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

221–230 of 239 posts

Re: Agent Skills

#221

Post by ditchfieldcaleb »

ai_fry_ur_brain wrote: post #199
cortesoft wrote: post #84

Earlier quoted context omitted.

I can understand skepticism to a degree, and even fundamentally believing that AI is bad for all sorts of reasons, but I am becoming more and more perplexed at the certainty behind statements like this one. How are you so certain that AI development is this doomed? It just hasn't matched my experience at all, and I wonder what your experience is that has driven you to this level of certainty about the certain doom of…

I dont know any serious engineers thay are doing real work with AI agents. I know some that are building features for web applications and just punching a clock, but I don't think that constitutes real work or provides much value to the world. I like thinking, solving problems and typing out code myself. Im going to keep putting tons of care into my craft and I promise I'll have more impact than the guy running 3 age…

> I like thinking, solving problems and typing out code myself.

I get this, I totally do, and I kind of hate relegating myself to doing "project manager" work instead of "software engineer" work, but the productivity gains make it no contest on whether to use AI here. Once I comprehensively validate the spec for a new feature, Codex just one-shots it basically every time. I'm talking thousands of lines of code in a single 3-hour session, with much of my time being spent browsing the internet while I wait for Codex to run in 15-20 minute sessions.

I'd estimate at least a 20x speedup in my ability to ship.

(and before you say it, yes, I review every single line of code before merging anything, so no - it's not AI slop)

Re: Agent Skills

#222

Post by applex1025 »

lukewarm707 wrote: post #170
ai_fry_ur_brain wrote: post #39

Cant wait for everyone to realize they've wasted a year + messing with agents and experiencing a feeling of psuedo productivity.

if i wanted to find out the answer to my question, i would need to: - open the browser - google "john repo" - find the website - copy the repo name - open the terminal - cd - git clone - try to find the file i want - read the whole file to find the answer = answer i now do: - "john repo question" = answer

[dead]

Re: Agent Skills

#223

Post by ditchfieldcaleb »

lukewarm707 wrote: post #170
ai_fry_ur_brain wrote: post #39

Cant wait for everyone to realize they've wasted a year + messing with agents and experiencing a feeling of psuedo productivity.

if i wanted to find out the answer to my question, i would need to: - open the browser - google "john repo" - find the website - copy the repo name - open the terminal - cd - git clone - try to find the file i want - read the whole file to find the answer = answer i now do: - "john repo question" = answer

TBH this alone is worth $20 (but don't tell OpenAI that).

Re: Agent Skills

#224

Post by hansmayer »

vidarh wrote: post #198
hansmayer wrote: post #159

Earlier quoted context omitted.

> 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. :) :) :) I could tell immediately you are somehow vested in the "success" of the LLM. So 600 B dollars and five years later, can you tell me how far did you guys get? Apollo programme costed a tiny fraction of that and started putting people on the moon some ~10…

I wish I had used 600B. I've spent a few thousand, and my efforts are very much profitable and earning me a substantial living right now.

So you spent a few thousand and now you are the next Ada Lovelace?

Re: Agent Skills

#225

Post by cavisne »

The problem with all these skill frameworks is when you are deep enough into AI coding to write one - your brain just cannot handle actually putting effort into it. These are all written by AI, and the authors skim read them.

It’s better to do the maybe 2 hours of human effort the authors put into them yourself for your own workflow.

Re: Agent Skills

#226

Post by suttontom »

Quarrel wrote: post #92
wg0 wrote: post #82

Earlier quoted context omitted.

We can build all the scaffolding around but I assure you that the LLMs aren't perfect rule following machines is the fundamental problem here and that would remain. Give it a few more months and I'm sure you'll see some of what I see if not all. I'm saying all the above having all sorts of systems tried and tested with AI leading me to say what I said.

> LLMs aren't perfect rule following machines is the fundamental problem here I kind of get what you're saying, but let us not pretend that SW engineers are perfect rule followers either. Having a framework to work within, whether you are an LLM or a human, can be helpful.

If someone regularly ignored critical instructions even though they were written down and had been told to follow them, that person would be fired.

Re: Agent Skills

#227

Post by sharperguy »

forlorn_mammoth wrote: post #185
sharperguy wrote: post #142

Earlier quoted context omitted.

Skills are often invoked imperatively by the user. In cases where they are intended to be used directly by the LLM, it would be included somewhere else in the context. E.g: ``` After implementing the feature, read the testing skill for instructions on how to test. ```

how do you guarantee that the LLM follows an instruction given imperatively by the user? It probably will, but this is not guaranteed behavior. Likewise, _how_ it follows that instruction is non-deterministic. it's turtles all the way down.

Nobody is arguing it's guaranteed. This is why you never give an LLM access to any essential infrastructure. Make sure everything it does can be undone. Double check when guarantees are required.

Re: Agent Skills

#228

Post by vidarh »

ai_fry_ur_brain wrote: post #202
vidarh wrote: post #172

Earlier quoted context omitted.

Initial drop, as people learn to use the tools, and while they keep babysitting their harnesses. Then significant boost once people start getting used to running the agents in the background, especially once they start running multiple sessions in parallel. I'd say you need a ~6 month push of getting people trained if they are not used to this way of working, and to customised setups etc. for your organisation, and t…

Was there previously huge backlog of work to do, or are you just building tons features for the hell of it because you can?

I've never once in 30+ years worked on a project where there weren't a lot of work we didn't get to because of lack of resources. So, yes, there's always been huge backlogs.

Re: Agent Skills

#229

Post by vidarh »

intended wrote: post #213
vidarh wrote: post #197

Earlier quoted context omitted.

> (there is no singular thread behind my comment. I think we probably have more in agreement than not, and its more a question of finding the precise words to declare the shapes we perceive.) I moved this up top, because I agree, despite the length of the below: > However, the current hype cycle has created expectations of reliability from LLMs that drive 'Automated Intelligence' styled workflows. Because for a lot o…

> Because for a lot of things it works. Today. I have a setup > There needs to be a rigorous process behind it, and I think we'll agree on that too. I would simplify it to: “I have a setup” is the part that is doing the actual heavy lifting. From my very unscientific survey / extensive pestering of network, the only people getting lift out of AI are people with both domain expertise/experience and familiarity with th…

I would agree with all of this. We could argue over whether/when there's sufficient intelligence for fully autonomous systems, but those systems will keep being tools for experts for the foreseeable future, and the question is just how small or large the autonomous components of that are, not whether or not you still need experts to wield them.

Re: Agent Skills

#230

Post by vidarh »

hansmayer wrote: post #224
vidarh wrote: post #198

Earlier quoted context omitted.

I wish I had used 600B. I've spent a few thousand, and my efforts are very much profitable and earning me a substantial living right now.

So you spent a few thousand and now you are the next Ada Lovelace?

No, I spent a thousand and now my profit margins are higher.
Post reply on HN