// components/efficiency.el - Token efficiency and environment section. // Three cards: local inference / per-task routing / context compression. extern fn el_section(attrs: String, children: String) -> String extern fn el_div(attrs: String, children: String) -> String extern fn el_span(attrs: String, children: String) -> String extern fn el_h2(attrs: String, text: String) -> String extern fn el_p(attrs: String, children: String) -> String fn efficiency() -> String { let header: String = el_div( "class=\"efficiency-header\"", el_div( "class=\"efficiency-label-row reveal\"", el_div("class=\"navy-line-left\" style=\"width:4rem;flex-shrink:0\"", "") + el_span("class=\"label\"", "Efficiency") ) + el_h2( "class=\"display-lg reveal\" style=\"transition-delay:80ms;max-width:32rem\"", "Every token spent " + el_span("class=\"gold\"", "is a choice.") ) + el_p( "class=\"efficiency-sub reveal\" style=\"transition-delay:160ms;margin-top:1.25rem\"", "Cost and environmental impact aren't afterthoughts - they're structural properties of the architecture. I built it that way from the start." ) ) let svg1: String = "" + "" + "" + "" + "" + "" let card1: String = el_div( "class=\"efficiency-card card-dark reveal\"", el_div("class=\"efficiency-icon\"", svg1) + el_p("class=\"efficiency-stat\"", "0 cloud tokens") + el_p("class=\"efficiency-title\"", "Local inference") + el_div("class=\"efficiency-rule\"", "") + el_p("class=\"efficiency-body\"", "The design: run inference entirely on-device via Ollama. No API calls, no inference cost, no carbon footprint from model compute. Full memory and context, zero cloud dependency. This is coming.") ) let svg2: String = "" + "" + "" + "" let card2: String = el_div( "class=\"efficiency-card card-dark reveal\" style=\"transition-delay:150ms\"", el_div("class=\"efficiency-icon\"", svg2) + el_p("class=\"efficiency-stat\"", "Use less") + el_p("class=\"efficiency-title\"", "Per-task routing") + el_div("class=\"efficiency-rule\"", "") + el_p("class=\"efficiency-body\"", "Simple tasks route to small, fast models. Complex reasoning escalates to frontier models only when necessary. And because every model has full access to your accumulated context, cheaper models punch well above their weight.") ) let svg3: String = "" + "" + "" + "" + "" let card3: String = el_div( "class=\"efficiency-card card-dark reveal\" style=\"transition-delay:300ms\"", el_div("class=\"efficiency-icon\"", svg3) + el_p("class=\"efficiency-stat\"", "Fewer tokens") + el_p("class=\"efficiency-title\"", "Same work done") + el_div("class=\"efficiency-rule\"", "") + el_p("class=\"efficiency-body\"", "Every time you open ChatGPT and explain who you are again, that's computation that didn't need to happen. Persistent context means shorter, more targeted prompts. The same outcome with less compute - and a smaller footprint on the planet.") ) let grid: String = el_div("class=\"efficiency-grid\"", card1 + card2 + card3) let pullquote: String = el_div( "class=\"efficiency-pullquote reveal\"", el_p("", "The frontier model without memory of you is starting from scratch every time. A smaller, faster model with years of accumulated context on your work, your decisions, and your patterns will outperform it. The intelligence isn't in the model - it's in what the model knows about you.") ) let bottom_line: String = el_div( "class=\"container\" style=\"margin-top:5rem\"", el_div("class=\"navy-line\"", "") ) el_section( "id=\"efficiency\" aria-label=\"Token efficiency and environment\"", el_div("class=\"container\"", header + grid + pullquote) + bottom_line ) }