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

Stevey's Birthday Blog

steve-yegge.medium.com

Post reply on HN
Print view View original

11–20 of 40 posts

Re: Stevey's Birthday Blog

#11

Post by minebreaker »

barrkel wrote: post #9

I think there's an interesting idea behind Gas Town (basically, using supervisor trees to make agents reliable, analogous to how Erlang uses them to make processes reliable), but it's lacking a proper quality ratchet (agents often don't mind changing or deleting tests instead of fixing code) and architectural function (agents tend to reinvent the wheel over and over again, the context window simply isn't big enough t…

> Steve Yegge's recent credulous foray into promoting a crypto coin

I didn't notice that. Can you give me a source?

Re: Stevey's Birthday Blog

#12

Post by sandinmyjoints »

minebreaker wrote: post #11
barrkel wrote: post #9

I think there's an interesting idea behind Gas Town (basically, using supervisor trees to make agents reliable, analogous to how Erlang uses them to make processes reliable), but it's lacking a proper quality ratchet (agents often don't mind changing or deleting tests instead of fixing code) and architectural function (agents tend to reinvent the wheel over and over again, the context window simply isn't big enough t…

> Steve Yegge's recent credulous foray into promoting a crypto coin I didn't notice that. Can you give me a source?

He wrote all about it in https://steve-yegge.medium.com/bags-and-the-creator-economy-...

Re: Stevey's Birthday Blog

#13

Post by tom_ »

minebreaker wrote: post #11
barrkel wrote: post #9

I think there's an interesting idea behind Gas Town (basically, using supervisor trees to make agents reliable, analogous to how Erlang uses them to make processes reliable), but it's lacking a proper quality ratchet (agents often don't mind changing or deleting tests instead of fixing code) and architectural function (agents tend to reinvent the wheel over and over again, the context window simply isn't big enough t…

> Steve Yegge's recent credulous foray into promoting a crypto coin I didn't notice that. Can you give me a source?

There's some related discussion here: https://news.ycombinator.com/item?id=46654878

Re: Stevey's Birthday Blog

#14

Post by lovich »

leoc wrote: post #10
lovich wrote: post #7

Every time I read another article from this guy I get even more frustrated telling if he’s grifting or legitimately insane Between quotes like these > I had lunch again (Kirkland Cactus) with my buddies Ajit Banerjee and Ryan Snodgrass, the ones who have been chastising teammates for acting on ancient 2-hour-old information. , and trying to argue that this is the future of all productivity while taking time to physic…

Even if something like Gas Town isn't remotely affordable today it could potentially be a useful glimpse at what can be done in principle and what might be affordable in, say, 10 years. There's a long history of this in computing, of course https://en.wikipedia.org/wiki/Expensive_Typewriter https://en.wikipedia.org/wiki/Sketchpad https://en.wikipedia.org/wiki/Xerox_Alto . OTOH it could certainly make the approach tot…

Nothing I have read about LLMs and related makes it seem like they will be affordable in the future when it comes to software specifically.

I will preface this that I think AI agents can accomplish impressive things, but in the same way that the Great Pyramid of Giza was impressive while not being economically valuable.

Software is constantly updating. For LLMs to be useful they need to be relatively up to date with software. That means training and from what I understand the training is the vast majority of costs and there is no plausible technical solution around this.

Currently LLMs seem amazing for software because AI companies like OpenAI or Anthropic are doing what Uber and Lyft did in their heyday where they sold dollars for pennys, just to gain market share. Mr. Yegge and friends have made statements about if cost scares you, then step away. Even in the article this thread is about he has this quote

> Jeffrey, as we saw from his X posts, has bought so many Claude Pro Max $200/month plans (22 so far, or $4400/month in tokens) that he got auto-banned by Anthropic’s fraud detection.

And so far what I’ve seen is that he’s developed a system that lets him scale out the equivalent of interns/junior engineers en masse under his tentative supervision.

We already had the option to hire a ton of interns/junior engineers for every experienced engineer. It was quite common 1.5-3 decades ago. You’d have an architect who sketched out the bones of the application down to things like classes or functions, then let the cheap juniors implement.

Everyone moved off that model because it wasn’t as productive per dollar spent.

Mr. Yegge’s Gas Town, to me, looks like someone thought “what if we could get that same gaggle of juniors, for the same cost or more, but they were silicon instead of meat”

Nothing he’s outlined has made me convinced that the unit economics of this are going to work out better than just hiring a bunch of young bright people right out of college, which corporations are increasingly loathe to do.

