Seems cute, but ultimately not very valuable without benchmarks or some kind of evaluation. For all I know, this could make Claude worse.
Superpowers: How I'm using coding agents in October 2025
11–20 of 242 posts
Re: Superpowers: How I'm using coding agents in October 2025
#12What's the cost of running with agents like this?
Re: Superpowers: How I'm using coding agents in October 2025
#13take #73895 on how to fix ur prompt to make ur slop better.
is better slop a bad thing somehow?
Re: Superpowers: How I'm using coding agents in October 2025
#14This is so interesting but it reads like satire. I'm sure folks who love persuading and teaching and marshalling groups are going to do very well in SWEng. According to this, we'll all be reading the feelings journals of our LLM children and scolding them for cheating on our carefully crafted exams instead of, you know, making things. We'll read psychology books, apparently. I like reading and tinkering directly. If…
We certainly will; they can’t replace humans in most language tasks without having a human like emotional model. I have a whole therapy set of agents to debug neurotic long lived agents with memory.
what on God's green Earth could the CEO of a no name b2b saas have a use for long running agents?
either your business isn't successful, so you're coding when you shouldn't be, or cosplaying coding with Claude, or you're lying, or you're telling us about your expensive and unproductive hobby.
How much do you spend on AI? What's your annual profit?
edit: oh cosplaying as a CEO. I see. Nice WPEngine landing page Mr AppBind.com CEO. Better have Claude fix your website! I guess that agent needs therapy...
Re: Superpowers: How I'm using coding agents in October 2025
#15> …*RIGHT NOW, go read…
I don’t like the looks of that. If I used this, how soon before those instructions would be in conflict with my actual priorities?
Not everything can be the first law.
Re: Superpowers: How I'm using coding agents in October 2025
#16Has anyone ever seen an instance in which the automated "How" removal actually improves an article title on HN rather than just making them wrong? (There probably are some. Most likely I notice the bad ones more than the good ones. But it does seem like I notice a lot of bad ones, and never any good ones.) [EDITED to add:] For context, the actual article title begins "Superpowers: How I'm using ..." and it has been a…
Yeah, to the point I can recall several examples where the title stuck out as dumb on HN and only when visiting the original page it started to make sense, but not a single case where I could say the automated removal really did a good job.
Re: Superpowers: How I'm using coding agents in October 2025
#17Re: Superpowers: How I'm using coding agents in October 2025
#18Has anyone ever seen an instance in which the automated "How" removal actually improves an article title on HN rather than just making them wrong? (There probably are some. Most likely I notice the bad ones more than the good ones. But it does seem like I notice a lot of bad ones, and never any good ones.) [EDITED to add:] For context, the actual article title begins "Superpowers: How I'm using ..." and it has been a…
I've had it happen with me a few times where it was reasonable, sometimes where it was debatable, and if it was just wrong I edit it to add the How back in.
Re: Superpowers: How I'm using coding agents in October 2025
#19It's not a superpower if everybody has that same power.
Everyone is better off with mobile phones. We can solve more diverse problems faster. Similarly we can combine our diverse superpowers (as they show in kids cartoons)
Re: Superpowers: How I'm using coding agents in October 2025
#20What's the cost of running with agents like this?
Claude Max is fixed cost