- 11comments
- 1comments
- 114comments
- 17comments
- 54comments
- 240comments
- —discuss
- 37comments
- 3comments
- 609comments
- 146comments
- 18comments
- 239comments
- 20comments
- 91comments
- 173comments
- 77comments
- 8comments
- 236comments
- 47comments
- —discuss
- 133comments
- 161comments
- 17comments
- 27comments
- 69comments
- 29comments
- 45comments
- —discuss
- 376comments
just another prompt right?
With a forloop
Yeah, but now with “agentic mapreduce”! A “talent dense” team of prompters selling to the Feds.
Their sample prompt takes me back a year or two:
If I "/goal remove unused code" in Claude today, I would not even think to specify "check for indirect references" and "don't consider generated code dead code," those sorts of intuitions have been "built in" to the frontier models for a while now.
So I'm pretty confused by this, what does it do that I can't with an agent swarm?
If someone came to me with these requirements, I would laugh in their face. These reek of busy work with no actual business benefit. Have these people actually built real software before?
I would categorize these all as grunt work, but definitely not busywork or even a lack of business value. Improving SEO has direct business value. And the fact that it's unglamorous and laborious feels like a really good reason to have agents do it.