If you have something to point to for why they thought is incorrect, in regards to this iteration of AI, then please link it.

Re: Stevey's Birthday Blog

#15

Post by slfnflctd »

vessenes wrote: post #3

Good summary. Upshot: Steve thinks he’s built a quality task tracker/work system (beads), and is iterating on architectures, and has gotten convinced an architecture-builder is going to make sense. Meanwhile, work output is going to improve independently. The bet is that leverage on the top side is going to be the key factor. To co-believe this with Steve, you have to believe that workers can self-stabilize (e.g. wit…

> Stay rested Steve, keep on this side of the manic curve please, we need you

This is my biggest takeaway. He may or may not be on to something really big, but regardless, it's advancing the conversation and we're all learning from it. He is clearly kicking ass at something.

I would definitely prefer to see this be a well paced marathon rather than a series of trips and falls. It needs time to play out.

Re: Stevey's Birthday Blog

#16

Post by mcphage »

This all reminds me of the offhand comment from an old XKCD: “You own 3D googles, which you use to view rotating models of better 3D googles.” He’s got this gigantic angentic orchestration system, which he uses to build… an agentic orchestration system. Okay.

Re: Stevey's Birthday Blog

#17

Post by wrs »

barrkel wrote: post #9

I think there's an interesting idea behind Gas Town (basically, using supervisor trees to make agents reliable, analogous to how Erlang uses them to make processes reliable), but it's lacking a proper quality ratchet (agents often don't mind changing or deleting tests instead of fixing code) and architectural function (agents tend to reinvent the wheel over and over again, the context window simply isn't big enough t…

I read this post as saying he won’t take funding from VCs, but he will from (his own word) crypto-bros?

Re: Stevey's Birthday Blog

#18

Post by leoc »

lovich wrote: post #14
leoc wrote: post #10

Earlier quoted context omitted.

Even if something like Gas Town isn't remotely affordable today it could potentially be a useful glimpse at what can be done in principle and what might be affordable in, say, 10 years. There's a long history of this in computing, of course https://en.wikipedia.org/wiki/Expensive_Typewriter https://en.wikipedia.org/wiki/Sketchpad https://en.wikipedia.org/wiki/Xerox_Alto . OTOH it could certainly make the approach tot…

Nothing I have read about LLMs and related makes it seem like they will be affordable in the future when it comes to software specifically. I will preface this that I think AI agents can accomplish impressive things, but in the same way that the Great Pyramid of Giza was impressive while not being economically valuable. Software is constantly updating. For LLMs to be useful they need to be relatively up to date with…

But why should one expect no future improvement in training costs (all else being equal) from Moore's Law, never mind any future use of eg. more efficient algorithms or more specialised hardware?

Re: Stevey's Birthday Blog

#19

Post by PrayagS »

barrkel wrote: post #9

I think there's an interesting idea behind Gas Town (basically, using supervisor trees to make agents reliable, analogous to how Erlang uses them to make processes reliable), but it's lacking a proper quality ratchet (agents often don't mind changing or deleting tests instead of fixing code) and architectural function (agents tend to reinvent the wheel over and over again, the context window simply isn't big enough t…

> have another look at that code

So true. beads[0] is such a mess. Keeps breaking often with each release. Can't understand how people can rely on it for their day-to-day work.

[0] https://github.com/steveyegge/beads

Re: Stevey's Birthday Blog

#20

Post by marcus_holmes »

lovich wrote: post #7

Every time I read another article from this guy I get even more frustrated telling if he’s grifting or legitimately insane Between quotes like these > I had lunch again (Kirkland Cactus) with my buddies Ajit Banerjee and Ryan Snodgrass, the ones who have been chastising teammates for acting on ancient 2-hour-old information. , and trying to argue that this is the future of all productivity while taking time to physic…

> telling if he’s grifting or legitimately insane

or if he's talking to us from 5 years in the future.

Ignoring the financial aspect, this all makes sense - one LLM is good, 100 is better, 1000 is better still. The whole analogy with the industrial revolution makes sense to me.

> AI firms are currently burning money as fast as possible selling a dollar for 10 cents.

The financial aspect is interesting, but we're dealing with today's numbers, and those numbers have been changing fast over the last few years. I'm a big fan of Ed Zitron's writing, and he makes some really good points, but I think condemning all creative uses of LLMs because of the finances is counterproductive. Working out how to use this technology well, despite the finances not making much sense, is still useful.

Post reply on HN