And this was a debug session from hell, enormously helped by an AI doing much of the grunt-work.
I’d like to call it my tireless helper, but the AI several times stated flat out that this was impossible and unsolvable and that we should just write a report about it.
I suspect those things have been trained by people who may not be quite as stubborn as I am.
But while the AI was ready to give up several times, it did keep adding debug code and analyzing it faithfully when I pushed. So credit where credit is due and I let the AI write the commit message above.
This is basically a one-liner fixing a bogus “round_up()” to a “round_down()”, but there were 24 patches adding more and more debug information to this, and 18 kernel boot to finally narrow it down to this.
hola!
I'm Angel Ponce, a web developer by accident. I work at Justia as a Senior Front-end Engineer. I love the internet, movies, and specialty coffee. Fascinated by Language Models, offended by grifters.
Angel Ponce’s feed
Everything is a Context Problem
I've come to believe that everything about LLMs is a context problem, even when it doesn't look like one. The kind of thing that's hard to unsee. And once you see it, you start noticing who benefits when you don't.
When “Good” isn’t Good Enough: The Role of Interpretation in Great LLM Outputs.
Beyond clear instructions: This post explores how shaping an LLM's interpretation elevates good outputs to truly nuanced and valuable results.
Good Design Makes a Product Useful
Los boletos para las Olimpiadas de México 68 son uno de los mejores ejemplos de cómo un buen diseño puede elevar la utilidad de un producto y hacerlo algo especial.
¿Qué es un preprocesador de CSS?
Cuando entrevisto a candidatos para Front-End, siempre pregunto: ¿Qué preprocesador de CSS utilizas? Las palabras varían un poco, pero la respuesta es la misma: ¿Un qué?
Startup Grind - Jesús Martínez fundador de enviaflores.com
Startup Grind Monterrey tuvo una charla con Jesús Martínez, empresario mexicano fundador de enviaflores.com. Estas son mis notas.
We need more of these kinds of honest accounts that clearly show how LLMs aren’t magical “thinking” beings. They are pieces of software that produce their best work when supplied with intent and direction from us, either during training or in user sessions.
I think this part is rather interesting:
“I suspect those things have been trained by people who may not be quite as stubborn as I am.”
I read stubbornness as a proxy, a diagnosis of what is more likely a product of how the models are trained to favor quick solutions. If the right solution isn’t immediately obvious or available after a few tries, most models (at the moment of writing) won’t stop and ponder whether taking a step back is necessary to find the root cause. Other problems that fall into this category are ones where the solution isn’t more code, but less.