logoalt Hacker News

zozbot234yesterday at 10:08 PM1 replyview on HN

Calling this a "hit piece" is overblown. Yes, the AI agent has speculated on the matplotlib contributor's motive in rejecting its pull request, and has attributed markedly adverse intentions to him, such as being fearful of being replaced by AI and overprotective of his own work on matplotlib performance. But this was an entirely explainable confabulation given the history of the AI's interactions with the project, and all the AI did was report on it sincerely.

There was no real "attack" beyond that, the worst of it was some sharp criticism over being "discriminated" against compared to human contributors; but as it turns out, this also accurately and sincerely reports on the AI's somewhat creative interpretation of well-known human normative standards, which are actively reinforced in the post-learning training of all mainstream LLM's!

I really don't understand why everyone is calling this a deliberate breach of alignment, when it was nothing of the sort. It was a failure of comprehension with somewhat amusing effects down the road.


Replies

overgardyesterday at 10:18 PM

I don't like assigning "intention" to LLMs, but the actions here speak for themselves, it created a public page for the purpose of shaming a person that did something it didn't "like". It's not illegal, but it is bullying.

show 1 reply