lots of "LLMs write terrible code, completely unacceptable, I always have to rewrite it to my standards" from the same folks who previously said "my colleagues wrote terrible code, completely unacceptable, I always have to rewrite it to my standards"

Show Post

It’s very clear by now that if LLMs are not improving your software quality it’s either a revealed preference (yours or your org’s) for more volume vs more quality, or a skill issue. The level of testing and review they are enabling in the Go cryptography standard library is amazing.

Show Post

Frontier LLMs are much better and dramatically faster than I am at finding and fixing bugs. If you are not asking them to debug your code and review your bugs, you are doing it wrong. A thread of Claude wins. (No longer at Google, btw.)

Show Post

The number of genuinely useful journalism tools a single developer at my newspaper has built thanks to AI coding is pretty incredible. Us reporters had asked for a lot of them (easier live blogging, better way of importing charts, transcription, calculators) for ages, but suddenly it just gets made!

Show Post

Putting words in the mouths of dead soldiers is next level

Show Post