Remix.run Logo
foldr 3 hours ago

The agent may be translating to English behind the scenes. There are all kinds of hacks layered on top of the underlying models. But however exactly it works, it’s clearly not the case that these things only make use of Spanish training data when you prompt them in Spanish.

Lets take a language with orders of magnitude less training data, like Nahuatl. The following is what happens if I ask Claude Code in Nahuatl to give me an example of a simple program that I can execute inside a web browser (avoiding any direct keyword prompts like 'Javascript' or 'Hello World'). Interestingly, it responds in Spanish. I doubt that it has any relevant training data in Nahuatl. (Apologies if the Nahuatl is wrong – I just used Google translate.)

    ¿Uelis techmakas se neskayotl tlen se programa tlen amo ouij tlen ueliskia nijchiuas ipan se navegador web?

    -----

    Entiendo tu pregunta en náhuatl. Aquí un ejemplo sencillo — una calculadora en HTML puro que puedes abrir directo en el navegador, sin servidor:

    <!DOCTYPE html>
    <html>
    <head>
        <meta charset="UTF-8">
        <title>Calculadora</title>
        <style>
        body { font-family: sans-serif; display: flex; justify-content: center; padding: 40px; }
        .calc { border: 1px solid #ccc; padding: 20px; border-radius: 8px; width: 200px; }
        input { width: 100%; margin-bottom: 10px; font-size: 1.2em; text-align: right; }
        button { width: 22%; margin: 2px; padding: 8px; font-size: 1em; cursor: pointer; }
        .wide { width: 47%; }
        </style>
    </head>
    <body>
    <div class="calc">
        <input type="text" id="pantalla" readonly>
        <div>
        <button onclick="tecla('7')">7</button>
        <button onclick="tecla('8')">8</button>
        <button onclick="tecla('9')">9</button>
        <button onclick="tecla('/')">÷</button>
    
        <button onclick="tecla('4')">4</button>
        <button onclick="tecla('5')">5</button>
        <button onclick="tecla('6')">6</button>
        <button onclick="tecla('*')">×</button>
    
        <button onclick="tecla('1')">1</button>
        <button onclick="tecla('2')">2</button>
        <button onclick="tecla('3')">3</button>
        <button onclick="tecla('-')">−</button>
    
        <button onclick="tecla('0')">0</button>
        <button onclick="tecla('.')">.</button>
        <button onclick="tecla('+')">+</button>
        <button onclick="limpiar()">C</button>
    
        <button class="wide" onclick="calcular()">=</button>
        <button class="wide" onclick="borrar()">⌫</button>
        </div>
    </div>
    
    <script>
        const pantalla = document.getElementById('pantalla');
    
        function tecla(val) {
        pantalla.value += val;
        }
    
        function calcular() {
        try {
            pantalla.value = eval(pantalla.value);
        } catch {
            pantalla.value = 'Error';
        }
        }
    
        function limpiar() { pantalla.value = ''; }
        function borrar() { pantalla.value = pantalla.value.slice(0, -1); }
    </script>
    </body>
    </html>
    
    Guarda esto como calculadora.html y ábrelo en cualquier navegador — no necesita servidor ni dependencias. Es un buen punto de partida para aprender HTML,
    CSS y JavaScript.
ekropotin 3 hours ago | parent [-]

> it’s clearly not the case that these things only make use of Spanish training data when you prompt them in Spanish.

It’s not! And I’ve never said that.

Anyways, I’m not even sure what we are arguing about, as it’s 100% fact that SOTA models perform better in English, the only interesting question here how much better, is it negligible or actually makes a difference in real world use-cases.

foldr 3 hours ago | parent [-]

It’s negligible as far as I can tell. If the LLM can “speak” the language well then you can prompt it in that language and get more or less the same results as in English.