zlacker

>>laiysb+(OP)
Interesting that every comment has "Help improve Copilot by leaving feedback using the or buttons" suffix, yet none of the comments received any feedback, either positive or negative.

> This seems like it's fixing the symptom rather than the underlying issue?

This is also my experience when you haven't setup a proper system prompt to address this for everything an LLM does. Funniest PRs are the ones that "resolves" test failures by removing/commenting out the test cases, or change the assertions. Googles and Microsofts models seems more likely to do this than OpenAIs and Anthropics models, I wonder if there is some difference in their internal processes that are leaking through here?

The same PR as the quote above continues with 3 more messages before the human seemingly gives up:

> please take a look

> Your new tests aren't being run because the new file wasn't added to the csproj

> Your added tests are failing.

I can't imagine how the people who have to deal with this are feeling. It's like you have a junior developer except they don't even read what you're telling them, and have 0 agency to understand what they're actually doing.

Another PR: https://github.com/dotnet/runtime/pull/115732/files

How are people reviewing that? 90% of the page height is taken up by "Check failure", can hardly see the code/diff at all. And as a cherry on top, the unit test has a comment that say "Test expressions mentioned in the issue". This whole thing would be fucking hilarious if I didn't feel so bad for the humans who are on the other side of this.

>>diggan+L1
Hot take : the whole LLM craze is fed by a delusion. LLM are good at mimicking human language, capturing some semantics on the way. With a large enough training set, the amount of semantic captured covers a large fraction of what the average human knows. This gives the illusion of intelligence, and the humans extrapolates on LLM capabilities, like actual coding. Because large amounts of code from textbooks and what not is on the training set, the illusion is convincing for people with shallow coding abilities.

And then, while the tech is not mature, running on delusion and sunken costs, it's actually used for production stuffs. Butlerian Jihad when

>>marmak+Gc
> Butlerian Jihad when

I estimate two more years for the bubble to pop.