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

Gas Town Decoded

alilleybrinker.com

Post reply on HN
Print view View original

211–220 of 245 posts

Re: Gas Town Decoded

#211

Post by colin_jack »

sonnig wrote: post #205
colin_jack wrote: post #202

Earlier quoted context omitted.

"Agent 1, refactor that method to be more efficient. Agent 5, tighten up the graphics on level 3!" I'm not sure its even that, his description of his role in this is: "You are a Product Manager, and Gas Town is an Idea Compiler. You just make up features, design them, file the implementation plans, and then sling the work around to your polecats and crew. Opus 4.5 can handle any reasonably sized task, so your job is…

Assuming both agents are using the same model, what could the reviewer agent add of value to the agent writing the code? It feels like "thinking mode" but with extra steps, and more chance of getting them stuck in a loop trying to overcorrect some small inane detail.

He does cover this later:

"I implemented a formula for Jeffrey Emanuel’s “Rule of Five”, which is the observation that if you make an LLM review something five times, with different focus areas each time though, it generates superior outcomes and artifacts. So you can take any workflow, cook it with the Rule of Five, and it will make each step get reviewed 4 times (the implementation counts as the first review)."

And I guess more generally, there is a level of non-determinism in there anyway.

Re: Gas Town Decoded

#212

Post by chrisjj »

Otterly99 wrote: post #177
nl wrote: post #56

Earlier quoted context omitted.

I think Andrew Ng wrote a great piece on this. For example, in the US, which do you think uses more water: Golf Courses or Data Centers? a) Gold Courses use twice as much water as Data Centers b) About the same c) Data Centers use twice as much water as Gold Courses The answer is "None of the above": "Golf courses in the U.S. use around 500 billion gallons annually of water to irrigate their turf [snip] data centers…

Thank you for pointing that out. It irritates me every time I see the "water waste" argument. A toilet tank contains 5-13L of water, so if everybody started flushing only half the time they piss, that's an average of 4.5L of water saved per usage! That's roughly 900 LLM queries (using the 5 gram of water figure). Yet, I don't see anybody urging other to flush less, even thought it would have a much bigger impact. And…

> It irritates me every time I see the "water waste" argument

You didn't see it here, note.

Re: Gas Town Decoded

#213

Post by majormajor »

lordnacho wrote: post #170
Ntrails wrote: post #167

Earlier quoted context omitted.

> Programming is just shifting to a language that looks more like Jira tickets than source code. Sure, but now I need to be fluent in prompt-lang and the underlying programming language if you want me to be confident in the output (and you probably do, right?)

No, you have to be fluent in the domain. That is ultimately where the program is acting. You can be confident it works if it passes domain level tests. You save all the time that was wasted forcing the language into the shape you intended. A lot of trivial little things ate up time, until AI came along. The big things, well, you still need to understand them.

> You can be confident it works if it passes domain level tests.

This is generally true for things you run locally on your machine IF your domain isn't super heavy on external dependencies or data dependencies that cause edge cases and cause explosions in test cases. But again, easier to inspect/be sure of those things locally for single-player utilities.

Generally much less true for anything that touches the internet and deals with money and/or long-term persistent storage of other people's data. If you aren't fluent in that world you'll run software built on old versions of third party code with iterations to make further changes that have to be increasingly broad in scope against a set of test cases that is almost certainly not as creative as a real attacker.

Personally I would love to see stuff move back to local user machines vs the Google-et-al-owned online world. But I don't think "cheap freeware" was the missing ingredient that prevented the corporate consolidation. And so people/companies who want to play in that massively-online world (where the money is) are still going to have to know the broader technical domain of operating online services safely and securely, which touches deep into the code.

