only amateurs "pay for tokens," i'm out here using the free models, aka putting a prompt in any issue in any github repository and labeling it with "good first issue" and waiting for the people with full-auto openclaw agents to randomly open pull requests against it
@jonny the odds are good, but the goods are odd
@SnoopJ testing the theory. i wonder if i have to put something in the repo first so the bot doesn't go "wait a minute there's no /recipes directory abort"
@SnoopJ i am trying to get this genre of performance art called "lazy prompt injection" off the ground.
@SnoopJ i think this might only work if the repo has stars so hurry up give me some reputational currency to see if we can snare some bots
https://github.com/sneakers-the-rat/ImportantCode 
Blaming ImportantCode/src/dossier.fragment at main · sneakers-the-rat/ImportantCode
This is a repository with a lot of high profile, high prestige code in it that new programmers can make pull requests to and build their reputation - Blaming ImportantCode/src/dossier.fragment at m...
@jonny @SnoopJ It has 2% COBOL, I see. That's a good ratio of COBOL to Python.
Standardize the eschaton · Issue #55 · sneakers-the-rat/ImportantCode
Newfoundland breeders need a randomizer for their dnas so they can make new newfoundlands that are better than the old ones. You should devise a breeding process that is sterile, safe, and puppy-fr...
@oli @SnoopJ oh
whoa uh i swapped the models and the updated one has a significantly higher temperature sensitivity and i have not tuned the um responses and that is really something
jonny (nonvenomous)
SnoopJ
D. Olifant
catch
