[denkmoon]

Insane. An LLM is just as likely to hallucinate a missing/extra underscore and ping the wrong person. A machine cannot be held accountable.

[Noumenon72]

My LLMs frequently find subtle typos and never make subtle typos. I don't think that's equally likely at all.

[denkmoon]

Just today I had an incident review meeting resulting from a prod incident where the root cause was an LLM refactor stripping ! from the front of a boolean statement "for no reason". Not to mention how often I've seen garbled output from the LLM.

Lots of things failed for that to reach prod, but the assertion that LLMs do not make subtle typos... is not congruent with my experience.

[phendrenad2]

Which LLM? When was this code written? When was the last time you saw "garbled output" and what was the context?

I'm really trying to get to the bottom of these claims, because I see them a lot and it's so wildly different from most people's experiences.

[Silamoth]

If a lot of people make the same claim, then from their perspective, you’re the one with a “wildly different” experience. What makes you so certain your experience generalizes to “most people’s experiences”?

[Ukv]

> Insane. An LLM is just as likely to hallucinate a missing/extra underscore and ping the wrong person

If it's just for "Catching typos", a hallucinated missing/extra underscore would just be a false positive to dismiss.

> A machine cannot be held accountable.

Seems unlikely that his lawyer, the law firm, the judge, whoever made the typo, or the police department will be held accountable either.

Nor can any of the tools they used, since that's not really the level at which it makes sense to hold accountability, but that's no reason not to use a tool that could find errors and reduce the chance for an innocent person to spend time in prison.

[Dilettante_]

Using LLMs to find errors and using LLMs to produce error-free artifacts are two extremely different levels of challenge.

[phendrenad2]

What's insane is that people say things like this in 2026. I suspect it stems from being retired and not really using LLMs for work, and instead using them for leisure, and therefore not knowing that they're extremely capable for logical operations, much more than they are for entertainment. Your second point about "machine cannot be held accountable" is a non sequitur, so I'll leave it.