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

You should write an agent

fly.io

Post reply on HN
Print view View original

161–170 of 409 posts

Re: You should write an agent

#161

Post by lowbloodsugar »

vinhnx wrote: post #112

> “You only think you understand how a bicycle works, until you learn to ride one.” This resonates deeply with me. That's why I built one myself [0], I really really love to truly understand how coding agents work. The learning has been immense for me, I now have working knowledge of ANSI escape codes, grapheme clusters, terminal emulators, Unicode normalization, VT protocols, PTY sessions, and filesystem operations…

It's conflating two issues though. Most people who can ride a bike can't explain the physics. They really don't know how it works. The bicycle lesson is about training the brain on a new task that cannot be taught in any other way.

This case is more like a journeyman blacksmith who has to make his own tools before he can continue. In doing so, he gets tools of his own, but the real reward was learning what is required to handle the metal such that it makes a strong hammer. And like the blacksmith, you learn more if you use an existing agent to write your agent.

Re: You should write an agent

#162

Post by AdieuToLogic »

furyofantares wrote: post #95
wayy wrote: post #88

everybody loves building agents, nobody likes debugging them. agents hit the classic llm app lifecycle problem: at first it feels magical. it nails the first few tasks, doing things you didn’t even think were possible. you get excited, start pushing it further. you run it and then it fails on step 17, then 41, then step 9. now you can’t reproduce it because it’s probabilistic. each step takes half a second, so you si…

That's why you build extensive tooling to run your change hundreds of times in parallel against the context you're trying to fix, and then re-run hundreds of past scenarios in parallel to verify none of them breaks.

In the event this comment is slathered in sarcasm:

  Well done!  :-D

Re: You should write an agent

#163

Post by olingern »

rbren wrote: post #79

Spoiler: it's not actually that easy. Compaction, security, sandboxing, planning, custom tools--all this is really hard to get right. We're about to launch an SDK that gives devs all these building blocks, specifically oriented around software agents. Would love feedback if anyone wants to look: https://github.com/OpenHands/software-agent-sdk

Only on HN is there a “well, actually” with little substance followed by a comment about a launch.

The article isn’t about writing production ready agents, so it does appear to be that easy

Re: You should write an agent

#164

Post by HDThoreaun »

furyofantares wrote: post #134
roadside_picnic wrote: post #124

Earlier quoted context omitted.

So you're assuming there's a world where these companies exist solely by providing inference? The first obvious limitation of this would be that all models would be frozen in time. These companies are operating at an insane loss and a major part of that loss is required to continue existing. It's not realistic to imagine that there is an "inference" only future for these large AI companies. And again, there are many…

> So you're assuming there's a world where these companies exist solely by providing inference? Yes, obviously? There is no world where the models and hardware just vanish.

If the game is inference the winners are the cloud mega scalers, not the ai labs.

Re: You should write an agent

#165

Post by tomcam »

javchz wrote: post #152
coffeecoders wrote: post #138

Earlier quoted context omitted.

Yeah, it’s a never-ending curve. I built an 8-bit computer on breadboards once, then went down the rabbit hole of flight training for a PPL. Every time I think I’m "done," the finish line moves a few miles further. Guess we nerds are never happy.

One should be melting sand to get silicon, anything else it's too abstract to my taste.

Glad you’ve got all that time on your hands. I am still working on the fusion reactor portion of my supernova simulator, so that I can generate the silicon you so blithely refer to.

Re: You should write an agent

#166

Post by azimux »

I wrote an agent from scratch in Ruby several months back. Was fun!

These 4 lines wound up being the heart of it, which is surprisingly simple, conceptually.

        until mission_accomplished? or given_up? or killed?
          determine_next_command_and_inputs
          run_next_command
        end

Re: You should write an agent

#167

Post by awayto »

aidenn0 wrote: post #140
awayto wrote: post #44

Earlier quoted context omitted.

Also if you're doing function calls you can just have the command as one response param, and arguments array as another response param. Then just black/white list commands you either don't want to run or which should require a human to say ok.

blacklist is going to be a bad idea since so many commands can be made to run other commands with their arguments.

Yeah I agree. Ultimately I would suggest not having any kind of function call which returns an arbitrary command.

Instead, think of it as if you were enabling capabilities for AppArmor, by making a function call definition for just 1 command. Then over time suss out what commands you need your agent do to and nothing more.

Re: You should write an agent

#168

Post by johnfn »

hoppp wrote: post #157
vel0city wrote: post #141

Earlier quoted context omitted.

Practically everything is something you will need to pay for in the end. You probably spent money on an internet connection, electricity, and computing equipment to write this comment. Are you intending to make a profit from commenting here? You don't need to run something like this against a paid API provider. You could easily rework this to run against a local agent hosted on hardware you own. A number of not-stupi…

The submission is an advertisement for fly.io and OpenAI , both are paid services. We are commenting on an ad. The person who wrote it did it for money. Fly.io operates for money, OpenAi charges for their API. They posted it here expecting to find customers. This is a sales pitch. At this point why is it an issue to expect a developer to make money on it? As a dev, If the chain of monetization ends with me then there…

Why are you repeatedly stating that the post is an ad as if it is some sort of dunk? Companies have blogs. Tech blogs often produce useful content. It is possible that an ad can both successfully promote the company and be useful to engineers. I find the Fly blog to be particularly well-written and thoughtful; it's taught me a good deal about Wireguard, for instance.

Re: You should write an agent

#169

Post by AdieuToLogic »

ht96 wrote: post #110
furyofantares wrote: post #95

Earlier quoted context omitted.

That's why you build extensive tooling to run your change hundreds of times in parallel against the context you're trying to fix, and then re-run hundreds of past scenarios in parallel to verify none of them breaks.

Do you use a tool for this? Is there some sort of tool which collects evals from live inferences (especially those which fail)

There is no way to prove the correctness of non-deterministic (a.k.a. probabilistic) results for any interesting generative algorithm. All one can do is validate against a known set of tests, with the understanding that the set is unbounded over time.

Re: You should write an agent

#170

Post by jbmsf »

I agree. I find LLMs a bit overblown. I don't think most people want to use chat as their primary interface. But writing a few agents was incredibly informative.
Post reply on HN