Image Text:
Github overview of a pull request for the file AGENTS.md.
Comments regarding line "# Repository Guidelines" in the file:
zanieb: "What's the point of this title? Seems like wasted tokens?"
zanieb: "(certainly inconsequential in the big scheme, but I don't see it adding value)"
charliemarsh: "It ensures that the agent does a good job."
7 Comments
magnetosphere@fedia.io · 17 pts · 100d
I’m proud of the fact that I don’t understand this.
wide_eyed_stupid@lemmy.world · 3 pts · 100d
You and me both.
racketlauncher831@lemmy.ml · 13 pts · 100d
It wastes tokens which is good. Every penny my boss spends on AI brings the company closer to bankruptcy.
addie@feddit.uk · 6 pts · 100d
My company has just implemented a token leaderboard. I find that asking particularly insane questions burns more tokens, since it won't have previous results to fall back on.
racketlauncher831@lemmy.ml · 4 pts · 100d
Kind sir, could you share those questions? I'm in great need!
haverholm@kbin.earth · 4 pts · 100d
If the agent can't tell a contextual comment from an actionable code line, then it is indeed a wasted token. Not because of the header, but because of the "AI" being a useless POS.
Which, to be fair, is the case in pretty much all scenarios.
jj4211@lemmy.world · 2 pts · 100d
Wasn't a comment, it was a header in a markdown prompt for ai agents to slurp into their context.