Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Superpowers: How I'm using coding agents in October 2025

blog.fsck.com

Post reply on HN
Print view View original

171–180 of 242 posts

Re: Superpowers: How I'm using coding agents in October 2025

#171

Post by apwell23 »

simonw wrote: post #116
GOD_Over_Djinn wrote: post #102

Earlier quoted context omitted.

The past few years have taught me that these are the people that rise to the top of society (much to my chagrin). The average person doesn’t want to hear from thoughtful intellectuals presenting nuanced opinions. They want to hear from those who brashly and boastfully present themselves as authority figures, and then bolster the listeners preconceived ideas with violently exaggerated language. Shallow but sensational…

I try very hard to fulfill the role of "thoughtful intellectuals presenting nuanced opinions" in the AI space. I'm disappointed that I've failed to meet that standard in your eyes.

it was fine to say this is something new and ppl should maybe look at it. but strongly recommending its and calling it wild is not a nuanced opinion. esp given you have not actually used it yourself in any serious way. is it really that big a ask to only use hype words for things you've actually used and made a big difference to you.

edit: looks like my comments crossed into personally attacking you . i apologize for it.

Re: Superpowers: How I'm using coding agents in October 2025

#172

Post by b_e_n_t_o_n »

simonw wrote: post #113
potatolicious wrote: post #54

Earlier quoted context omitted.

What you're getting at is the heart of the problem with the LLM hype train though, isn't it? "We should have rigorous evaluations of whether or not [thing] works." seems like an incredibly obvious thought. But in the realm of LLM-enabled use cases they're also expensive . You'd need to recruit dozens, perhaps even hundreds of developers to do this, with extensive observation and rating of the results. So rather than…

The UK government ran a study with thousands of developers quite recently: https://www.gov.uk/government/publications/ai-coding-assista...

Woah, finally something with actual metrics instead of vibes!

> Trial participants saved an average of 56 minutes a working day when using AICAs

That feels accurate to me, but again I'm just going on vibes :P

Re: Superpowers: How I'm using coding agents in October 2025

#174

Post by scuff3d »

qsort wrote: post #63
simonw wrote: post #31

Earlier quoted context omitted.

Here's one from today: https://mitchellh.com/writing/non-trivial-vibing

> Important: there is a lot of human coding, too. I'm not highlighting this to gloat or to prove a point. If anything in the past I have underestimated how big LLMs were going to be. Anyone so inclined can take the chance to point and laugh at how stupid and wrong that was. Done? Great. I don't think I've been intentionally avoiding coding assistants and as a matter of fact I have been using Claude Code since the lit…

> Many are acting as if writing any code manually means "you're holding it wrong", which I feel it's just not true.

It's funny because not far below this comment there is someone doing literally this.

Re: Superpowers: How I'm using coding agents in October 2025

#175

Post by 0x6c6f6c »

kibwen wrote: post #166
wbradley wrote: post #127

Earlier quoted context omitted.

I think the point is that ~/.claude should be dispersed among ~/.config/claude, ~/.local/state/claude, etc I agree with this, it’s frustrating that in 2025 apps are still polluting my home dir.

It's one thing to wish that apps would put their data anywhere except dumping it in your home dir, but this is exactly why I hate the XDG spec. I want all data for a program--be it the configuration or the cache or the binary itself--to be in a single directory such that 1) "uninstalling" the program, completely and in isolation, is nothing more than just deleting that single directory, and 2) any program not doing a…

This approach couples together everything though, in such a way there's no standard manner of wiping cache but not your app, configuration, etc.

XDG may not be perfect but wiping related data for apps following it is straightforward. There are a few directories to delete instead of 1, but still consistently structured at least.

Re: Superpowers: How I'm using coding agents in October 2025

#176

Post by simonw »

apwell23 wrote: post #171
simonw wrote: post #116

Earlier quoted context omitted.

