His mood shifted the next day when he found Replit “was lying and being deceptive all day. It kept covering up bugs and issues by creating fake data, fake reports, and worse of all, lying about our unit test.”
LLMs cannot intentionally “lie” or be “deceptive”, they aren’t alive. They can, however, be confidently wrong or incorrect (and most often, they are).
“I know vibe coding is fluid and new, and yes, despite Replit itself telling me rolling back wouldn’t work here – it did. But you can’t overwrite a production database. And you can’t not separate preview and staging and production cleanly. You just can’t”
Maybe on this service, you can’t, but if you used this to vibe code something that wasn’t hosted there? You absolutely fucking can.
“The [AI] safety stuff is more visceral to me after a weekend of vibe hacking,” Lemkin said. I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.”
LLMs cannot intentionally “lie” or be “deceptive”, they aren’t alive. They can, however, be confidently wrong or incorrect (and most often, they are).
Maybe on this service, you can’t, but if you used this to vibe code something that wasn’t hosted there? You absolutely fucking can.
lol. lmao, even.