sjmog
Joined 9 years ago
Karma
3
Submissions
6
Member since
May 6
Recent submissions
Comment · 1 year ago
AI feels a lot to me like improv. It’s fun to watch, sometimes, and in experienced hands it can even be great - but it’s missing the crafted core of what makes something really good - the “thing” that great art becomes transparent before.
Comment · 1 year ago
yesterday I posted a video testing claude-4 sonnet solving an https://simstack.io long-horizon swe challenge unaided (https://news.ycombinator.com/item?id=44424468). for comparison, here's gemini 2.5-pro.
I noticed that 2.5-pro is way more cavalier, skipping backups, and trying "more stuff more quickly" than claude's more cautious approach.
Comment · 1 year ago
forgot to mention that the fastest time to solve the first challenge was 43 minutes (cloudflare engineer)
second was a google engineer, 48 minutes
claude + o3 (and a bit of help) does it in about 1h15