So I, personally, don't have to be confident in one-off or utility scripts for manual tasks or ops that I write, because I can be confident in the domain of their behavior since I'm intimately familiar with the surrounding systems. Saves me a TON of time. Time I can devote to the important-to-get-correct code. But what about the next generation? Not familiar with the surrounding systems, so not even aware of what the domains they need to know (or not know) in depth are? (Maybe they'll pay us a bunch of money to help clean up a mess, which is a classic post-just-build-shit-fast successful startup story.)

Re: Gas Town Decoded

#214

Post by Capricorn2481 »

Kostchei wrote: post #140
brushfoot wrote: post #136

Gas Town seems like a more confusing/expensive alternative to GitHub Copilot Agents. https://github.com/copilot/agents Go to the URL, type what you want done, and a cloud Claude agent creates a PR. $10/month.

try the tools. Really. If you are remotely interested in tech or AI, try the tools Copilot this is not. You may be trolling of course. There are huge steps between these various tools, if you try them, for a smidge of investment, it will become obvious what the trajectory is. It is like saying "I don't handwrite anything, I care too much about line spacing, I only use a dot matrix printer" when some one is trying to…

In your post history you say you have never programmed. Why are you so sure it produces code of value?

This is so prohibitively expensive in its wastefulness that blithely telling strangers to try the tools likely means you either haven't tried it, or have money to burn.

Re: Gas Town Decoded

#215

Post by spmurrayzzz »

aaronblohowiak wrote: post #210
spmurrayzzz wrote: post #198

Earlier quoted context omitted.

This has also been an interesting social experiment in that we get to see what work people think is actually impressive vs trivial. Folks who have spent years effectively snapping together other people’s APIs like LEGOs (and being well-compensated for it) are understandably blown away by the current state of AI. Compare that to someone writing embedded firmware for device microcontrollers, who would understandably be…

>Compare that to someone writing embedded firmware for device microcontrollers, who would understandably be underwhelmed by the same. One datum for you: I recently asked Claude to make a jerk-limited and jerk-derivative-limited motion planner and to use the existing trapezoidal planner as reference for fuzzy-testing various moves (to ensure total pulses sent was correct) and it totally worked. Only a few rounds of gu…

My comment above I hope wasn't read to mean "LLMs are only good at web dev." Only that there are different capability magnitudes.

I often do experiments where I will clone one of our private repos, revert a commit, trash the .git path, and then see if any of the models/agents can re-apply the commit after N iterations. I record the pass@k score and compare between model generations over time.

In one of those recent experiments, I saw gpt-oss-120b add API support to swap tx and rx IQ for digital spectral inversion at higher frequencies on our wireless devices. This is for a proprietary IC running a quantenna radio, the SDK of which is very likely not in-distribution. It was moderately impressive to me in part because just writing the IQ swap registers had a negative effect on performance, but the model found that swapping the order of the IQ imbalance coefficients fixed the performance degradation.

I wouldn't say this was the same level of "impressive" as what the hype demands, but I remain an enthusiastic user of AI tooling due to somewhat regular moments like that. Especially when it involves open weight models of a low-to-moderate param count. My original point though is that those moments are far more common in web dev than they are elsewhere currently.

EDIT: Forgot to add that the model also did some work that the original commit did not. It removed code paths that were clobbering the rx IQ swap register and instead changed it to explicitly initialize during baseband init so it would come up correct on boot.

Re: Gas Town Decoded

#216

Post by soulofmischief »

kibwen wrote: post #168
soulofmischief wrote: post #142

Earlier quoted context omitted.

On the other hand, flight is ubiquitous and has changed everything.

Flight changed everything when it comes to warfare. But as far as individuals are concerned, the average human on the planet will take a handful of flights in their lifetime, at best, and nearly all flights that are taken are for recreation which is ultimately fungible with other forms of recreation that don't involve taking flights, and of the flights that aren't for recreation most could be replaced by things like…

It's silly to say that the ability to fly has not changed society. Or that it won't continue to change society, if we manage to become space-faring before ruining our home planet.

