David Vaughan

[Ryan Tuffy @TheRyanTuffy]

Most LLM calls in production aren't really generation. They're decisions: route this ticket, flag this prompt, score this urgency.
Laya handles those in one forward pass: ~33ms, calibrated probabilities, zero output tokens.
Open weights, Apache 2.0.

https://t.co/yJmHwyE5Un

[David Vaughan @DavidVaugh38865]

@TheRyanTuffy Spot on.

[David Vaughan @DavidVaugh38865]

Good morning @GoogleWorkspace thank you for your price rise justification email. But I just want email from you, that's all. You too @Atlassian - just want the tool to keep working as is, I'd rather opt out of any upgrades that make the bill bigger.