Stevey's Birthday Blog
21–30 of 40 posts
Re: Stevey's Birthday Blog
#22Re: Stevey's Birthday Blog
#23I 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…
That would assume he's even looked at the code in the first place - I think his whole thesis is based on you never looking at the code.
Re: Stevey's Birthday Blog
#24I 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
#25Re: Stevey's Birthday Blog
#26I spent some time reading about Gas Town to see if I could understand what Stevey was trying to accomplish. I think he has some good ideas in there, actually - it really does seem like he's thought a bit about what coding in the future might look like. Unfortunately, it's so full of esoteric language and vibecoded READMEs that it is quite difficult to get into. The most concerning thing is that Stevey seems totally u…
Re: Stevey's Birthday Blog
#27I 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…
Re: Stevey's Birthday Blog
#28Earlier quoted context omitted.
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?
I guess we’ll make up the losses per unit at scale, and grow to infinity.
Re: Stevey's Birthday Blog
#29I 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…
He's obviously a smart guy, so he definitely should've known better. It's weird how these AI evangelists use AI for everything, but somehow he didn't ask ChatGPT what all of this means and if it may have reputational damage, because I just asked if I should claim these trading fees, and it said:
Claiming could be interpreted as:
* Endorsing the token
* Being complicit if others get rugged later
* This matters if your X account has real followers.
and in the end told me to NOT claim these fees unless I'm OK with being associated with that token.Re: Stevey's Birthday Blog
#30I 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…
Indeed, the Gas-Town token is down 97% from all-time high, see https://coinmarketcap.com/currencies/gas-town/ He's obviously a smart guy, so he definitely should've known better. It's weird how these AI evangelists use AI for everything, but somehow he didn't ask ChatGPT what all of this means and if it may have reputational damage, because I just asked if I should claim these trading fees, and it said: Claiming coul…
There's another thing. A certain type of engineer seems to get sucked into Amazon's pressure culture. They either are, or end up, a bit manic. Laid back and relaxed one day (especially after holidays), but wound up and under a lot of internal pressure to produce the next, and a lot more of the latter. Something like Gas Town must be a crazy fix when you're feeling that pain. Combined with the vision that if you don't, you're unemployed/unemployable in 12 to 24 months, you might feel you have no choice but to spend every waking minute at it.
It's a bit (more than a bit) rude to analyse someone at a distance. And to be honest, I think something like Gas Town is probably one of the possible shapes of things to come. I don't think what I can observe looks super healthy, is all.