gojkoa · HackerTrans

45 分前議論

The study unfortunately looks only at individual productivity, not any org gains, and the big claim in the PDF is that adopters "merge roughly 24% more pull requests" over a four month period. not exactly headline-making material. There's no data in the paper whether those 24% extra pull requests actually added anything more valuable or not.

gojkoa

8 時間前議論

(using claude code) I force the agent to work in steps where each step changes no more than 4-5 files, where each step has some observable result, ideally unit testable or e2e integration testable, and do a quick git diff/git add after each step. I have a bunch of deterministic checks (custom linting rules) that verify pretty much any repeatable comment I had to provide to Claude code over time (Claude is also writing/maintaining the rules, and unit tests for the rules) so I can focus on identifying new stuff. It took a few months to grow this rule set but now it exists things work pretty smoothly.

gojkoa

8 時間前議論

0. product developer/consultant

1. macbook pro, generally maxed out spec at time of purchase

2. 5-6 years

gojkoa

8 時間前議論

combining idea banks/feature request boards with popular product management surveys, with the idea to help people discover better signals from the noise of user feedback, and then follow up with interested users for in-depth research. We used to do this combining several tools for a SaaS product that we sold last year, and I thought it would be useful to build a unified service so everything is in a single tool. An early version (useful but not fully polished) is live at https://www.votito.com

コメント