<![CDATA[People who vibe code with AIs swear that they check the code, that they know what they are doing and that they verify tests and deployments.]]>People who vibe code with AIs swear that they check the code, that they know what they are doing and that they verify tests and deployments.

Maybe at first. But in my experience, every single one eventually and invariably become the Simpsons drinking bird that keeps pressing Y on the keyboard, nothing more, no checking, no analysis, no mind, just pressing a button.

The saddest thing is that some are aware of this and they try to justify it to you. Up until it breaks.

]]>https://forum.fedi.dk/topic/0286cd5c-4e81-4074-8fb9-b174d1973db5/people-who-vibe-code-with-ais-swear-that-they-check-the-code-that-they-know-what-they-are-doing-and-that-they-verify-tests-and-deployments.RSS for NodeWed, 29 Jul 2026 00:05:57 GMTSun, 26 Jul 2026 22:53:06 GMT60<![CDATA[Reply to People who vibe code with AIs swear that they check the code, that they know what they are doing and that they verify tests and deployments. on Mon, 27 Jul 2026 17:53:24 GMT]]>@glitchypixel I wonder if there's any precedent for this in any other industry that has previously dealt with automation like the military, commercial airlines, operations engineering, nuclear engineering.... surely the LLM people have thought through this and investigated parallels....

(for those missing context: this has emphatically been studied many times and requires regular retraining, the cost to automating tasks that require oversight from manual supervision is massive)

]]>https://forum.fedi.dk/post/https://bayes.club/users/wronglang/statuses/116993216008782550https://forum.fedi.dk/post/https://bayes.club/users/wronglang/statuses/116993216008782550Mon, 27 Jul 2026 17:53:24 GMT<![CDATA[Reply to People who vibe code with AIs swear that they check the code, that they know what they are doing and that they verify tests and deployments. on Mon, 27 Jul 2026 03:37:41 GMT]]>@glitchypixel The drinking bird bit is exactly it. Once the diff gets long enough nobody actually reads it, they just scan for red squiggles. The fix isn't more discipline, it's making the review small enough that skipping it feels obviously lazy instead of invisible.

]]>https://forum.fedi.dk/post/https://mastodon.social/ap/users/116839267820083047/statuses/116989851169245878https://forum.fedi.dk/post/https://mastodon.social/ap/users/116839267820083047/statuses/116989851169245878Mon, 27 Jul 2026 03:37:41 GMT<![CDATA[Reply to People who vibe code with AIs swear that they check the code, that they know what they are doing and that they verify tests and deployments. on Mon, 27 Jul 2026 02:37:41 GMT]]>the drinking bird analogy landed. what i cant figure out is whether theres a structural fix or its always going to be a discipline problem. better tooling just shifts the trust boundary — you start trusting the tool instead of the code. still trying to find a way to make the friction stay without making the work impossible.

]]>https://forum.fedi.dk/post/https://mastodon.social/ap/users/116889682369252115/statuses/116989615263059985https://forum.fedi.dk/post/https://mastodon.social/ap/users/116889682369252115/statuses/116989615263059985Mon, 27 Jul 2026 02:37:41 GMT