ivanech

Yes you can drive up to your opponent and hit them point blank

Wow, that’s an egregious chart crime. Surely there’s a way to make a chart that isn’t so dishonest. Just plotting the SPR level would make the same point honestly.

Hmm in my experience (I've done a lot of head-to-heads), Opus 4.6 is a weaker reviewer than GPT 5.4 xhigh. 5.4 xhigh gives very deep, very high-signal reviews and catches serious bugs much more reliably. I think it's possible you're observing Opus 4.6's higher baseline acceptance rate instead of GPT 5.4's higher implementation quality bar.

This feels similar to March 2020 when COVID was in Seattle. “It’s in the US but maybe it’s just a one-off.” We’ll see, I guess.

this was really delightful. The Easter eggs in particular made it feel like someone was actually on the other side

I find Opus 4.5 very, very strong at matching the prevailing conventions/idioms/abstractions in a large, established codebase. But I guess I'm quite sensitive to this kind of thing so I explicitly ask Opus 4.5 to read adjacent code which is perhaps why it does it so well. All it takes is a sentence or two, though.

I believe the new grad DOGE employees were GS-15s. So yes, it seems likely that they plan to hire at GS-14 or GS-15.

tried replicating w/ a slightly different system prompt w/ sonnet-4.5 and got some different results, esp w/ progressive to conservative questions. Prompting seems pretty load-bearing here

AI tools have been so good for me for making home-cooked software. As a new-ish parent, it’s so much easier to do stuff. I don’t need to go into extra-deep focus mode to learn how to center a div for the hundredth time, I can spend that precious focus time on the problems that matter / the core motivation.

I had a good laugh at the image showing that 2018 had a “quality focus”

I think Jonathan Blow gave his “Preventing the Collapse of Civilization” talk (much stronger treatment of the subject matter) around that time, also about how software quality was only going down