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

Agent Skills

addyosmani.com

Post reply on HN
Print view View original

131–140 of 239 posts

Re: Agent Skills

#131

Post by blitzar »

wg0 wrote: post #68

Snake 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. T…

All this said, I quite like the mental model of documenting a simple process, and I suspect our future ai overlords will find it useful that I have a series of md files that outline my preferences and processes for certain tasks.

I am not however going to share any of this with work colleagues and make myself redundant.

Re: Agent Skills

#133

Post by teodosin »

hansmayer wrote: post #127
vidarh wrote: post #93

Earlier quoted context omitted.

Humans also drop any hard requirements you specify regularly, and similarly require review. Nevertheless we manage to increase reliability of human output through processes and reviews, and most of the methods we use for harnesses are taken from experience with how to reduce reliability issues in humans, who are notoriously difficult to ensure delivers reliably.

[flagged]

Calm down. They were comparing a very specific and narrow aspect of both. Not totally equivalent maybe, but that doesn't justify a tantrum.

Re: Agent Skills

#135

Post by kigiri »

fragmede wrote: post #22
gavmor wrote: post #13

Naming things is such a hard problem that many devs don't even bother trying. That being said, this post is full of reasonable assertions, so I'm looking forward to experimenting with this... whatever it is.

Wait, shit, are people using LLMs to name things now? I'm definitely out of a job then!

Naming things is my principal use for AI, I don't always pick a name from the suggested ones but it sure help me find better ones.

Re: Agent Skills

#136

Post by vidarh »

hansmayer wrote: post #127
vidarh wrote: post #93

Earlier quoted context omitted.

Humans also drop any hard requirements you specify regularly, and similarly require review. Nevertheless we manage to increase reliability of human output through processes and reviews, and most of the methods we use for harnesses are taken from experience with how to reduce reliability issues in humans, who are notoriously difficult to ensure delivers reliably.

[flagged]

Because certain aspects (both are error prone) are similar and comparable. The notion that two entities need to be close in abilities for it to be possible to compare them is nonsense.

You make the point for me: We managed to put men on the moon despite humans being enormously unreliable and error prone, because we built system around them that allowed for harnessing the good bits and reducing the failures to acceptable levels.

We are - I am anyway - using our lessons from building reliable systems from unreliable elements to raise the reliability of outputs of LLMs the same way.

Re: Agent Skills

#137

Post by theshrike79 »

djhn wrote: post #125
tokioyoyo wrote: post #75

Earlier quoted context omitted.

I’m a bit curious with these takes. Arguing in good faith - is the general assumption that people who use AI/agents/harnesses don’t ship features? We’ve been all in Claude Code since ~Septemberish, and have been able to successfully track the boost. Like the features that we ship that get used in production. Both from infrastructure side, and business logic implementations. Frontend and backend. I don’t think people…

I can take on a slightly weaker form in good faith: professionally it’s a non-starter until private, open source inference can be self-hosted and the ROI is clear enough to invest in that. And on the ROI side, trying things out regularly, I haven’t seen the positive ROI in the limited time I’ve dedicated to exploring the tools. I’ve restricted experimenting to 4 hours per month, because spending more than 2.5% of the…

"I studied math 4 hours per month and I can confirm that mathematics is stupid"

You can't learn how to use _anything_ by experimenting 4 hours a month.

Re: Agent Skills

#138

Post by j45 »

keeda wrote: post #122
wg0 wrote: post #68

Snake 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. T…

Snake oil may be a bit strong, because snake oil never works (except maybe as placebo?) whereas anything with an LLM, even though stochastic, has a pretty high chance of working. > ... 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. Not really, though it depends on the code; reading…

Pretty high chance isn’t what the intent or impression the end user often has.

Re: Agent Skills

#139

Post by j45 »

vidarh wrote: post #117
kaashif wrote: post #106

Earlier quoted context omitted.

The primary way to increase reliability is to automate. Instead of humans producing some output manually, humans producing machines which produce that output. I've seen a disturbing trend where a process that could've been a script or a requirement that could've been enforced deterministically is in fact "automated" through a set of instructions for an LLM.

Sure, when that is possible. However, there are lots of processes we don't know how to automate in a deterministic way. Hence the vast amount of investment in building organisations of people with mechanism to make peoples output more reliable through structure, reviews, and so on. Large parts of human civilization rests on our ability to make something unreliable less unreliable through organisational structure and…

Underrated comment.

So many applications of LLMs have even to start with deterministic brain when using a non-deterministic llm and then wonder why it’s not working.

Post reply on HN