't written up this one. Slashdot has the full story — the link below goes straight to it.

Read the original at entertainment.slashdot.org →

More in AI

The Repository Is the Runtime

How much software-engineering knowledge can we compile into deterministic constraints so that model intelligence matters less?

1h ago ·dev.to

AWS Lets Agent Builders Restrict Web Search to Approved, Recent Sources

AWS has added domain and publish-date filtering to the Web Search tool inside Amazon Bedrock AgentCore, according to the AWS Machine Learning Blog .

AWS introduces domain and publish-date filtering for Web Search in AgentCore.
Filters limit search to predetermined domains and recent sources.
Enhances relevance, reliability, and security for AI agents.

1h ago ·dev.to

SIT to give undergrads nearly 2 years’ work experience for better job prospects in age of AI

It's meant to give fresh graduates an edge in their job hunt as growing AI capabilities raise the bar for new hires.

1h ago ·straitstimes.com

Why Most Multi-Agent Systems Fail in Production (And How to Fix It)

Most multi-agent demos look impressive on stage. Then they hit production and fall apart. Here's the pattern: agents that "worked" in a Jupyter notebook start conflicting, retrying infinitely, or…

Multi-agent systems fail in production due to lack of structured communication.
Agents use plain text messages leading to misinterpretations and errors.
Absence of retry mechanisms causes failures to halt or loop endlessly.

1h ago ·dev.to

How to Stop Fighting Your AI Coding Assistant

I used to hate AI coding assistants. They felt like talking to a junior developer who had read the documentation once and forgot the rest.

Treat AI assistants as probabilistic text generators, not oracles
Break down complex tasks into smaller, manageable steps
Provide clear context, style preferences, and constraints to guide AI

1h ago ·dev.to

EPA proposal could leave the public in the dark on data center plans

EPA proposal could remove public notification requirement for data center permits.
Critics argue this hinders local residents' ability to learn about new data centers.
EPA spokesperson claims proposal streamlines permitting for minor pollution sources.

1h ago ·winnipegfreepress.com

More from Thursday 3 September →