alt Hacker NewsLooks like a human to me. But some of the public gists on that account suggest a case of AI psychosis e.g. [1] [2]
Also [3] (this is obviously written by AI, but the fact that he publishes it all in public is concerning):
> Claim: The straylight/nix reimplementation is the greatest feat of software engineering in history, normalized by time and resources.
> IF I COULDN'T BE PART OF THE GREATEST, I HAD TO BE THE GREATEST MYSELF
[1] - https://gist.github.com/b7r6/bed1551cc2bb6551eb279b68c5db8de...
[2] - https://gist.github.com/b7r6/193a89d393dd5508c22ca4e6595cdb5...
[3] - https://gist.github.com/b7r6/418ccfe6cf3ac57ad9a100dde560fae...
Replies
Running droids at scale produces weird / zany artifacts, you GC them lazily. Some huge fraction of repositories on GitHub have `CLAUDE.md` full of bonkers machine generated shit, and `gh gist create` of throwaway markdown is a tool call in my harness. This is a transitional time in the software business, I don't think I am unique in still figuring out the effort to spend on garbage collecting junk with a cost model of "GitHub stores it, maybe there's some value in it, let it accumulate".
I posted a C++ house style guide in the hopes that one person somewhere. What's with the fucking full court gang tackle? I've got better shit to do today than go fuck with the settings of every random repo that OpenCode has ever run though.
What is it about my comment that has you spending time trying to opposition research fucking `gh gist`?
Sorted, my random detritus of the `gh gist` tool call in an agent swarm shall bother you no longer. I haven't even read any of those three.
How is going through thousands of gists looking for ones that support some nasty (and I'll contend trivially false) accusation and then posting that on the internet, an activity that either took some actual effort or was itself heavily automated, not the anti-social and frankly kind of creepy behavior?
Also side observation, the last HN user to regularly mention b7r6 (with the strong implication that it's them) got banned here several months ago: https://news.ycombinator.com/item?id=47119245
The "dissertation" linked there (https://github.com/b7r6/cassandra-dissertation) is also incredibly interesting; looks like the HN user asked an LLM to prove/validate that they are "right" in their comments more often than not.
In general, these GH accounts and their repos/gists are kind of a rabbit hole.