Hacker News Reader

I'd rate myself as "above-average receptive" to ML-based tooling, but after trying two "AI autocomplete" tools (Kite and TabNine) I've decided it's not for me. The suggestions were usually good, but I found having complex, nondeterministic IDE commands pretty unsettling.

View on HN

Could actually make you better at producing robust code, though. It's somehow always easier to spot someone else's mistakes than your own.

Or to put it another way: you know you can't trust the AI-generated code w/o convincing yourself it's correct. You think you can trust the code you wrote yourself, but you're probably wrong! :-)

Reply on news.ycombinator.com