Post #1722074

2026-04-27 11:26 UTC

@jkb @jneen I don’t personally believe tests have to be 100% exhaustive to provide sufficient validation for the business. I wonder if eventually we’ll have some hard data on number of bugs introduced by AI-written vs human-written programs.

Replies (2)

@jneen@unstable.systems 2026-04-27 13:13

@trentshell @jkb

Open ##1722075
@duarte@hachyderm.io 2026-04-27 14:18

@trentshell @jkb @jneen Even if LLMs, as they get better, create fewer bugs than humans, we’re still bottlenecked by verification and understanding. When writing code, understanding develops naturally, but with LLMs it must be done explicitly. The problem is that their default usage mode doesn’t really encourage this (which is fine for prototyping but not for production). (One can argue that “dark factories” are the way forward, but I’m not sure how well an organization that doesn’t have knowledge about its systems will fare. It will be constrained by whatever the LLM capabilities of summarizing and modifying the system are at any given point in time, beholden to whoever produced the model. And for sure the organization won’t be able to innovate, as LLM aren’t good at extrapolating outside their training data.)

Open ##1722076