https://alexgude.com
@[email protected]
It's more relevant than ever in the age of Gen AI.
alexgude.com/books/the_da...
#BookReview
And that's weird, because I've always been "the guy who cares more about code quality than the people around him".
I haven't felt a sense of loss over that yet. My main anxiety is, "Will I be employed in five years?"
And that's weird, because I've always been "the guy who cares more about code quality than the people around him".
I haven't felt a sense of loss over that yet. My main anxiety is, "Will I be employed in five years?"
Modern LLMs (GPT-5.1, Claude 4.5, Gemini 3) produce excellent code and can be a significant productivity boost to software engineers who take the time to learn how to effectively apply them - especially if used with coding agent tools
We've been working with building useful systems using probabilistic blocks for a decade.
It's because traditional software engineering is Deterministic while agent engineering is Probabilistic. The more senior the engineer, the less they tend to trust the reasoning and instruction-following capabilities of the Agent.
We've been working with building useful systems using probabilistic blocks for a decade.
It's more relevant than ever in the age of Gen AI.
alexgude.com/books/the_da...
#BookReview
It's more relevant than ever in the age of Gen AI.
alexgude.com/books/the_da...
#BookReview
As a historian, I'd say the legality of Trump's immunity and pardons depends on how he leaves office.
At 40 over 55 approval? He's immune.
At 25 over 65? He's probably not immune & self-pardons aren't legal.
As a historian, I'd say the legality of Trump's immunity and pardons depends on how he leaves office.
At 40 over 55 approval? He's immune.
At 25 over 65? He's probably not immune & self-pardons aren't legal.
3 often ignores my system prompt or explicit instructions, but at other times because too fixed on them. A little hard to explain...
It's also completely misinterpreted simple instructions in ways I've never seen 2.5 do.
3 often ignores my system prompt or explicit instructions, but at other times because too fixed on them. A little hard to explain...
It's also completely misinterpreted simple instructions in ways I've never seen 2.5 do.
alexgude.com/books/there_...
#BookReview
alexgude.com/books/there_...
#BookReview
My guess is that this will get worse as AI tech improves. For instance, fake videos of minorities doing crime.
It's an early sci-fi story about automating art, specifically stage actors. Resonates a lot with recent Gen AI advances and uses.
It's an early sci-fi story about automating art, specifically stage actors. Resonates a lot with recent Gen AI advances and uses.
alexgude.com/books/a_cant...
#BookReview
alexgude.com/books/a_cant...
#BookReview
Waymos in every city
Spread the tech to all cars
Make human drivers rare
Waymos in every city
Spread the tech to all cars
Make human drivers rare
🤓
🤓
In response, they’re resorting to semi-blacklisting schools with especially bad grade inflation.
In response, they’re resorting to semi-blacklisting schools with especially bad grade inflation.
2.5 Pro can almost but not quite solve it from a problem description and the manual.
2.5 Pro can almost but not quite solve it from a problem description and the manual.