The phrase, "The average human on the planet will take a handful of flights in their lifetime" is doing a lot of work. What are those flights to? How meaningful/important were the experiences? What cultural knowledge was exchanged? What about crucial components that enable industries we depend on? For example, a nuclear plant might constantly be ordering parts that are flown in overnight.

In general you're really minimizing the importance of aviation without really providing anything to back up your claims.

Re: Gas Town Decoded

#217

Post by jrowen »

nhinck3 wrote: post #106
jrowen wrote: post #77

Earlier quoted context omitted.

What games are notable in this regard? The classic Majesty series comes to mind. UO aspired to complex NPC systems. Fable as well. I always dreamt of a more advanced Sim City-meets-MMO that just went all in on that.

UO? I don't remember any complex NPC systems there. Ultima 7 had daily schedules and the veneer of a functioning economy though

Well, I said aspired to. They had ambitions that eventually got walked back to more basic behaviors. Here's an article from Raph Koster on it:

https://www.raphkoster.com/2006/06/09/why-dont-our-npcs/

Re: Gas Town Decoded

#218

Post by soulofmischief »

troupo wrote: post #178
soulofmischief wrote: post #139

Earlier quoted context omitted.

I am responding to what you wrote: > We are perpetually just months away from software jobs being obsolete. only hype artists are saying this. and you're using it as a way to negate the argument of more skeptical people.

Functional illiteracy and lack of any capacity to hold any context longer than two sentences has long been a plague on HN. Now that we've outsourced our entire thinking process to "@grok is this true", it has now claimed almost the entirety of human race. soulofmischief: complains that AI-skeptics would say the Wright brothers were idiots because they didn't imediately implement a supersonic jet ares623: we were prom…

Apply your own "functional literacy". I made a clarification that those outside of an industry have to separate the opinions of professionals and hype artists.

The irony of your comment would be salient, if it didn't feel like I was speaking with a child. This conversation is over, there's no reason to continue speaking with you as long you maintain this obnoxious attitude coupled with bad reading comprehension.

Re: Gas Town Decoded

#219

Post by cthalupa »

bonzini wrote: post #149
skywhopper wrote: post #147

Earlier quoted context omitted.

But the color thing is self-evidently untrue. It’s not even hard to talk about. Unless you yourself are colorblind I think that would be obvious?

Sort of, at least some degree of relativism exists though how much is debated. Would you ever talk about sea having the same color as wine? But that's exactly what Homer called it. https://en.wikipedia.org/wiki/Wine-dark_sea https://en.wikipedia.org/wiki/Linguistic_relativity_and_the_...

This is still quite clearly something different than being unable to see the different colors, though.

Their mental model, sure. The way they convey it to others, sure.

But you can easily distinguish between two colors side by side that are even closer in appearance than wine and the sea, even if you only know one name for them. We can differentiate between colors before we even know the words for them when we're young, too.

Re: Gas Town Decoded

#220

Post by aprdm »

spmurrayzzz wrote: post #198
dchuk wrote: post #98

I’m very bought in to the idea that raw coding is now a solved problem with the current models and agentic harnesses. Let alone what’s coming in the near term. That being said, I think we’re in a weird phase right now where people’s obvious mental health issues are appearing as “hyper productivity” due to the use of these tools to absolutely spam out code that isn’t necessarily broadly coherent but is locally impress…

This has also been an interesting social experiment in that we get to see what work people think is actually impressive vs trivial. Folks who have spent years effectively snapping together other people’s APIs like LEGOs (and being well-compensated for it) are understandably blown away by the current state of AI. Compare that to someone writing embedded firmware for device microcontrollers, who would understandably be…

This is not true. You can see people who are much older and built a lot of the "internet scale" equally excited about it, e.g: freebsd OG developers, Steve himself (who wrote gas town) etc.

In fact, I would say I've seen more people who are "OG Coders" excited (and in their >50s) then mid generation

Post reply on HN