Earlier quoted context omitted.
You’ll get downvoted for this hearsay!
I think you mean heresy. But maybe I don't get the reference you're making when you say hearsay
Hearsay is a rumor or something that can't be verified.
Agent Skills
61–70 of 239 posts
Re: Agent Skills
#62Why are people so excited to put themselves out of a job? Not that these or any "skills" will do that, but just- in principle. This is like alienation from labor at scale.
Because usually the people who lose their jobs are people who do not adapt to the market. Right now it's not clear in which direction everything is involving and that's why people experiment with handing all their data to random agents, figuring out how to store and access context, re-use prompts and other attempts to harness this tech. Most of these will maybe be useless in a year as they might be deeply integrated…
People are building bots to do the most legible thing possible which is feature in X amount of time. But it doesn't matter if the bottleneck is human thinking time required to output quality code rather than X amount of code written.
Re: Agent Skills
#63Earlier quoted context omitted.
I would love to know how many people are actually using superpowers. I showed up on the agentic dev scene prior to superpowers, and I am getting concerned that >50% of my self-rolled processes are now covered by superpowers. I no longer trust gh stars, can anyone chime in? Is superpowers now truly adopted? If it is truly valuable, why hasn't Boris integrated the concepts yet?
I just removed superpowers from my own setup. In my opinion, given the quality of the planning modes in both claude code and codex, superpowers was really just slowing things down and burning more tokens than vanilla.
It never worked well for me. The only thing I really needed outside of the harnesses was a better plan review surface. https://github.com/backnotprop/plannotator
Re: Agent Skills
#64I was surprised how long some of these skills are. They are pages and pages long with tables and checkbox lists and code examples, etc. Curious how normal that is - it would only take a couple of these to really fill the context alot.
> it would only take a couple of these to really fill the context alot.
Only skill front-matter (name, description, triggers etc) are loaded within context by default, so this isn't likely to happen without 1000s of skills.
Re: Agent Skills
#65[flagged]
Re: Agent Skills
#66Cant wait for everyone to realize they've wasted a year + messing with agents and experiencing a feeling of psuedo productivity.
They will lie to themselves and deny it.
Re: Agent Skills
#67I really wish he wouldn't use AI to write his posts. It would be faster to just post the prompt he used to write the article
I wish this fucking meme of "post the prompt" would die. Very little work is one-shotted, very little has a singular "the prompt", most is iterated until it's close to the vision of what the author actually set out to write.
Re: Agent Skills
#68Snake oil. Good to read for sure. Seems all plausible too. But snake oil nevertheless.
Here's why: The slot machine can drop any hard requirement that you specifically in your AGENTS.md, memory.md or your dozens of skill markdowns. Pretty much guaranteed.
These harnesses approaches pretend as if LLMs are strict and perfect rule followers and the only problem is not being able to specify enough rules clearly enough. That's fundamental cognitive lapse in how LLMs operate.
That leaves only one option not reliable but more reliable nevertheless: Human review and oversight. Possibly two of them one after the other.
Everything else is snake oil but at that point, you also realize that promised productivity gains are also snake oil because reading code and building a mental model is way harder than having a mental model and writing it into code.
Re: Agent Skills
#69Lately I keep hearing the same thing over and over: the things that are good for managing a team of devs are good for LLMs.
Good test cases.
Clear and concise documentation.
CI/CD.
Best practices and onboarding docs.
Managing LLMs is becoming more and more similar to managing teams of people.
Re: Agent Skills
#70[dead]