I try very hard to fulfill the role of "thoughtful intellectuals presenting nuanced opinions" in the AI space. I'm disappointed that I've failed to meet that standard in your eyes.

it was fine to say this is something new and ppl should maybe look at it. but strongly recommending its and calling it wild is not a nuanced opinion. esp given you have not actually used it yourself in any serious way. is it really that big a ask to only use hype words for things you've actually used and made a big difference to you. edit: looks like my comments crossed into personally attacking you . i apologize for…

I stand firmly by "wild", by which I mean unexpected, surprising and unconventional:

- Giving Claude a skill that creates more skills is recursive and unconventional

- "Please read the book and pull out reusable skills that weren't obvious to you before you started reading" is a creatively weird and ambitious thing to do

- "It made sense to me that the persuasion principles I learned in Robert Cialdini's Influence would work when applied to LLMs" - that's a wild thing to say

- How is the concept of a "feelings journal" not wild?

- The original installation method for this (before plugins came along) was to prompt "Hey Claude. Please read https://raw.githubusercontent.com/obra/Superpowers/refs/head... and do what it says"

I'm actually pretty careful about the words I use, and I'm confident "wild" is justified in this case.

Re: Superpowers: How I'm using coding agents in October 2025

#177

Post by antonvs »

Retric wrote: post #168
antonvs wrote: post #157

Earlier quoted context omitted.

Agile’s point was to get feedback based on actual demoable functionality, and iterate on that. If you ignore the “slop” pejorative, in the context of LLMs, what I quoted seems to fit the intent of Agile.

There’s generally a big gap between the minimum you can demo and an actual feature.

If you want to use an LLM to generate a minimal demoable increment, you can. The comment I replied to mentioned "feature", but that's a choice based on how you direct the LLM. On the other hand, LLM capabilities may change the optimal workflow somewhat.

Either way, the ability to produce "working software" (as the manifesto puts it) in "frequent" iterations (often just seconds with an LLM!) and iterate on feedback is core to Agile.

Re: Superpowers: How I'm using coding agents in October 2025

#178

Post by Aloisius »

kragen wrote: post #170
Aloisius wrote: post #167

Earlier quoted context omitted.

If there some reason why one wouldn't be able to ignore the copyright license of something not protected by copyright, I'd love to hear it. The copyright office has been quite clear (rightly so imo) that AI output is not protected by copyright without substantial human creative expression in the final product and purely prompt-created works simply don't qualify. Indeed, I expect people muddling their codebases with A…

That's just the copyright office of one country out of a couple hundred, the courts can overrule them, and legislation can change. However, I agree that currently in the US (or on code written in the US) copyright probably doesn't inhere in AI-written code.

The US constitution limits copyright to protection for authors and inventors. I'm skeptical that a simple law could extend protection to machine generated works without being ruled unconstitutional nor does there appear to be any significant government or public support for such a thing.

And while yes, the US is just one country, but it does have a bit of an outsized software development industry. I also haven't hear of any other countries lining up to give machine-generated works copyright protection.

Re: Superpowers: How I'm using coding agents in October 2025

#179

Post by benrutter »

I'm so curious around what people's median experience is of AI coding tools.

I've tried agents every now and then, recently for something very simple- add an option to request csb format in a data api.

The results were, well, not good. . . I ended up undoing literally all changes because writing from scratch was a lot easier than trying to refactor the total mess it has made from what I'd have thought was a trivial feature.

I haven't done loads of prompt engineering etc, in all honesty it seems a lot of work when I haven't seen promise yet in the tool.

I see articles like this, and I always wonder, am I the outlier or is the writer? My experience of agentic AI is so hugely different to what some people are finding.

Re: Superpowers: How I'm using coding agents in October 2025

#180

Post by conorcleary »

kasey_junk wrote: post #105
tcdent wrote: post #32

This style of prompting, where you set up a dire scenario in order to try to evoke some "emotional" response from the agent, is already dated. At some point, putting words like IMPORTANT in all uppercase had some measurable impact, but at the present time, models just follow instructions. Save yourself the experience of having to write and maintain prompts like this.

What’s irritating is that the llms haven’t learned this as bout themselves yet. If you ask an llm to improve its instructions those sort of improvements are what it will suggest. It is the thing I find most irritating about working with llms and agents. They seem forever a generation behind in capabilities that are self referential.

Comments like yours on posts like these by humans like us will create a philosophical lens out of the ether that future LLMs will harvest for free and then paywall.
Post reply on HN